by yan-yanko · MCP Server · ★ 22
Rainman Context-aware project memory for AI coding tools. Remembers what you've built, what failed, what works — and surfaces it when your AI assistant needs it. Zero LLM calls. Zero external dependencies. Runs locally. No embeddings, no API calls — zero tokens to store and rank memory. Recalled memories are injected as ordinary context (the relevant slice, not your whole history), so they cost normal input tokens only when actually used — fewer than pasting your full CLAUDE.md into every prompt. Why This Exists We were debugging a systematic voting bias in an election predictor.
| Stars | 22 |
| Forks | 2 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 72.9192607853307/100 |
| Last Updated | 2026-07-04 |
| Created | 2026-06-05 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~16k |
These tools work well together with rainman for enhanced workflows:
Explore other popular mcp server tools:
rainman is Context-aware project memory for AI coding tools. Zero LLM calls. Runs locally.. It is categorized as a MCP Server with 22 GitHub stars.
rainman is primarily written in Python. It covers topics such as ai, claude-code, context.
You can find installation instructions and usage details in the rainman GitHub repository at github.com/yan-yanko/rainman. The project has 22 stars and 2 forks, indicating an active community.
rainman is released under the MIT license, making it free to use and modify according to the license terms.