Home / AI/LLM / llm-wiki-memory

llm-wiki-memory

ctxr-dev/llm-wiki-memory
★ 107 stars JavaScript AI/LLM Updated today
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.
View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "llm-wiki-memory": {
      "command": "npx",
      "args": [
        "-y",
        "ctxr-dev/llm-wiki-memory"
      ]
    }
  }
}

README Excerpt

<div align="center"> 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. Memory lives on your machine as plain Markdown in an [LLM wiki](https://github.com/ctxr-dev/skill-llm-wiki) versioned in git, searched with local embeddings, and consolidated offli

Tools (14)

MEMORY_LLM_BASE_URLMEMORY_LLM_MODELMEMORY_LLM_PROVIDERMEMORY_LLM_TIMEOUT_MSMEMORY_MCP_SERVER_NAMEaudit_memoryconsolidate_memorymove_documentrecall_lessonssave_lessonsave_to_datasetsearch_memorytransformerswrite_memory

Topics

agent-memoryandrej-karpathyandrej-karpathy-llm-wikiandrej-karpathy-skillsclaude-codeembeddingsllm-wikimemoryragsemantic-search

Related AI/LLM Servers

gemini-cli ✓ Clean★ 97.7K
An open-source AI agent that brings the power of Gemini directly into your terminal.
AI/LLM TypeScript
private-gpt ✗ Risk★ 57.3K
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more....
AI/LLM Python
context7 ✗ Risk★ 49.0K
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
AI/LLM TypeScript
headroom ★ 47.0K
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers....
AI/LLM Python