by ctxr-dev · MCP Server · ★ 102
Persistent local memory for AI coding agents. Your agent remembers every session, learns from its mistakes, and gets smarter the longer you work with it. Claude Code, Cursor, Codex, and every other MCP client forget everything when a session ends. LLM Wiki Memory fixes that: it captures your conversations, compiles them into durable project knowledge and lessons your agent applies next time, and recalls the right context through a local MCP server.
| Stars | 102 |
| Forks | 0 |
| Language | JavaScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 68.9035043558658/100 |
| Last Updated | 2026-07-05 |
| Created | 2026-05-22 |
| Platforms | claude-code, docker, mcp, node |
| Est. Tokens | ~25k |
These tools work well together with llm-wiki-memory for enhanced workflows:
Explore other popular mcp server tools:
llm-wiki-memory is 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.. It is categorized as a MCP Server with 102 GitHub stars.
llm-wiki-memory is primarily written in JavaScript. It covers topics such as agent-memory, andrej-karpathy, andrej-karpathy-llm-wiki.
You can find installation instructions and usage details in the llm-wiki-memory GitHub repository at github.com/ctxr-dev/llm-wiki-memory. The project has 102 stars and 0 forks, indicating an active community.
llm-wiki-memory is released under the MIT license, making it free to use and modify according to the license terms.