Local, git-versioned memory for AI coding agents. No RAG, no Docker, no external service. Capture, compile, recall over a local LLM wiki with on-device embeddings and an MCP server.
Capture and store conversations with your AI coding agent, allowing it to remember and apply knowledge in future sessions (Claude Code required)
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeLocal, git-versioned memory for AI coding agents. No RAG, no Docker, no external service. Capture, compile, recall over a local LLM wiki with on-device embeddings and an MCP server.
llm-wiki-memory has 128 stars on GitHub. It has been forked 2 times. llm-wiki-memory is written mainly in JavaScript. It has been in active development since 2026. llm-wiki-memory is available under the MIT license. Its main topics are agent-memory, andrej-karpathy, andrej-karpathy-llm-wiki, andrej-karpathy-skills.
Local, git-versioned memory for AI coding agents. No RAG, no Docker, no external service. Capture, compile, recall over a local LLM wiki with on-device embeddings and an MCP server.
llm-wiki-memory is an open-source project. It is released under the MIT license.
Yes. llm-wiki-memory is free and open source — you can use, modify and self-host it.
llm-wiki-memory is available under the MIT license.
llm-wiki-memory is written mainly in JavaScript.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/ctxr-dev-llm-wiki-memory.html)