CoreCoder
Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder.
Learning how a coding agent works, or forking a minimal base to build your own.
You want a production-grade agent; the project positions itself as a foundation to learn from, not a competitor.
About CoreCoder
The nanoGPT of coding agents. 1,081 lines of pure Python — understand how a coding agent actually works, then fork your own.
The nanoGPT column is there as a reference point: minimal, readable, but it teaches you to train a GPT. CoreCoder is after the same thing, only the subject is an agent that actually edits code. Sitting it next to Claude Code and aider isn't about competing for their users. CoreCoder is the foundation you stand on while you learn from them and get going; it isn't in the same race.
I've always felt coding agents get talked about as if they were arcane. Strip a tool like Claude Code or Cursor all the way down and the core is a while loop wrapped around a large model, plus seven or eight tools that let it actually do things. The hard part was never the loop; it's everything the loop has to cope with once it meets the real world. CoreCoder is the minimal version that writes that core out honestly.
CoreCoder is an open-source project written primarily in Python, with 1.8k stars on GitHub. It was last updated in September 2026.
pip install -e .CoreCoder vs. the alternatives
All 49 alternatives →| Record | Stars | Pricing | ||
|---|---|---|---|---|
| CoreCoderthis listing | 1.8k | Python | MIT | Open source |
| OpenCode | 211k | — | MIT | Open source |
| gemini-cli | 107k | TypeScript | Apache-2.0 | Open source |
| Zed | 91k | Rust | GPL-3.0-or-later | Open source |
| OpenHands | 89k | — | MIT | Open source |
| Cline | 69k | — | Apache-2.0 | Open source |
