I've been using OpenCode V2 since it first appeared on the website, and I can only repeat the positive views on usability, the client/server model and self-awareness/ability to edit it's config and write plugins.
I'd like to mention two other impressive things about OpenCode.
First, their issue tracker on GitHub works really well. They have the OpenCode GitHub App connected, and for any bug report it reads the issue, tests on the mentioned version and latest dev branch, and comments the findings along with a reproduction script. For TUI Bugs it even records a video. And all that in less than two minutes, usually.
Another thing they are working on is opentunnel, where you can tunnel services to https on <random>.opentunnel.xyz and its subdomains. What's notable is that the subdomain is persistent and unique to you, and a wildcard ssl cert is actually generated on your machine, so the platform cannot see the traffic. Their primary use case seems to be making the OpenCode Server usable from anywhere, but it can do much more with their cli:
I see people talking about this being new in v2 everywhere but it's not the case. What's new is that it's the default (and also not really since `opencode service` and `opencode serve` start two different things). But in v1 it was very possible to run one opencode instance and have multiple clients connect to it (like Openchamber and neovim).
Many of the annoyances from V1 are gone. Skills and plugins reload automatically (finally). Tasks can be backgrounded (though I think this doesn't happen automatically yet). There's a built-in skill for editing the configuration (finally I can retire mine). The front-end got some love. Apparently they re-architected the loop around Effect. Sub-sessions can be communicated with better. Configuration is loaded from the folder the session is created in rather than where the server was started.
In general, this update largely takes OpenCode into the current age features-wise and is a good overhaul quality-wise. Just in time to stop my early switching away efforts, which would've been a pain because I know few other harnesses with such a strong server/client model.
To me, there are more annoyances in V2, so many that I've switched harnesses to Pi (for now?). I think the hot-reload is another security misalignment. An agent should not be able to modify plugins and have that immediately reloaded for availability.
I tried switching to Pi twice. Both times it seemed agents go crazy with tools on Pi and do stupid things right out of the gate, (like get `find` syntax wrong, seriously who [what] does that??). Plus things I appreciate in opencode (even if they were buggy in 1.x) like "prompt for perms tool-by-tool in this session" seem to only be available in Pi by writing your own extension, and now I'm wasting time debugging my extension with an AI that gets tools wrong and constantly wants to search `/` for no good reason.
Then I upgraded OpenCode to 2.0 and pretty much all the bugs vanished. I still wish there was a happy medium between "parse tool calls for perms" (which fails all the time if the tool call is long/complex enough) and a full-on sandbox, but otherwise 2.0 is really solid.
DeepSeek Harness allows the user/agent to build its own plug-ins and run them without restart, mostly. Pi and OpenCode were then influenced to do the same in their respective new versions. I don't know which has the better implementation.
Yeah, but only I can click to move a task to the background when it takes longer, which could and IMO should happen automatically. The model can’t always judge that. (I see how my comment wasn’t clear enough that I mean this)
In general, the preventable “model gets stuck” class of annoyances has not been fixed quite yet - there are also stil no timeouts for permission requests, at least by default.
This is the only way. Auto mode is really just yolo mode with more LLM tokens billed. It may catch some weird shit but it isn't a reliable sandbox. Just lock up the LLM and let it run.
FWIW OC 2.0 remembers perms for a project/directory pretty solidly now, so flow-killing approvals are more a one-time thing for a given project. It's sad they can't be globally set though, so a new project pays the approval-by-tool tax.
It’s great, they’re embracing even more the “everything’s a plugin” principle that has been pushed by other harnesses like Deepseek. Shoutout to all the AI model companies out there: if your subscription can’t be used on open code, I’ll buy something else.
Many of the workarounds I had to develop for the v1 now come as native features in v2 (i.e. session rebinding to other folders), now the only thing that was missing is the ability of plugins to read the response you’re writing (useful if you want to have the double-Esc feature like in claude code).
Native apps connecting to the OpenCode server is a great way to run sessions on remote hosts!
I wish Claude Code would adopt the same model. The desktop app deploys a separate engine that restarts and clobbers long-running sessions upon reconnect (Remote Control is their recommended solution but requires a Claude.ai account).
I’ve been vibe coding a native macOS Claude Code app that spawns a server that wraps Claude Code on remote hosts, but the UX and features are always lagging behind.
I am quite keen on this as well, I have been trying to move all my active development to happen inside a container, including the harnesses. This, of course, makes it very hard to run GUI harnesses. I prefer CLI, but it would be neat to be able to better isolate gui-based harnesses as well.
I have been using VSCodium with https://github.com/jeanp413/open-remote-ssh so (most of) the IDE also runs inside the container. I have been trying to get everything inside the container, including the projects I work on, the IDE, the harness, the dependencies, etc. Both for security and for portability so I can have the same setup in both my work and home computers.
One thing I haven't been able to do is limit the blast radius of is git, github ssh keys give blanket access to all repos tied to my profile and ATM I set up the github SSH key inside the container.
Claude code agents have a protocol that's usable for the same purpose it just listen locally but it's usable i have my own claw-like that has options for claude, codex, and pi (my subscription, wife subscription, and i got a yearly sub on glm when it was cheap)
I've developed something similar for personal use. A harness who's only job is to delegate to other harnesses (i.e: AntiGravity, Codex, Claude Code, Hermes) to create an opencode-web-like interface across multiple hosts.
For Claude Code, don't use remote-connections. Your best option is to look at how the closed-source VSCode plugin interfaces with Claude Code. The way it works is that it reads files directly. This API, although unofficial, is likely very stable, because an old VSCode extension still has to interact with new version of Claude Code.
If there's any interest in this sort of thing, maybe I'll open-source it. I would have to cleanup the slop though.
I suspect heavy eyes free coding. I spent the last week helping them understand a major security regression in config loading, took two issues/pull requests. Our hunch is the Ai told them what they had was good, not enough human critical thinking.
Ive anecdotally never found OpenCode to have a real axis where I find it "best". But I havent tried it in a bit, mostly because I don't have a real gap in use case coverage between Codex/CC/Pi. Anything more specific in need probably gets a custom harness.
I think it's due to they are doing a funny business to parse the progress, that's pretty much vibed and no one care. Like instead of using curl's progress, they re-invented a progress tracking with the tracing interface (--trace-ascii), byte by byte :(
I don't think fast gpu rendering terminals should be mandatory for this kind of thing, and if you should have an option that facilitates the need for one then might I suggest falling back to something sensible rather than stalling out for forever when the user doesn't render glyphs as fast as you want them to?
If it doesn't work at least ok with something like xterm, someone really needs to reconsider some life decisions. Htop makes it work, why should a terminal emulator need to crack the engima just to render silly stuff?
Of course? I never ever upgrade any software unless I'm facing a bug or I want a new feature from the new release. Otherwise it's just taking risk for almost nothing in return.
Took me a little while to figure out this was a llm harness for coding (also called an agent, I suppose, but that term seems overloaded and ambiguous to me)
There are many of these available, alongside the provider ones.
Are there any benchmarks which help me decide which ones I should try over the standard codex/claude?
Seems foolish to use a single-vendor harness to be honest. With how fast things change, and the price/performance you get from open weight models, building a workflow around a single llm provider seems super limiting.
I use "harness" for the tool which calls the llm, has the tools, interacts with the computer (filesys, bash, etc), does the session bookeeping
and "agent" as the instance which is running... this is the more overloaded term because there are "agent" definitions, this is where a combinatorial exists, because the running "agent" is a combination of agent definitions, context, tool choice where you can modify each independently to create a new "agent"
From what I gathered, a simple harness like the one from Pi is sufficient.
Similarly, I would advise against using tons of skills and keep the ones you genuienly find useful (they are just .md files so you can copy them).
The only skill I use is /strategic-compact from everything claude code (ecc) because I like to read the summary before a manual compaction.
For example, consider something like SWEBench, where a test should pass. Harness or a skill can just tell the agent keep trying until the test pass. So same model can have a lot of behavior changes between the harnesses.
In my experience (i own a multi-agent IDE with 50+ supported harness) folks stick to first party, usually either openai or anthropic, grok, agy; if they are willing to pay for the subscription the value is unbeatable. And they don't risk trying different harnesses.
I made a harness too, and recently added eval with opencode and pi and I sat between them. No gaming other than trying to figure out why I was really bad on some evals (I was not returning thinking tokens which broke cache, for example, and different model families do things way different here). I have yet to try my harness for coding but I do have a few terabytes for it to read. And I’d rather use a local model that’s fast and good at retention, but that run could take a year, lol.
The main four seem to be Pi, Opencode, Claude Code, abd Codex.
I do often see benchmarks comparing them and usually Pi comes out on top, but I think the benchmarks are generally testing one moderately sized clear task. Pi is minimal and great in that situation.
For more general usage, where tasks are not clear, you might interrupt at any moment to steer it, etc. benchmarks are harder I guess. I personally love pi because anytime there's something I don't like, I spin up a separate session and fix it.
E.g. I've found the "reply in simple technical English" hack amazing but I have to keep saying it over and over. So I had an agent write an extension in about ten minutes that appends a short hidden message saying all user and dev facing text must be in STE, apply that without talking about STE. Works amazingly well.
I would state the same, but looking at commercial offerings for agents, such as MCP servers or skill instructions in the vender's own docs, opencode is often not mentioned at all.
Here is an example I encountered recently: The Figma MCP Server documents usage with Claude (Code), Codex, Cursor, Grok and Antigravity [], but notably not OpenCode. More so, their oauth registration seems to use some kind of whitelist, meaning just adding the MCP by url does not work either. To make it work, my agent edited the config entry to use "Codex" as the oauth name, which worked.
That's just one example, but something you see quite frequently.
the person said that there were too many samey harnesses and they couldn't see why or which to choose and you thought you'd fix that by adding another to the pile?
A pretty important feature is that the client process can crash without losing progress on my current session, similar to how I can reconnect to my tmux server without losing current active processes.
If you think about the evolution of AI coding, companies (who will eventually pay for these tools) will realize they want to run the coding tasks in a remote, controlled environment.
Every engineer typing on their machine and burning tokens (money) won't work in an enterprise setting.
> Every engineer typing on their machine and burning tokens (money) won't work in an enterprise setting.
Of course. Obviously, just a week ago and before that none of the harnesses did work in enterprise settings.
Irony aside, I don't think that there are that many tasks that will benefit from a daemon but which aren't solvable with screen or tmux. In other words, I think this feature should not exist, let alone be enabled by default.
Also, I actually am "an enterprise who pays money for these tools" and I strongly believe most of my engineers immediately disabled the background daemon. I know of a few who were unpleasantly surprised by the cli codex update.
I agree that it shouldn't be default, but I'm wondering why you think it shouldn't exist _at all_. The daemon mode for emacs, for instance, is incredibly useful for speeding up startup time and persisting things between windows. It's probably very similar here.
There’s two answers, depending on your personal cynicism.
The optimistic version is that the new zeitgeist is deeply recursive agents writing _huge_ swaths of code at once. The human side seems very asynchronous. You do a lot of queueing something that the agents churn on for an hour, so being able to detach/reattach would make sense.
The cynical version is everyone is realizing that nobody will pay for a harness, so they’re pivoting to a client-server model to try to PaaS-ify them. If they haven’t announced it already, they’ll have an OpenCode Cloud within the next quarter or two.
We’ll see how that goes. I’m not holding my breath that these will thrive as long as infrastructure teams exist. Agents are too simple from an infra perspective, and we’re seeing frameworks to make them stateless pop up already.
it feels like a clear improvement across the board but a heads up: i got bitten by upgrading - since all tool calls now go through the background process, the sandbox that i use to wrap the TUI process quietly became useless. took me a day or two to realize that web fetches, etc. which should have been blocked were succeeding.
There are at least 3 security regressions (imo) in the initial v2 release
1. configuration loading (now fixed) dropped support for system level, then restored it incorrectly, now it is better, but still some issues in user space
2. hot-reloading of plugins, agents can now change them with immediate effect
3. this, which I was unaware of
I wonder how many more there are given this much has been found already
I don't think that's the case. This is from anomalyco, the company who made sst.dev. Crush is from Charm. I think OpenCode may have originally been written in Go but nowadays their codebase is TypeScript.
Edit: I'm missing some context others have pointed out.
I'm really tired of this being retread time and time and time again.
It's just not interesting, it doesn't seem to matter, they are are separate projects and both doing great. The inside baseball about old history doesn't feel like it goes anywhere, adds anything. It didn't the last 5 times opencode got submitted!
It's my daily driver - very easy to customize. Added a pretty solid vim plugin for it and a few more really useful plugins. Here are my dotfiles https://github.com/dkarter/dotfiles
Can you share that vim plugin? Now running opencode at Ghostty and looking diffs at github and rarely when need to do code changes manually I am using vscode but proper vim plugin would be godsend.
I wish they’d invest more time in performance improvements over code mods. I recently switched to pi which uses an order of magnitude less RAM (hundreds vs dozens) and noticeably less CPU on my machine… OpenCode is really nice but it’s about as heavy as antigravity and is substandard in features…
When I opened the site, I started hearing a sound that I never heard before: My MacBook Pro M4's fans. I checked ActivityMonitor and Firefox was using a significant CPU share. Are they mining crypto in the background or what's happening?
OpenChamber ftw! I'm surprised it's not more popular - so much nicer to use than the TUI.
I'm always confused when people at work show me their opencode or Claude code setup of 6 terminal windows open simultaneously with the same illegible walls of text. No idea how people still prefer that over a nice GUI.
Once you really know your keyboard, it's like an extension of your hands. You can fly through those six terminals, and moving your hand to grab a mouse means stopping whatever you were doing. That wall of text is all familiar to me - I see an UI full of empty space and wonder what I could have used it for.
Of course there are great reasons for using pointers also. I'd say this is mostly a preference, I'm sure you are extremely effective using your own methods. I have maybe two dozen terminals open atm, and I can tell you what each of them is for - but put a phone bill or a bank statement in front of me and it might as well be Greek.
Interesting and I'll definitely give this a try, the client/server and plugin system do look very powerful.
However, I've been using OMP in combination with Tern (the terminal) lately and it's an incredibly smooth operation. It's hard to find a decent terminal on Windows (corporate device) but this is the best I've found so far.
Same OpenCode team who ignore bug reports, don't respond on their discord, don't have modern CI/CD test suites (often shipping regressions), don't have bots to triage bug reports or PRs, and have what might be the worst open model subscription service available today.
OpenCode users: switching to Pi takes about 5 minutes, and customizing it to work just like OpenCode takes another 30 minutes. Better design, better devs, better community.
While I just switched from OpenCode to Pi, I'm still unclear on which is better in terms of handling github issues/pull-requests. I do give OC credit here, especially after the last week.
Here's the Pi issue for a security feature request, derived from an opencode v2 security regression I was able to work through with the OC team. This issue links to the OpenCode ones too.
OpenCode Go is the best deal in the market right now imo. Their quotas are so generous I often assume they are burning money, but I think they are largely thriving off of the subscription revenues and making it work, or their vendors are subsidizing things.
None of these are considered important. Opencode is a vibecoded vibecoding tool, so 1) software quality is fundamentally unachievable and if they will pay attention to bugreports, they will simple drawn in them; 2) it's now a trend to delete tests in the name of AI ideology.
Based on this post, it sounds like a ton of great improvements.
I've only used OpenCode a bit, but I found it was sufficient for the workloads I was throwing at it. It wasn't quite enough to beat out Codex or Claude Code as my go-to choice, though. Perhaps I'll give this version a shot and see if they've gotten it over the hump.
Is there a way to buy tokens with a good model that makes OpenCode near as cheap as Claude Code with a Claude Pro subscription?
For personal projects, Claude Pro seems to give me a lot of tokens to use with Claude Code, and from experiments using other models with Claude Code (e.g. via Vercel) always seems way more expensive.
There is opencode go [1] that gets you quite far compared to paying API prices. For example for the $10 subscription you get $80 in deepseek 4.1 flash credits.
The headline figures are $10/month for 'Go' with "Generous limits" and $40/month for 'Go Plus' with "Higher limits".
Then, in the table below, picking (at random of course) Claude Haiku 5.5, I see it listing 3,850 'requests' per 5h for 'Go', 15,380 'requests' per hour for 'Go Plus'. Then there's another column saying that the "Monthly Usage" is $15 for 'Go', and $60 for 'Go Plus'.
What are the limits?
What's a 'request' and how does it relate to a token?
Why are the 'requests' figures per '5h' (the limit resets every 5h?)
Why are there 'Monthly Usage' dollar amounts that are in no way connected to the subscription costs, and what do they mean?
All the explanations below are just repeated rewordings of the same thing: "Go costs $10/month with generous limits and Plus costs $40/month with higher limits", as if that makes everything clear.
Found out on 1.x it goes crazy with file watches. If you launch in a top level directory with lots of sub directories, iirc it can create millions of watches X2
Not sure if it's fixed in 2.x. There's some way to get it to not do that with ignore files or rules but not sure exactly how--I had Claude fix it...
I just tried the excellent local https://www.liquid.ai/blog/lfm2-5-24b-a2b model, but the model is trained to talk in bash, while OpenCode stubbornly expects JavaScript, and there seems to be no way to make them work together. The model itself performs excellently in pi.
OpenCode is a beast. Does it still try to take a disk snapshot of my working directory, even when it contains hundreds of millions of files? Does it still eat all of my memory? Does it still have a super-gigantic system prompt that wastes a solid percentage of my context window before I've even begun?
I switched to pi some months ago, and I have no complaints. It just does what it says, with no shenanigans. They updated the rendering approach recently so scrollback is nice and smooth now.
I was opencode user, but like few months ago tried pi and never looked back. Pi with open models is absolutely mind-blowing - my agents run with speeds not achievable with any remote frontier model - they certainly not as smart, but it doesn't matter because they do their "work done" perfectly and fast.
All problems I had with opencode are not presented in pi - it looks it's the best approach to guarantee most productive coding environment - speed, simplicity, transparency, absolute customization. I will certainly try this 2.0, maybe they have now improvements.
I switched to Pi after experiencing OpenCode V2 about a week ago. Dislike the UX direction a lot. I took some effort to sift through the Pi plugin ecosystem to get my setup in a good place.
I will say OpenCode has likely improved significantly from your experience. I never experienced any of that since ~May of this year when I picked up OpenCode the first time.
For me the distinguishing feature of OpenCode is the web ui/desktop app. I’m using OpenCode because it’s the only open-source agent-harness I’ve tried that runs outside of a TUI. I like terminals but not TUIs and especially not for prose-based interactions like prompting.
But that’s a shallow moat, and the rest of the features here are not particularly interesting to me. I don’t have a use for plugins or a model-server proxy (I can connect other tools directly to the model provider).
Unfortunately many subscriptions require you use their harness. In that case, I highly recommend using Termic (https://github.com/simion/termic/).
It's an incredibly useful GUI that lets you use the provider's harness, but adds extra productivity features. You can use OpenCode, Pi, Claude, Codex, whatever you want. The TUI runs in a window, but you can also pull up terminals, open tabs, keep projects, workspaces, show file diffs, give feedback on lines of code, review PRs, and way, way more. The number of features is impressive.
The devs are very quickly adding features, yet the app remains stable. And they fix bugs super fast! They fixed like three bugs and implemented two feature requests of mine within a week of asking. Best of all the whole thing is FOSS and they're not trying to make money off you. Absolutely awesome maintainers.
Are there any recommended sandbox patterns to use? Custom linux users or bubblewrap and managing openbao is getting to be a lot to manage each harness by themselves!
I've been using https://nono.sh which uses landlock instead of bubblewrap. I had a look at all the similar alternatives when I started using it and everything else I could find was far too vibe coded for me to trust, especially for this.
I am using v2 since its released I like OpenCode because of its user experience for TUI which imo is best for any coding agents out there but still there are rough edges which have to be resolved currently I am facing clipboard issue in Ubuntu/X11. I have not figured the root cause yet i hope they gt resolved
I don't understand why compiled languages would make plugins harder. They just need explicitly defined entry points in libraries like DLLs. This has been existing for literal decades in other systems, for example Adobe plugins or Steinberg VSTs. It's not an unsolved problem.
It's a big improvement over the previous version. Currently, the Codex TUI has constant display issues for me, the most prevalent being random deviations of light/dark characters. So far no such issue in OpenCode. Since it's model agnostic, this might become my daily driver.
Started work with OpenCode and my number one issue is that they do not cleanly document how to configure the settings to only run local ML models.
It is all focused on pushing prompts out to 3rd party providers that uses them for training. Irony is having to use the 3rd party provider to properly configure OpenCode with local only ML. I cannot have private information leak.
Good thing I tested it on open source code base before touching property code bases.
Huh ... is that related to why I see little Gemini hits constantly when selecting e.g. DeepSeek 4.1 flash on openrouter? I'm not going private for a bit (mac studio on the way) but when I do I want to lock it down, but pretty stuck on opencode for the moment. If it's leaky that's a problem.
Unfortunately, opencode v2 still has mandatory remote config loading from your model provider's .well-known/opencode url, which gives your model provider remote code execution on your machine.
You should't really run a coding harness on your host computer anyway, because it is impossible to protect yourself from prompt injections and from an incredible amount of security vulnerabilities in the vibecoded plugins.
Security is fundamentally unachievable in popular coding harnesses.
The only right way to use it is in an isolated environment.
This isn't really true. You're talking about unattended execution, where the user doesn't review each action before letting the model proceed. I agree that it's bad to run that on a machine with important data, but I disagree that coding harnesses are fundamentally insecure just because the practice of reviewing each tool call has gone out of fashion. I do see harnesses these days not designed with that in mind, but that just makes those particular harnesses insecure, not the fundamental idea of harnesses as a concept.
The background task / subagent feature and the ability to specify a model when starting a subagent are so far my favorite improvements. Small things but make huge QoL difference in everyday development.
Good lord, me either. I thought it was a gag reading through these comments, but there was no way all of these people commenting were that locked into a joke.
OC is all right -- it's my daily driver -- but it could be better. I'd like a harness to let me customize the GUI, not just add MCPs and plugins. For example, I'd like add buttons to merge a PR, and show indicators for CI. Claude Code does a lot of this out of the box. Give me UI building blocks (buttons, labels, etc.) and wire them with my own functions. Could Code Mode enable this?
The built-in browser is a most welcome feature.
PS(A): Opencode Go is a great deal and now has a $40 plan.
Thanks for the great recommendation. In the meantime, if anyone wants to contribute to GUI plugin support for OpenCode, here is a PR under review: https://github.com/anomalyco/opencode/pull/55246
It looks like they finally fixed the issue where the system prompt at the start of the transcript was regenerated from scratch every request, leading to significantly higher input costs. Unfortunately it's still rewritten whenever you revert to an earlier point in the conversation, but at least it's not on every single request.
These guys stole money from me. It amounts to like 10 US or something, so not significant, but still...
Their models have pricing published in their docs, like any other LLM provider. I measured the tokens I consumed, did the math, and it was always off, in their favor. One model (GPT Luna) was about 2x as expensive as advertised.
I joined their Discord, which is apparently how you get support from them. I filed a bug and someone from their team replied, we verified the data, and he said that something was indeed off and that he'd escalate it. Then silence. After 2–3 weeks, I followed up and was now ignored.
As I said, the amount isn't material to me, but if they do this a million times, they could make some decent money out of it. No idea if it's on purpose, I'll leave that to the reader to speculate.
Overall, their complete lack of interest after acknowledging the "bug" left a really bad taste in my mouth, so I decided to leave.
Ahh. I recall their opencode go plan offered $60-$80 worth of Deepseek for $5-10 or something? I was debating if I should try it out but I think this is convincing me not to...Thanks for the heads up
I tried opencode 2 with my locally hosted llama, and I noticed that llama is always producing stuff even when I close opencode. I suspect it's the backend still doing stuff with the frontend isn't displaying, but I have no way of investigating. So I'm sticking with 1.9 for now.
9 months ago I had opencode fill my 2tb storage with temp files and if I delete it’d redo it on session start. From that time onwards I have not gotten around to building my own verification pipeline to convince me that opencode won’t do it again. I guess I wanted to highlight that verification is what would sell me on opencode again.
I have been using open code and it is horrible with ram usage. Every subagent takes like 300 MB of RAM. As they are vibe coding, i think they should use language that consumes less RAM eg. Rust or C.
> If a story has not had significant attention in the last year or so, a small number of reposts is ok. Otherwise we bury reposts as duplicates.
In my experience, if a story gets 4-5 points and < 5 comments, it hasn't gotten "significant attention" and a repost gets a second chance. That's not data, just anecdote.
I had to update because the previous OpenCode 2.0.3 I had installed stopped working suddenly. I love the idea behind OpenCode but compared to managing Claude and Codex, it's such a pain and requires continuous debugging or managing.
Is there azure login capability, for az login?
We are 100+ devs and claude code has this built in by default where we can host our own models in Azure Foundry. Devs don't need any keys since they can just use az login and it just works.
Never got used to opencode honestly, there is always this clunky feeling (same with pi but at least i can customize it more than anything.) and this feeling didn't go away with 2.0 either :/
I use OpenChamber as my IDE. It uses OpenCode behind the scenes. I've not really noticed a difference in OpenCode v1 vs v2 but I guess it's because OpenChamber does a great job dealing with those details.
The site took a minute to load in completely and when I scrolled to the bottom I couldn't read the SDK text, it was literally cut off, kinda resembling the current state of coding very accurately lmao
Judging by comments opencode seems popular. Why is it not in the top ranking coding agents on openrouter? HN's darling Pi is there, along with few others which I never heard about, but not opencode.
Maybe because of their rich provider ecosystem allowing you to use a whole bunch of subscriptions in it. I use OpenCode Go and OpenAI for almost everything, almost never touching OpenRouter.
tried opencode for the first time to use the $200 in api credits that come with claude max but can't be used in claude code. it's great. the free nemotron 3 model is even decent, i love seeing agentic coding accessible to students and hobbiests and folks that can't drop $200/mo.
i used the bonus anthropic credits to get ornith 1.5 35b q8 running on a jetson. it's no opus 5, but it's usable for real coding and sys admin work, and works great in opencode. at least as good as sonnet 4. 5 token/sec is a little painful though.
- Miserable startup times are now "solved" by leaving it always running.
- Someone in this thread said the curl installer was slow because the install script needed cute progress bar rendering. To be clear, I don't care about the installer user experience, but I want to spend a moment on this point, because having used OpenCode for over a year, I think this perfectly sums up the entire experience. A commit born from "Claude, please make the installer look sick as fuck with loading bars and stuff" will always be preferred by the developers over a commit that reverts such a change for a 10 MB drop in memory use.
- Tried to read the unreadable announcement website after waiting for the little ThreeJS demo to load. I gave up.
- Logs from various old sessions leaked up to 16GB on some temp folder on my drive. The harness prompts are still token heavy. I know neither of these are real issues, and chat logs are a useful feature for many, but I felt validated to see someone else in the comments also complaining about the silent storage of chat sessions leaking into my drive in a random folder being the default behaviour.
IMO, this release goes far beyond OpenCode. I had always imagined that the advent of LLMs developing human-level coding abilities, combined with the high hardware prices as a result of it, would act as a forcing function to inspire a new generation of ultra-performant, bloat-free open software.
But this release is proving me wrong in every way.
We are entering a new era, what George Hotz coined "maximalist software": A new dawn of computing, where one one hand, we can simply prompt a superintelligent LLM to "please prove the Riemann hypothesis", and it will actually work. On the other hand, the chat log for the proof disappeared, because because the 2 GB Bun server (yes, the one meant to interact with a plaintext LLM API) just crashed.
> A commit born from "Claude, please make the installer look sick as fuck with loading bars and stuff" will always be preferred by the developers over a commit that reverts such a change for a 10 MB drop in memory use.
Not my experience. YMMV
> I had always imagined that the advent of LLMs developing human-level coding abilities, combined with the high hardware prices as a result of it, would act as a forcing function to inspire a new generation of ultra-performant, bloat-free open software.
I mean, faster and better hardware has never resulted in more efficient software, I really didn’t expect it to be any different here.
application/x-apple-diskimage
Last Analysis Date
3 days ago
Summary
Detection
---
SOCRadar
Malicious
---
ZeroCERT
Malicious
----
Gridinsoft
Suspicious
---
??
they deprecated the old layout which I very much preferred in open code desktop. I'm never in a rush so I'll wait for the early adopters to vouch for this release.
I've been getting good results from OpenCode. Has anyone been able to get it to work with local models though? It doesn't seem to want to play nice with Ollama.
I have an open code server running as a service on a linux desktop with the port opened up so I can use the web UI from my windows laptop. The same linux desktop is running Ollama and I'm currently using qwen3.6:35b with it.
The setup was mostly for the learning experience and I haven't done any serious work with it, but it's been great for writing bash scripts.
I used OpenCode to help me install ollama, Qwen local LLM, and connect OpenCode to it.
The computer is very slow (old Dell Optiplex running Mint Debian Linux), but it worked! So cool to turn off the network, and still be able to chit-chat with Qwen model ("Tell me a joke about...").
cool, I'll have to mess around with it some more. I don't expect to be able to do any real work with my 16GB MacBook Pro, but eventually, I would like an all local setup.
Can someone tell me what am I missing if I just use the Claude extension via vscode instead of opencode? I use codex as well but only as mcp for reviews
If workspaces had a way of managing separate Go subscriptions for team members, a large chunk of my org would jump in. DS and GLM are solid for a lot of tasks.
OpenCode is a vibecoded vibecoding tool. From that kind of software you really shouldn't expect things like renaming of a project to work all the time.
I mean this neutrally: quality is not something that these projects strive for. Other values are a priority: features, speed of development, etc.
It's not. A permanently running buggy() server on your computer instead of a screen or tmux session is not something that should be a default solution.
I mean it neutrally. Software quality is not a value in code harnesses. Something else is a value: speed of development, features, etc. But quality is ignored.
You may like pi-web-ui, it has a ton of useful functionality. Was a bit rough around the edges before but it's improved quickly. (https://pi.dev/packages/pi-web-ui)
I was a Vim user that switched to VS Code (for reasons) and now the TUIs are where my Vim personalization efforts have been redirected. Pi is a good harness for vim users to consider if they want to try a TUI experience. The Pi plugin ecosystem is a slopfest though. There are vim bindings for Pi and OC (and VS Code) because I'm never going to give those up.
Is still forbidden to use Claude Code accounts with other harnesses? I will try with DeepSeek later, but it would be better if I could use Claude subsidized as well
There's this amazing three letter harness that had all those features and more for many, many months already, but many aren't ready for that conversation
What in the hell is wrong with this page? Whole blocks of content disappear and reappear on my phone as I scroll. Eventually the page just starts force reloading. It’s a blog post! What could possibly require … whatever this is?
> What in the hell is wrong with this page? Whole blocks of content disappear and reappear on my phone as I scroll. Eventually the page just starts force reloading. It’s a blog post! What could possibly require … whatever this is?
Somehow I manage to get issues noticed and PRs merged. They aggressively cull old issues but if they take notice things get done. I contributed just this week.
Bros - that opening disk transfer interaction is peak awesomeness. I copied about 4 files and did not want to stop...Id sit there all day and do all of them just to see what happens in the end...perhaps later this weekend.
I've been using OpenCode V2 since it first appeared on the website, and I can only repeat the positive views on usability, the client/server model and self-awareness/ability to edit it's config and write plugins.
I'd like to mention two other impressive things about OpenCode.
First, their issue tracker on GitHub works really well. They have the OpenCode GitHub App connected, and for any bug report it reads the issue, tests on the mentioned version and latest dev branch, and comments the findings along with a reproduction script. For TUI Bugs it even records a video. And all that in less than two minutes, usually.
https://github.com/anomalyco/opencode/issues?q=is%3Aissue+st...
Another thing they are working on is opentunnel, where you can tunnel services to https on <random>.opentunnel.xyz and its subdomains. What's notable is that the subdomain is persistent and unique to you, and a wildcard ssl cert is actually generated on your machine, so the platform cannot see the traffic. Their primary use case seems to be making the OpenCode Server usable from anywhere, but it can do much more with their cli:
https://opentunnel.xyz/
> the client/server model
I see people talking about this being new in v2 everywhere but it's not the case. What's new is that it's the default (and also not really since `opencode service` and `opencode serve` start two different things). But in v1 it was very possible to run one opencode instance and have multiple clients connect to it (like Openchamber and neovim).
issue tracker is awesome, will have to copy that for sure!
The opentunnel feature is probably related to the "official native apps that are in the coming" mentioned in the article
Try pangolin for tunneing , it works so well.
It's good.
Many of the annoyances from V1 are gone. Skills and plugins reload automatically (finally). Tasks can be backgrounded (though I think this doesn't happen automatically yet). There's a built-in skill for editing the configuration (finally I can retire mine). The front-end got some love. Apparently they re-architected the loop around Effect. Sub-sessions can be communicated with better. Configuration is loaded from the folder the session is created in rather than where the server was started.
In general, this update largely takes OpenCode into the current age features-wise and is a good overhaul quality-wise. Just in time to stop my early switching away efforts, which would've been a pain because I know few other harnesses with such a strong server/client model.
To me, there are more annoyances in V2, so many that I've switched harnesses to Pi (for now?). I think the hot-reload is another security misalignment. An agent should not be able to modify plugins and have that immediately reloaded for availability.
Stellar example of how one person's security vulnerability is another person's most important feature...
1 reply →
Security misalignments OpenCode has a good few of (it used to have more).
I think the benefits of this one vastly outweigh the risks since it enables the self-modification Pi (!) became famous for.
20 replies →
I tried switching to Pi twice. Both times it seemed agents go crazy with tools on Pi and do stupid things right out of the gate, (like get `find` syntax wrong, seriously who [what] does that??). Plus things I appreciate in opencode (even if they were buggy in 1.x) like "prompt for perms tool-by-tool in this session" seem to only be available in Pi by writing your own extension, and now I'm wasting time debugging my extension with an AI that gets tools wrong and constantly wants to search `/` for no good reason.
Then I upgraded OpenCode to 2.0 and pretty much all the bugs vanished. I still wish there was a happy medium between "parse tool calls for perms" (which fails all the time if the tool call is long/complex enough) and a full-on sandbox, but otherwise 2.0 is really solid.
DeepSeek Harness allows the user/agent to build its own plug-ins and run them without restart, mostly. Pi and OpenCode were then influenced to do the same in their respective new versions. I don't know which has the better implementation.
6 replies →
Just curious, what other annoyances do you have with V2?
6 replies →
Tasks can be backgrounded by the model you are using automatically. It is not just manual fyi
Yeah, but only I can click to move a task to the background when it takes longer, which could and IMO should happen automatically. The model can’t always judge that. (I see how my comment wasn’t clear enough that I mean this)
In general, the preventable “model gets stuck” class of annoyances has not been fixed quite yet - there are also stil no timeouts for permission requests, at least by default.
3 replies →
Does opencode support anything similar to claude code's auto mode (https://code.claude.com/docs/en/permission-modes#eliminate-p...)?
I'd like to switch to opencode, But "yolo mode" feels risky and manually approving every command the model runs kills the flow
I run --yolo but I'm running opencode in a VM: https://github.com/marius/devmicrosandbox
Put the agent in a sandbox.
This is the only way. Auto mode is really just yolo mode with more LLM tokens billed. It may catch some weird shit but it isn't a reliable sandbox. Just lock up the LLM and let it run.
4 replies →
What sandboxing tools do you recommend? There's lots out there and I'm unsure which to trust.
8 replies →
FWIW OC 2.0 remembers perms for a project/directory pretty solidly now, so flow-killing approvals are more a one-time thing for a given project. It's sad they can't be globally set though, so a new project pays the approval-by-tool tax.
[flagged]
[flagged]
It’s great, they’re embracing even more the “everything’s a plugin” principle that has been pushed by other harnesses like Deepseek. Shoutout to all the AI model companies out there: if your subscription can’t be used on open code, I’ll buy something else.
Many of the workarounds I had to develop for the v1 now come as native features in v2 (i.e. session rebinding to other folders), now the only thing that was missing is the ability of plugins to read the response you’re writing (useful if you want to have the double-Esc feature like in claude code).
Native apps connecting to the OpenCode server is a great way to run sessions on remote hosts!
I wish Claude Code would adopt the same model. The desktop app deploys a separate engine that restarts and clobbers long-running sessions upon reconnect (Remote Control is their recommended solution but requires a Claude.ai account).
I’ve been vibe coding a native macOS Claude Code app that spawns a server that wraps Claude Code on remote hosts, but the UX and features are always lagging behind.
I am quite keen on this as well, I have been trying to move all my active development to happen inside a container, including the harnesses. This, of course, makes it very hard to run GUI harnesses. I prefer CLI, but it would be neat to be able to better isolate gui-based harnesses as well.
I have been using VSCodium with https://github.com/jeanp413/open-remote-ssh so (most of) the IDE also runs inside the container. I have been trying to get everything inside the container, including the projects I work on, the IDE, the harness, the dependencies, etc. Both for security and for portability so I can have the same setup in both my work and home computers.
One thing I haven't been able to do is limit the blast radius of is git, github ssh keys give blanket access to all repos tied to my profile and ATM I set up the github SSH key inside the container.
[dead]
Claude code agents have a protocol that's usable for the same purpose it just listen locally but it's usable i have my own claw-like that has options for claude, codex, and pi (my subscription, wife subscription, and i got a yearly sub on glm when it was cheap)
ACP?
2 replies →
I was experimenting with Paseo for this.
The Opencode desktop app could already connect to a remote web session; does it now talk to the server directly?
Claude Code already has a server mode. The difference is that it connects through Anthropic rather than via a local socket.
one server, multiple Claude Code clients is what OP is proposing
a server like herdr has a server
1 reply →
I've developed something similar for personal use. A harness who's only job is to delegate to other harnesses (i.e: AntiGravity, Codex, Claude Code, Hermes) to create an opencode-web-like interface across multiple hosts.
For Claude Code, don't use remote-connections. Your best option is to look at how the closed-source VSCode plugin interfaces with Claude Code. The way it works is that it reads files directly. This API, although unofficial, is likely very stable, because an old VSCode extension still has to interact with new version of Claude Code.
If there's any interest in this sort of thing, maybe I'll open-source it. I would have to cleanup the slop though.
I don’t know much about your use case but in case you need some inspiration shout out to t3 codes
1 reply →
[flagged]
[flagged]
Feels like more of the same, although I can't say because this article wasn't very readable so I couldn't bring myself to reading it.
A list of big new features and changes would have been nicer.
I hope they fixed the long delays to opening OpenCode I have been experiencing, and the huge database of old chats I don't care about anymore.
It opens much faster because there is a persistent server running now
That seems like the totally wrong solution to fixing spending minutes opening.
1 reply →
Their installer (curl | sh) was taking so long yesterday for me.
It turns out it's incredibly slow... because of the progress bar rendering. This is insane. The installer took 6 minutes to reach 10%:
curl -fsSL https://opencode.ai/v2/install | bash
Managed to fix it by running this instead:
curl -fsSL https://opencode.ai/v2/install | bash 2>&1 | cat
I suspect heavy eyes free coding. I spent the last week helping them understand a major security regression in config loading, took two issues/pull requests. Our hunch is the Ai told them what they had was good, not enough human critical thinking.
https://github.com/earendil-works/pi/issues/10895
Ive anecdotally never found OpenCode to have a real axis where I find it "best". But I havent tried it in a bit, mostly because I don't have a real gap in use case coverage between Codex/CC/Pi. Anything more specific in need probably gets a custom harness.
Maybe the Go plan is changing that for others?
1 reply →
[flagged]
Isn't that an issue with your terminal? Why is stdout so slow?
I think it's due to they are doing a funny business to parse the progress, that's pretty much vibed and no one care. Like instead of using curl's progress, they re-invented a progress tracking with the tracing interface (--trace-ascii), byte by byte :(
https://github.com/anomalyco/opencode/issues/22998 https://github.com/anomalyco/opencode/issues/53702
4 replies →
I don't think fast gpu rendering terminals should be mandatory for this kind of thing, and if you should have an option that facilitates the need for one then might I suggest falling back to something sensible rather than stalling out for forever when the user doesn't render glyphs as fast as you want them to?
either that or fail outright; dont waste my time.
1 reply →
If it doesn't work at least ok with something like xterm, someone really needs to reconsider some life decisions. Htop makes it work, why should a terminal emulator need to crack the engima just to render silly stuff?
Well, stdout is not typically implemented for the purpose of simulating graphics rendering via character manipulation.
4 replies →
[dead]
Sounds like I'm not upgrading then. My current OpenCode works perfectly and too many life experiences with "don't fix something that ain't broke" ;)
Of course? I never ever upgrade any software unless I'm facing a bug or I want a new feature from the new release. Otherwise it's just taking risk for almost nothing in return.
My laptop fan went nuts on their homepage.
On my phone I can't scroll there. I left again
If you have Nix, you can run it using:
https://agent-distro.nixos.asia/ brings auto-updating coding agents managed by Nix, along with https://agent-plugins.org/ based profiles.
and they probably haven't stopped hijacking copy paste.
Yes this is why I'll never use the TUI.
The full gui app is decent though.
probably my single biggest beef with their client and why i don't use it all that often outside of non-interactive mode
you are correct, still hijacking
And they created the slowest webpage on the planet Earth. Full throttle slop.
[dead]
[flagged]
chuckling
This is a you problem
time curl -fsSL https://opencode.ai/v2/install | bash
real 0m24.975s user 0m9.537s sys 0m14.904s
They might have fixed it in the meantime though
Edit: indeed https://github.com/anomalyco/opencode/commit/d099d2cb2a0869d... / https://github.com/anomalyco/opencode/pull/55586
Took me a little while to figure out this was a llm harness for coding (also called an agent, I suppose, but that term seems overloaded and ambiguous to me)
There are many of these available, alongside the provider ones.
Are there any benchmarks which help me decide which ones I should try over the standard codex/claude?
Codex and Claude should not be seen as ‘the standard’
They are vendor offerings but you don’t have to take them.
You kinda do have to take Claude if you want to take advantage of their subscription pricing, sadly.
7 replies →
Seems foolish to use a single-vendor harness to be honest. With how fast things change, and the price/performance you get from open weight models, building a workflow around a single llm provider seems super limiting.
So is OpenCode. They are quite a vendor.
I use "harness" for the tool which calls the llm, has the tools, interacts with the computer (filesys, bash, etc), does the session bookeeping
and "agent" as the instance which is running... this is the more overloaded term because there are "agent" definitions, this is where a combinatorial exists, because the running "agent" is a combination of agent definitions, context, tool choice where you can modify each independently to create a new "agent"
I think Scion (Google's) does a decent job defining these concepts: https://googlecloudplatform.github.io/scion/concepts/
https://harnesstax.github.io/
From what I gathered, a simple harness like the one from Pi is sufficient.
Similarly, I would advise against using tons of skills and keep the ones you genuienly find useful (they are just .md files so you can copy them). The only skill I use is /strategic-compact from everything claude code (ecc) because I like to read the summary before a manual compaction.
There are a few benchmark, where they run different harness with the same model, e.g. [artficial analysis](https://artificialanalysis.ai/agents/coding-agents) but honestly they are easily game-able.
For example, consider something like SWEBench, where a test should pass. Harness or a skill can just tell the agent keep trying until the test pass. So same model can have a lot of behavior changes between the harnesses.
In my experience (i own a multi-agent IDE with 50+ supported harness) folks stick to first party, usually either openai or anthropic, grok, agy; if they are willing to pay for the subscription the value is unbeatable. And they don't risk trying different harnesses.
I made a harness too, and recently added eval with opencode and pi and I sat between them. No gaming other than trying to figure out why I was really bad on some evals (I was not returning thinking tokens which broke cache, for example, and different model families do things way different here). I have yet to try my harness for coding but I do have a few terabytes for it to read. And I’d rather use a local model that’s fast and good at retention, but that run could take a year, lol.
The main four seem to be Pi, Opencode, Claude Code, abd Codex.
I do often see benchmarks comparing them and usually Pi comes out on top, but I think the benchmarks are generally testing one moderately sized clear task. Pi is minimal and great in that situation.
For more general usage, where tasks are not clear, you might interrupt at any moment to steer it, etc. benchmarks are harder I guess. I personally love pi because anytime there's something I don't like, I spin up a separate session and fix it.
E.g. I've found the "reply in simple technical English" hack amazing but I have to keep saying it over and over. So I had an agent write an extension in about ten minutes that appends a short hidden message saying all user and dev facing text must be in STE, apply that without talking about STE. Works amazingly well.
I would state the same, but looking at commercial offerings for agents, such as MCP servers or skill instructions in the vender's own docs, opencode is often not mentioned at all.
Here is an example I encountered recently: The Figma MCP Server documents usage with Claude (Code), Codex, Cursor, Grok and Antigravity [], but notably not OpenCode. More so, their oauth registration seems to use some kind of whitelist, meaning just adding the MCP by url does not work either. To make it work, my agent edited the config entry to use "Codex" as the oauth name, which worked.
That's just one example, but something you see quite frequently.
1 reply →
Could opencode do the same? Thinking of trying pi because of these extensions
1 reply →
AGENTS.md
Here is a benchmark where they actually evaluated harnesses across same models and measured task completion rates: https://frontierharness.org/
You might look at Block's open-sourced Goose (https://goose-docs.ai) and view it as something of a neutral opinion for a harness application.
the person said that there were too many samey harnesses and they couldn't see why or which to choose and you thought you'd fix that by adding another to the pile?
I wonder why all of a sudden these harnesses want to run a permanent daemon on my machine? Like, all of them, and at the same time.
(Obviously, this feature should not exist at all let alone be default.)
A pretty important feature is that the client process can crash without losing progress on my current session, similar to how I can reconnect to my tmux server without losing current active processes.
If you think about the evolution of AI coding, companies (who will eventually pay for these tools) will realize they want to run the coding tasks in a remote, controlled environment. Every engineer typing on their machine and burning tokens (money) won't work in an enterprise setting.
> Every engineer typing on their machine and burning tokens (money) won't work in an enterprise setting.
Of course. Obviously, just a week ago and before that none of the harnesses did work in enterprise settings.
Irony aside, I don't think that there are that many tasks that will benefit from a daemon but which aren't solvable with screen or tmux. In other words, I think this feature should not exist, let alone be enabled by default.
Also, I actually am "an enterprise who pays money for these tools" and I strongly believe most of my engineers immediately disabled the background daemon. I know of a few who were unpleasantly surprised by the cli codex update.
1 reply →
I agree that it shouldn't be default, but I'm wondering why you think it shouldn't exist _at all_. The daemon mode for emacs, for instance, is incredibly useful for speeding up startup time and persisting things between windows. It's probably very similar here.
Because this feature solves no problem.
It’s not obvious to me why this feature shouldn’t be the default.
I routinely run dozens or hundreds of daemons. Why wouldn’t I want one to keep my network connections to llms open?
The problem is pre-ai and has excellent solutions. Some of which have not been changed for a couple of decades because they are perfect.
There’s two answers, depending on your personal cynicism.
The optimistic version is that the new zeitgeist is deeply recursive agents writing _huge_ swaths of code at once. The human side seems very asynchronous. You do a lot of queueing something that the agents churn on for an hour, so being able to detach/reattach would make sense.
The cynical version is everyone is realizing that nobody will pay for a harness, so they’re pivoting to a client-server model to try to PaaS-ify them. If they haven’t announced it already, they’ll have an OpenCode Cloud within the next quarter or two.
We’ll see how that goes. I’m not holding my breath that these will thrive as long as infrastructure teams exist. Agents are too simple from an infra perspective, and we’re seeing frameworks to make them stateless pop up already.
> deeply recursive agents writing _huge_ swaths of code
No daemon needed for that. Like, at all.
> they’re pivoting to a client-server model to try to PaaS-ify them
This is absolutely it! The more I think about it.
4 replies →
idk about permanent but my own custom harness runs as a daemon, which lets me close my terminal without it killing long running sessions.
Maybe there is another solution to this problem. Perhaps the problem itself is not new and has been thought of before.
2 replies →
Because it’s better and users want it.
I use all of them, but I'm not interested in this feature.
It's not and they don't.
With websites i went back to 90s styles. Hyper dense in information. Anything clickable is a link. A button is for Write actions.
Interactive element are distinct from text.
If webpage page is an interactive canvas , make the canvas the main thing ad text as support.
If you start mixing the two idk..
it feels like a clear improvement across the board but a heads up: i got bitten by upgrading - since all tool calls now go through the background process, the sandbox that i use to wrap the TUI process quietly became useless. took me a day or two to realize that web fetches, etc. which should have been blocked were succeeding.
There are at least 3 security regressions (imo) in the initial v2 release
1. configuration loading (now fixed) dropped support for system level, then restored it incorrectly, now it is better, but still some issues in user space
2. hot-reloading of plugins, agents can now change them with immediate effect
3. this, which I was unaware of
I wonder how many more there are given this much has been found already
4. Tools added by plugins don’t respect your permission config! For example you can set a tool to always ask when used, but it auto allows.
1 reply →
Yeah, it is a regression IMO.
You need to run it with —standalone to properly sandbox it.
Those tools should be designed to be sandboxed.
[flagged]
[flagged]
Wait, but OpenCode got renamed to Crush and the original dev went on to that new project. Where did this come from? Is this a fork? Who is behind it?
Someone from Opencode went to Crush, but Opencode continued.
EDIT: as a rewrite, owning the name. but not code.
https://x.com/thdxr/status/1933561254481666466
TIL - there was business in TUIs that actually warranted “acquisitions”. Always considered developing them a hobby…
4 replies →
More on Charm x Anomaly: https://news.ycombinator.com/item?id=44741894
I don't think that's the case. This is from anomalyco, the company who made sst.dev. Crush is from Charm. I think OpenCode may have originally been written in Go but nowadays their codebase is TypeScript.
Edit: I'm missing some context others have pointed out.
I'm really tired of this being retread time and time and time again.
It's just not interesting, it doesn't seem to matter, they are are separate projects and both doing great. The inside baseball about old history doesn't feel like it goes anywhere, adds anything. It didn't the last 5 times opencode got submitted!
It's my daily driver - very easy to customize. Added a pretty solid vim plugin for it and a few more really useful plugins. Here are my dotfiles https://github.com/dkarter/dotfiles
Can you share that vim plugin? Now running opencode at Ghostty and looking diffs at github and rarely when need to do code changes manually I am using vscode but proper vim plugin would be godsend.
I wish they’d invest more time in performance improvements over code mods. I recently switched to pi which uses an order of magnitude less RAM (hundreds vs dozens) and noticeably less CPU on my machine… OpenCode is really nice but it’s about as heavy as antigravity and is substandard in features…
Pi is also super context-efficient. The out-of-the-box system prompt before adding tools and skills is like dozens of tokens.
OpenCode was thousands or tens of thousands last time I checked. Not sure if this has been improved.
true but from what i found, the opencode team tested these prompts and evaluated that a bigger prompt is better for some models, overall.
very possible that a smaller more custom system prompt (+ custom tools) could work better for specific use cases.
1 reply →
My notebook took up flight and launched itself through the window and died trying to render this site.
When I opened the site, I started hearing a sound that I never heard before: My MacBook Pro M4's fans. I checked ActivityMonitor and Firefox was using a significant CPU share. Are they mining crypto in the background or what's happening?
[flagged]
My M3 Pro noticeably stuttered when I opened it :/
I love opencode, but not this website. so difficult to use.
I've been using OpenCode 2.0 indirectly via OpenChamber 2.0 and I've been very happy with it.
Once I got past the initial hurdle of having to upgrade my server and clients all at once, everything has been smooth sailing.
OpenChamber ftw! I'm surprised it's not more popular - so much nicer to use than the TUI.
I'm always confused when people at work show me their opencode or Claude code setup of 6 terminal windows open simultaneously with the same illegible walls of text. No idea how people still prefer that over a nice GUI.
Once you really know your keyboard, it's like an extension of your hands. You can fly through those six terminals, and moving your hand to grab a mouse means stopping whatever you were doing. That wall of text is all familiar to me - I see an UI full of empty space and wonder what I could have used it for.
Of course there are great reasons for using pointers also. I'd say this is mostly a preference, I'm sure you are extremely effective using your own methods. I have maybe two dozen terminals open atm, and I can tell you what each of them is for - but put a phone bill or a bank statement in front of me and it might as well be Greek.
2 replies →
At first glance it looks like an electron app, so thats probably a great reason not to use it. (But I could be wrong)
I just use Zed and interface to agents via ACP. Works like a charm.
Interesting and I'll definitely give this a try, the client/server and plugin system do look very powerful.
However, I've been using OMP in combination with Tern (the terminal) lately and it's an incredibly smooth operation. It's hard to find a decent terminal on Windows (corporate device) but this is the best I've found so far.
Gave it a try as well, but the RAM consumption was pretty high. Had to move back to Ghostty.
There are dozens of us, dozens!
I don't see a "performance" section. Should be the first one they mention.
Last time I tried OpenCode was on a tiny VPS which stopped responding when OpenCode tried to eat over 2GB of RAM in launch.
Same OpenCode team who ignore bug reports, don't respond on their discord, don't have modern CI/CD test suites (often shipping regressions), don't have bots to triage bug reports or PRs, and have what might be the worst open model subscription service available today.
OpenCode users: switching to Pi takes about 5 minutes, and customizing it to work just like OpenCode takes another 30 minutes. Better design, better devs, better community.
While I just switched from OpenCode to Pi, I'm still unclear on which is better in terms of handling github issues/pull-requests. I do give OC credit here, especially after the last week.
Here's the Pi issue for a security feature request, derived from an opencode v2 security regression I was able to work through with the OC team. This issue links to the OpenCode ones too.
https://github.com/earendil-works/pi/issues/10895
The Pi dev does not seem to grasp the issue after several back and forths.
I do really like their CONTRIBUTING.md
https://github.com/earendil-works/pi/blob/main/CONTRIBUTING....
What open model subscription services are there that’s better. Genuinely interested in knowing.
I thought $80 of deepseek usage for $10 was a pretty good deal, but I’d be delighted to hear of better ones.
OpenCode Go is the best deal in the market right now imo. Their quotas are so generous I often assume they are burning money, but I think they are largely thriving off of the subscription revenues and making it work, or their vendors are subsidizing things.
4 replies →
ollama cloud, syntetic - they both has much more care about quality of model hosting
> bug reports
> CI/CD test suites
None of these are considered important. Opencode is a vibecoded vibecoding tool, so 1) software quality is fundamentally unachievable and if they will pay attention to bugreports, they will simple drawn in them; 2) it's now a trend to delete tests in the name of AI ideology.
Do you mean the same OpenCode that has the owner shitposting on Twitter for most of the day typing in all lowercase?
Sorry, too busy vibe coding ship games.
https://x.com/thdxr/status/2110567456947507698
There's an actual team? I had the same experience and figured it was basically just one guy. Their issue backlog does seem a total shambles though.
All the power of LLMs in the hands but a page impossible to read on my phone...
Yup, Firefox on Android as well. The page scrolls in frames per MINUTE: scroll, wait 2 seconds, page instantly jumps to future scroll location.
Why? Loads fine on iOS 27 Safari.
Firefox on Android: scrolling is lagging, and when scrolling to far the text takes time to appear. Even text that was already there before.
The main animation is hungry.
yeah absolutely unusable, kinda insane to have access to fronteer models and produce a website that unusable
Based on this post, it sounds like a ton of great improvements.
I've only used OpenCode a bit, but I found it was sufficient for the workloads I was throwing at it. It wasn't quite enough to beat out Codex or Claude Code as my go-to choice, though. Perhaps I'll give this version a shot and see if they've gotten it over the hump.
out of curiosity, how or what do you use codex/claude code for that beats opencode?
Is there a way to buy tokens with a good model that makes OpenCode near as cheap as Claude Code with a Claude Pro subscription?
For personal projects, Claude Pro seems to give me a lot of tokens to use with Claude Code, and from experiments using other models with Claude Code (e.g. via Vercel) always seems way more expensive.
DeepSeek has very good bang for the buck if you're paying API prices.
There is opencode go [1] that gets you quite far compared to paying API prices. For example for the $10 subscription you get $80 in deepseek 4.1 flash credits.
[1]: https://opencode.ai/go
I don't understand the pricing on that page.
The headline figures are $10/month for 'Go' with "Generous limits" and $40/month for 'Go Plus' with "Higher limits".
Then, in the table below, picking (at random of course) Claude Haiku 5.5, I see it listing 3,850 'requests' per 5h for 'Go', 15,380 'requests' per hour for 'Go Plus'. Then there's another column saying that the "Monthly Usage" is $15 for 'Go', and $60 for 'Go Plus'.
What are the limits?
What's a 'request' and how does it relate to a token?
Why are the 'requests' figures per '5h' (the limit resets every 5h?)
Why are there 'Monthly Usage' dollar amounts that are in no way connected to the subscription costs, and what do they mean?
All the explanations below are just repeated rewordings of the same thing: "Go costs $10/month with generous limits and Plus costs $40/month with higher limits", as if that makes everything clear.
12 replies →
"From the beginning OpenCode adopted a client/server model."
+1 for knowing when to use a slash, not a hyphen.
Otherwise called OpenMemoryLeak, it eats memory like a piece of cake.
Moved to pi after killing my computer one too many times. It's like they think memory has never been cheaper.
Found out on 1.x it goes crazy with file watches. If you launch in a top level directory with lots of sub directories, iirc it can create millions of watches X2
Not sure if it's fixed in 2.x. There's some way to get it to not do that with ignore files or rules but not sure exactly how--I had Claude fix it...
Is this related to https://opencode.ai/?
Anomaly is the company behind OpenCode (https://github.com/anomalyco/opencode)
Yes.
[dead]
Anyone know how to turn off code mode?
I just tried the excellent local https://www.liquid.ai/blog/lfm2-5-24b-a2b model, but the model is trained to talk in bash, while OpenCode stubbornly expects JavaScript, and there seems to be no way to make them work together. The model itself performs excellently in pi.
OpenCode is a beast. Does it still try to take a disk snapshot of my working directory, even when it contains hundreds of millions of files? Does it still eat all of my memory? Does it still have a super-gigantic system prompt that wastes a solid percentage of my context window before I've even begun?
I switched to pi some months ago, and I have no complaints. It just does what it says, with no shenanigans. They updated the rendering approach recently so scrollback is nice and smooth now.
I was opencode user, but like few months ago tried pi and never looked back. Pi with open models is absolutely mind-blowing - my agents run with speeds not achievable with any remote frontier model - they certainly not as smart, but it doesn't matter because they do their "work done" perfectly and fast.
All problems I had with opencode are not presented in pi - it looks it's the best approach to guarantee most productive coding environment - speed, simplicity, transparency, absolute customization. I will certainly try this 2.0, maybe they have now improvements.
I switched to Pi after experiencing OpenCode V2 about a week ago. Dislike the UX direction a lot. I took some effort to sift through the Pi plugin ecosystem to get my setup in a good place.
I will say OpenCode has likely improved significantly from your experience. I never experienced any of that since ~May of this year when I picked up OpenCode the first time.
I am pretty new to it, but I like OpenCode. Except when it decided to build 430GB of snapshot data out of a simple Android application.
For me the distinguishing feature of OpenCode is the web ui/desktop app. I’m using OpenCode because it’s the only open-source agent-harness I’ve tried that runs outside of a TUI. I like terminals but not TUIs and especially not for prose-based interactions like prompting.
But that’s a shallow moat, and the rest of the features here are not particularly interesting to me. I don’t have a use for plugins or a model-server proxy (I can connect other tools directly to the model provider).
Unfortunately many subscriptions require you use their harness. In that case, I highly recommend using Termic (https://github.com/simion/termic/).
It's an incredibly useful GUI that lets you use the provider's harness, but adds extra productivity features. You can use OpenCode, Pi, Claude, Codex, whatever you want. The TUI runs in a window, but you can also pull up terminals, open tabs, keep projects, workspaces, show file diffs, give feedback on lines of code, review PRs, and way, way more. The number of features is impressive.
The devs are very quickly adding features, yet the app remains stable. And they fix bugs super fast! They fixed like three bugs and implemented two feature requests of mine within a week of asking. Best of all the whole thing is FOSS and they're not trying to make money off you. Absolutely awesome maintainers.
The OpenCode UI was OK to use for the first few months but then it basically didn't improve at all in the next -insert-too-many-months-.
It's long been surpassed by better UIs like OpenChamber. Looks like I'll be trying Paseo out next.
Have you tried https://github.com/openchamber/openchamber ?
Paseo <3
4 replies →
You should try dsh then. It also had a web ui.
hermes also has desktop app.
You sound like someone who might like what I'm doing with Juggler [https://juggler.studio]!
Nice work!
Are there any recommended sandbox patterns to use? Custom linux users or bubblewrap and managing openbao is getting to be a lot to manage each harness by themselves!
I've been using https://nono.sh which uses landlock instead of bubblewrap. I had a look at all the similar alternatives when I started using it and everything else I could find was far too vibe coded for me to trust, especially for this.
[dead]
Make sure to use the —standalone flag with sandbox invocations of opencode, else you will run the client in a sandbox but not the server.
Microsoft has mxc which I think is neat — not sure if it’s the right level of abstraction for your needs
https://github.com/microsoft/mxc
I am using v2 since its released I like OpenCode because of its user experience for TUI which imo is best for any coding agents out there but still there are rough edges which have to be resolved currently I am facing clipboard issue in Ubuntu/X11. I have not figured the root cause yet i hope they gt resolved
Okay, my iPhone is not good enough to run their vibecoded promo website
Must be safari then because my midrange android does without issue
this should not be an excuse for creating such a horrific website with eternity loading time.
it took me a while to figure out how to skip that intro...
Goes to check the repo out
> TypeScript
Considering the whole thing is LLM produced I would like an explicit answer as to why C++ or Rust weren't used to write the project in.
They refactored from golang to typescript too, which is wild.
Compiled languages make 3rd party plugins harder.
Also, the Rust ecosystem is annoying with demands for explicit answers to why their preferred language was not used.
I don't understand why compiled languages would make plugins harder. They just need explicitly defined entry points in libraries like DLLs. This has been existing for literal decades in other systems, for example Adobe plugins or Steinberg VSTs. It's not an unsolved problem.
2 replies →
> the Rust ecosystem is annoying with demands
One person != "the ecosystem"
1 reply →
Check out JCode. Over 20K Github stars, written in Rust.
https://jcode.sh/
https://github.com/1jehuang/jcode
Probably because of Effect.
It's a big improvement over the previous version. Currently, the Codex TUI has constant display issues for me, the most prevalent being random deviations of light/dark characters. So far no such issue in OpenCode. Since it's model agnostic, this might become my daily driver.
From my limited testing, oc2.0 doesn't support sock5 proxy in HTTPS_PROXY, while v1 supports.
I enjoy this program, and 2.0 is a great improvement.
Started work with OpenCode and my number one issue is that they do not cleanly document how to configure the settings to only run local ML models.
It is all focused on pushing prompts out to 3rd party providers that uses them for training. Irony is having to use the 3rd party provider to properly configure OpenCode with local only ML. I cannot have private information leak.
Good thing I tested it on open source code base before touching property code bases.
Huh ... is that related to why I see little Gemini hits constantly when selecting e.g. DeepSeek 4.1 flash on openrouter? I'm not going private for a bit (mac studio on the way) but when I do I want to lock it down, but pretty stuck on opencode for the moment. If it's leaky that's a problem.
Unfortunately, opencode v2 still has mandatory remote config loading from your model provider's .well-known/opencode url, which gives your model provider remote code execution on your machine.
"s" in "opencode" stands for security.
You should't really run a coding harness on your host computer anyway, because it is impossible to protect yourself from prompt injections and from an incredible amount of security vulnerabilities in the vibecoded plugins.
Security is fundamentally unachievable in popular coding harnesses.
The only right way to use it is in an isolated environment.
This isn't really true. You're talking about unattended execution, where the user doesn't review each action before letting the model proceed. I agree that it's bad to run that on a machine with important data, but I disagree that coding harnesses are fundamentally insecure just because the practice of reviewing each tool call has gone out of fashion. I do see harnesses these days not designed with that in mind, but that just makes those particular harnesses insecure, not the fundamental idea of harnesses as a concept.
3 replies →
The background task / subagent feature and the ability to specify a model when starting a subagent are so far my favorite improvements. Small things but make huge QoL difference in everyday development.
I had no clue you have to scroll down.
Good lord, me either. I thought it was a gag reading through these comments, but there was no way all of these people commenting were that locked into a joke.
Based just on the description, the desktop app is reinventing dsh. Then again reinventing frontends is a single prompt now, eh
OC is all right -- it's my daily driver -- but it could be better. I'd like a harness to let me customize the GUI, not just add MCPs and plugins. For example, I'd like add buttons to merge a PR, and show indicators for CI. Claude Code does a lot of this out of the box. Give me UI building blocks (buttons, labels, etc.) and wire them with my own functions. Could Code Mode enable this?
The built-in browser is a most welcome feature.
PS(A): Opencode Go is a great deal and now has a $40 plan.
Look at Paseo and build your own backend and UI plugins while still using opencode.
https://github.com/getpaseo/paseo (first time I'm seeing this, reading through I'm not sure this is for me)
Scion was the tool I'd been using for this, but haven't been doing that kind of stuff for some time.
https://googlecloudplatform.github.io/scion/overview/
4 replies →
Thanks for the great recommendation. In the meantime, if anyone wants to contribute to GUI plugin support for OpenCode, here is a PR under review: https://github.com/anomalyco/opencode/pull/55246
[dead]
It looks like they finally fixed the issue where the system prompt at the start of the transcript was regenerated from scratch every request, leading to significantly higher input costs. Unfortunately it's still rewritten whenever you revert to an earlier point in the conversation, but at least it's not on every single request.
This game is quite interestingly fun despite how basic it is.
So about this point-and-click game: Am I supposed to carry this floppy disk 2408 times between those PCs? Or I missed some obvious detail?
These guys stole money from me. It amounts to like 10 US or something, so not significant, but still...
Their models have pricing published in their docs, like any other LLM provider. I measured the tokens I consumed, did the math, and it was always off, in their favor. One model (GPT Luna) was about 2x as expensive as advertised.
I joined their Discord, which is apparently how you get support from them. I filed a bug and someone from their team replied, we verified the data, and he said that something was indeed off and that he'd escalate it. Then silence. After 2–3 weeks, I followed up and was now ignored.
As I said, the amount isn't material to me, but if they do this a million times, they could make some decent money out of it. No idea if it's on purpose, I'll leave that to the reader to speculate.
Overall, their complete lack of interest after acknowledging the "bug" left a really bad taste in my mouth, so I decided to leave.
Ahh. I recall their opencode go plan offered $60-$80 worth of Deepseek for $5-10 or something? I was debating if I should try it out but I think this is convincing me not to...Thanks for the heads up
Can you link to the discord thread? I'm very much interested and I'll be double check my usage vs. their rates.
Sure, shoot me an email (see profile).
I'd prefer not to share my Discord username here.
[flagged]
I guess I"m the only person with complaints here.
I tried opencode 2 with my locally hosted llama, and I noticed that llama is always producing stuff even when I close opencode. I suspect it's the backend still doing stuff with the frontend isn't displaying, but I have no way of investigating. So I'm sticking with 1.9 for now.
Performance is horrible both of the website and of the tool itself.
That's why I first switched to Pi and then to DeepSeek harness.
Is the tool performance you mentioned for v1? Or is v2 of the tool also performing badly?
9 months ago I had opencode fill my 2tb storage with temp files and if I delete it’d redo it on session start. From that time onwards I have not gotten around to building my own verification pipeline to convince me that opencode won’t do it again. I guess I wanted to highlight that verification is what would sell me on opencode again.
I have been using open code and it is horrible with ram usage. Every subagent takes like 300 MB of RAM. As they are vibe coding, i think they should use language that consumes less RAM eg. Rust or C.
Huh. I submitted this exact thing four days ago. I wonder why it didn't get marked as a duplicate?
https://news.ycombinator.com/item?id=50041870
From https://news.ycombinator.com/newsfaq.html
> If a story has not had significant attention in the last year or so, a small number of reposts is ok. Otherwise we bury reposts as duplicates.
In my experience, if a story gets 4-5 points and < 5 comments, it hasn't gotten "significant attention" and a repost gets a second chance. That's not data, just anecdote.
Essentially, all I get from opencode is "Error: opencode-ai's postinstall script was not run."
No matter how many times I run the postinstall script, it still comes up in a few hours or days. On various Linuxes and on macOS.
I had to update because the previous OpenCode 2.0.3 I had installed stopped working suddenly. I love the idea behind OpenCode but compared to managing Claude and Codex, it's such a pain and requires continuous debugging or managing.
Is there azure login capability, for az login? We are 100+ devs and claude code has this built in by default where we can host our own models in Azure Foundry. Devs don't need any keys since they can just use az login and it just works.
Yes. Their docs have a providers page. I was able to set it up pretty easily
Never got used to opencode honestly, there is always this clunky feeling (same with pi but at least i can customize it more than anything.) and this feeling didn't go away with 2.0 either :/
I use OpenChamber as my IDE. It uses OpenCode behind the scenes. I've not really noticed a difference in OpenCode v1 vs v2 but I guess it's because OpenChamber does a great job dealing with those details.
The site took a minute to load in completely and when I scrolled to the bottom I couldn't read the SDK text, it was literally cut off, kinda resembling the current state of coding very accurately lmao
Judging by comments opencode seems popular. Why is it not in the top ranking coding agents on openrouter? HN's darling Pi is there, along with few others which I never heard about, but not opencode.
Maybe because of their rich provider ecosystem allowing you to use a whole bunch of subscriptions in it. I use OpenCode Go and OpenAI for almost everything, almost never touching OpenRouter.
I find it odd that opencode is not even in the top 50 of coding apps on openrouter. I wonder if it's just .. somehow not counting or missing?
haven't upgraded yet to 2.0 but wanted to comment and just say thanks to the opencode/anomaly team for the generous (no-login) free tier.
you install the software and it just works, no login no nothing.
Agreed. Although, limiting it to opencode has been a fool's errand thus far, it's way too easy to "unlock" anyway.
tried opencode for the first time to use the $200 in api credits that come with claude max but can't be used in claude code. it's great. the free nemotron 3 model is even decent, i love seeing agentic coding accessible to students and hobbiests and folks that can't drop $200/mo.
i used the bonus anthropic credits to get ornith 1.5 35b q8 running on a jetson. it's no opus 5, but it's usable for real coding and sys admin work, and works great in opencode. at least as good as sonnet 4. 5 token/sec is a little painful though.
- Miserable startup times are now "solved" by leaving it always running.
- Someone in this thread said the curl installer was slow because the install script needed cute progress bar rendering. To be clear, I don't care about the installer user experience, but I want to spend a moment on this point, because having used OpenCode for over a year, I think this perfectly sums up the entire experience. A commit born from "Claude, please make the installer look sick as fuck with loading bars and stuff" will always be preferred by the developers over a commit that reverts such a change for a 10 MB drop in memory use.
- Tried to read the unreadable announcement website after waiting for the little ThreeJS demo to load. I gave up.
- Logs from various old sessions leaked up to 16GB on some temp folder on my drive. The harness prompts are still token heavy. I know neither of these are real issues, and chat logs are a useful feature for many, but I felt validated to see someone else in the comments also complaining about the silent storage of chat sessions leaking into my drive in a random folder being the default behaviour.
IMO, this release goes far beyond OpenCode. I had always imagined that the advent of LLMs developing human-level coding abilities, combined with the high hardware prices as a result of it, would act as a forcing function to inspire a new generation of ultra-performant, bloat-free open software.
But this release is proving me wrong in every way.
We are entering a new era, what George Hotz coined "maximalist software": A new dawn of computing, where one one hand, we can simply prompt a superintelligent LLM to "please prove the Riemann hypothesis", and it will actually work. On the other hand, the chat log for the proof disappeared, because because the 2 GB Bun server (yes, the one meant to interact with a plaintext LLM API) just crashed.
> A commit born from "Claude, please make the installer look sick as fuck with loading bars and stuff" will always be preferred by the developers over a commit that reverts such a change for a 10 MB drop in memory use.
Not my experience. YMMV
> I had always imagined that the advent of LLMs developing human-level coding abilities, combined with the high hardware prices as a result of it, would act as a forcing function to inspire a new generation of ultra-performant, bloat-free open software.
I mean, faster and better hardware has never resulted in more efficient software, I really didn’t expect it to be any different here.
>faster and better hardware has never resulted in more efficient software, I really didn’t expect it to be any different here.
I agree with this.
By "high hardware prices", I am implying that we are not getting faster and better hardware.
NVidia halted 5090 production yesterday. As a consumer, where can I buy this faster and better hardware you speak of?
1 reply →
mmh what is going on?
anyone knows?
source:virustotal
https://opencode.ai/update/api/latest/desktop/opencode/openc...
application/x-apple-diskimage Last Analysis Date 3 days ago Summary Detection --- SOCRadar Malicious --- ZeroCERT Malicious ---- Gridinsoft Suspicious --- ??
https://x.com/mattjay/status/2111480005435719885
they deprecated the old layout which I very much preferred in open code desktop. I'm never in a rush so I'll wait for the early adopters to vouch for this release.
I've been getting good results from OpenCode. Has anyone been able to get it to work with local models though? It doesn't seem to want to play nice with Ollama.
I have an open code server running as a service on a linux desktop with the port opened up so I can use the web UI from my windows laptop. The same linux desktop is running Ollama and I'm currently using qwen3.6:35b with it.
The setup was mostly for the learning experience and I haven't done any serious work with it, but it's been great for writing bash scripts.
I used OpenCode to help me install ollama, Qwen local LLM, and connect OpenCode to it.
The computer is very slow (old Dell Optiplex running Mint Debian Linux), but it worked! So cool to turn off the network, and still be able to chit-chat with Qwen model ("Tell me a joke about...").
cool, I'll have to mess around with it some more. I don't expect to be able to do any real work with my 16GB MacBook Pro, but eventually, I would like an all local setup.
I have no issues using it with llama.cpp.
I basically only have eyes for Claude code. Sell me on this?
It works, but the CPU utilisation is huge even if it's idle, and after it allocated 40 gb of RAM on my laptop once, I've stopped using it.
Can someone tell me what am I missing if I just use the Claude extension via vscode instead of opencode? I use codex as well but only as mcp for reviews
I was finally forced to go CLI from the VSCode extension because its treatment of sub-agents is abysmal.
If workspaces had a way of managing separate Go subscriptions for team members, a large chunk of my org would jump in. DS and GLM are solid for a lot of tasks.
Stopped using Open Code because it's too buggy and can't even rename the project. Sharing this because I wanted to use it.
What do you mean by it can't rename the project? Which project? OpenCode?
OpenCode is a vibecoded vibecoding tool. From that kind of software you really shouldn't expect things like renaming of a project to work all the time.
I mean this neutrally: quality is not something that these projects strive for. Other values are a priority: features, speed of development, etc.
What would you recommend instead?
their client server model is a fantastic idea and the core reason i started building https://wingman.actor a year ago.
unfortunately making a great harness is tricky and i often just steal with things i like from ocv2 and pi.
been using ocv2 as my daily driver for a while and had very little complaints. its a great product from a great team.
> their client server model is a fantastic idea
It's not. A permanently running buggy() server on your computer instead of a screen or tmux session is not something that should be a default solution.
I mean it neutrally. Software quality is not a value in code harnesses. Something else is a value: speed of development, features, etc. But quality is ignored.
I'm a Vim user and I actually like the web interface of AI better than the TUIs, which is weird perhaps.
You may like pi-web-ui, it has a ton of useful functionality. Was a bit rough around the edges before but it's improved quickly. (https://pi.dev/packages/pi-web-ui)
I was a Vim user that switched to VS Code (for reasons) and now the TUIs are where my Vim personalization efforts have been redirected. Pi is a good harness for vim users to consider if they want to try a TUI experience. The Pi plugin ecosystem is a slopfest though. There are vim bindings for Pi and OC (and VS Code) because I'm never going to give those up.
The site is barely useable/slow/hangs on my crapola Moto G Play 2024.
Does it still have rediculous system prompt alignment preventing use on red teams?
It's open source so... It does if you want it to. ;-)
Did anyone find out what numbers trigger something on that counter box on the left?
can someone recommend what plugins/skills they use with opencode, esp with the free models in Zen, and your coding setup?
Is it still super bloated?
Much more now. They run a permanent background server by default.
> We've built a minimal JavaScript interpreter
Huh?
This scared me even more than all the other security issues (like hot reloading of plugins, permissions not being followed, etc.).
A vibe coded minimal JavaScript interpreter? This sounds dangerous af.
With several thousand of open issues on GitHub already.
Are we just ignoring security when it comes to harnesses?
This should be the top comment. This is frankly very alarming that they think this is a reasonable approach.
Imagine if there were already existing ones like QuickJS...
They intentionally skipped QuickJS because it's "too complicated" (paraphrasing) which I think is a decision they'll regret.
1 reply →
Is still forbidden to use Claude Code accounts with other harnesses? I will try with DeepSeek later, but it would be better if I could use Claude subsidized as well
There's this amazing three letter harness that had all those features and more for many, many months already, but many aren't ready for that conversation
Why are “many aren’t ready for that conversation” about a harness?
Then name it, because not everyone knows about it. Another commenter said it might be omp.
Agreed, DSH is pretty great
omp?
ah man, I wanted this domain but I'm pleased to see it's at least being put to use instead of squatted
what happened to crush(charmbracelet/crush), it was being told as opencode successor?
What in the hell is wrong with this page? Whole blocks of content disappear and reappear on my phone as I scroll. Eventually the page just starts force reloading. It’s a blog post! What could possibly require … whatever this is?
> What in the hell is wrong with this page? Whole blocks of content disappear and reappear on my phone as I scroll. Eventually the page just starts force reloading. It’s a blog post! What could possibly require … whatever this is?
You're looking at software written by SOTA AI.
having a daemon PID helps for web gui, but may bite in unexpected ways under extensive parallization.
how do you beat the game? What does the little box on the left do?
nice animation. but can you convince me to switch from Codex?
What the heck is this website, it completely locks up the tab it's in for 15 seconds and none of the text shows up at all until it finishes.
2.0 is a big disappointment so far.
Several basic things don't work, like hiding the sidebar.
With 3.2k open GitHub issues there's no point reporting anything.
Somehow I manage to get issues noticed and PRs merged. They aggressively cull old issues but if they take notice things get done. I contributed just this week.
I too have been able to get several issues addressed and pull requests merged (not mine, others had noticed first).
I had one this week that, while took some effort to explain the why, was handled better than I expected. (https://github.com/anomalyco/opencode/pull/54921)
Being the most popular open harness, they get inundated with slop and are doing their best (imo).
Everyone copies https//maki.sh. I've been the first!
curl | sh should die
The monkey's paw curls, now it's "Give your agent a link to our SKILL.md!"
oh coolio
I was annoyed that it takes just as much ram if not more than 1.0
pi-mono is better
Bros - that opening disk transfer interaction is peak awesomeness. I copied about 4 files and did not want to stop...Id sit there all day and do all of them just to see what happens in the end...perhaps later this weekend.
I really hope we don't get a slew of WebGL-intensive sites.
I can hardly scroll this page on my pixel 6.
Don't worry, it's janky on my Pixel 11 as well
[flagged]
[flagged]
[flagged]
[flagged]
[flagged]
[dead]
[dead]
[flagged]
[dead]
[dead]
I would expected that they also rewrite it in Rust, but that's life, what a missed opportunity! /s