itayinbarr/little-coder

A coding agent tuned for small local models, built on top of pi.

The research story behind all this — why scaffold–model fit matters, how a 9.7 B Qwen beat frontier entries on Aider Polyglot, and what the load-bearing mechanisms actually do — is written up on Substack: Honey, I Shrunk the Coding Agent. Start there if you want the "why"; stay here for the "how".

pi is the minimal substrate — agent loop, multi-provider API, TUI, session tree, compaction, extension model. Four built-in tools (read / write / edit / bash) and a ~1000-token system prompt.

little-coder is pi + 20 extensions + 30 skill markdown files + a Python benchmark harness. It doesn't fork pi or shadow its CLI — pi is a plain dependency in package.json, and everything little-coder-specific lives under .pi/extensions/, skills/, and benchmarks/. The launcher runs pi with --no-extensions and wires in exactly the bundled set, so you add your own extension by dropping a directory into .pi/extensions/ (or passing little-coder -e /path/to/ext/index.ts at launch) and remove one of ours by deleting its directory. Note this also means a globally pi install'd package won't load inside little-coder — pi install registers into pi's settings, which --no-extensions skips.

If you've never used pi, it's useful to skim pi.dev first — the rest of this doc assumes pi's model of --agent-import-path, --mode rpc, and .pi/extensions/ auto-discovery.