[shaurya-sethi]

hi gabriel, the problem you are trying to solve is valid, but both claude-code and codex natively support local models ran through ollama. i've tried doing this before, and SLMs still fail to do basic tasks because they are put in a harness that has too many features and tools.

i've had really good success though in using them in minimal harnesses like pi-coding-agent. without an open-source repo it would be difficult to guess/assume what your approach is, but i hope you're thinking in the same direction and not trying to reinvent the wheel.

best, shaurya

[gabriel_oauth]

That's funny inventing the wheel was already done and inventing agents was also already done this approach gives the agent enough tools to understand what it is working with in the code base configurations with local llms with codex and claude-code gives it too much to work with but giving it the right dose of tools can scale well try it yourself it's easy to setup