← Back to context

Comment by CuriouslyC

5 days ago

Aider is almost there, in fact it's intentionally "not" there. You can set it up to do things like run test/static analysis automatically and fix errors, and work with it to get a to-do list set up so the entire project is spec'd out, then just keep prompting it with "continue...". It has a hard coded reflection limit of 3 iterations right now, but that can also be hacked to whatever you want. The only thing missing for full agentic behavior is built in self prompting behavior.

4 comments

CuriouslyC

Reply
diggan  5 days ago

> The only thing missing for full agentic behavior is built in self prompting behavior.

Correct me if I'm wrong, but Aider still doesn't do proper tool calling? Last time I tried it, they did it the "old school" way of parsing out unix shell commands from the output text and ran it once the response finished streaming, instead of the sort of tool call/response stuff we have today.

  • sandinmyjoints  5 days ago

    I think this is still the case. There are some open issues around this. I am surprised they have not moved forward more. I find Aider hugely useful, but would like the opportunity to try out MCP with it.

  • Karrot_Kream  5 days ago

    There's an open PR for MCP integration (actually 2 PRs but one has more community consensus around it) with a Priority label on it but it hasn't been merged yet. Hopefully soon.