Rainman gives AI coding tools local project memory
Rainman is an open-source tool that helps AI coding tools remember past code, failed fixes, and useful project decisions. It runs on your computer and does not use an LLM, so it adds no tokens. This can help AI agents avoid repeating work and may lower cost during long coding sessions.
Key points
- It can build project memory from Git history and file structure.
- It can connect to Claude Code through MCP and bring back relevant memories during a session.
- It works without LLM calls, so it does not add tokens to the bill.
- It is still a small open-source project, so teams should test it before relying on it.
Quick term guide
- open-source
- Software whose code is shared publicly so others can inspect, use, or change it.
- AI coding tool
- Software that uses AI to help write, edit, or explain code.
- compute
- The server power and chips needed to run AI systems.
- tokens
- Tokens are small pieces of text that AI systems count when reading or writing.
- AI agents
- AI agents are AI tools that can carry out steps toward a goal, not just answer once.
- AI agent
- An AI program that can inspect information and suggest what to do next.
- session
- A continuous period of interaction between a user and a computer program.
- LLM call
- Sending a question or instruction to an AI language model (like ChatGPT or Claude) and receiving its response.