Comment by ig0r0
2 days ago
I wrote a similar post some time ago just used ollama and opencode https://blog.kulman.sk/running-local-llm-coding-server/
2 days ago
I wrote a similar post some time ago just used ollama and opencode https://blog.kulman.sk/running-local-llm-coding-server/
Ollama is not a good choice - https://sleepingrobots.com/dreams/stop-using-ollama/
As for oprncode, doesn't the system prompt eat too much of the context? Local models are really constraint in regards contex, and opencode AFAIR uses a 10k of it or some thing close.
[dead]
Did you have any issue with tool calling inside opencode? I tried the same approach, but my models don't see any tool.
No issues with OpenCode and the Qwen models. Some issues with Pi because it uses different tool calling format, but I solved that with an extension.
actually useful and the ollama gui could probably even simplify this more.
this is the way, given anyone could swap for oh my pi / pi / etc
yes, whether for home experiments or at work, it is good practice (good hygiene) to be able to swap out both agentic harnesses and models. It is important to have a good strategy for exporting skills, etc.
yeah, I am using Pi right now, I switched from OpenCode