#143 · Primary category: Knowledge Base & RAG
swarmvault
The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal knowledge management, AI second brain, and durable Claude Code / Codex / OpenClaw memory.
Project last updated:06/30/26
GitHub Stars
673
Forks
78
Contributors
2
License
MIT
Why we included this project
Most people's notes and transcripts never quite become something they can actually search and reuse. SwarmVault is a local toolchain that fixes that: it ingests files, directories, or public GitHub repos, keeps the originals untouched on disk, and has an LLM compile them into markdown wiki pages plus a machine-readable knowledge graph you can inspect and query. The CLI walks you through ingestion, compilation, review, and graph navigation, and hybrid search that combines full-text and embeddings keeps queries fast even as the vault grows past a few hundred pages. It also feeds coding agents: an MCP server and context-pack generation let Claude Code, Codex, and similar tools draw on the same vault, so it can serve as both a personal second brain and durable agent memory. Everything runs locally and offline with no API keys required, which matters if you'd rather not send your notes to a cloud service.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Understand-Anything
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
crawl4ai
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
docling
Get your documents ready for gen AI
anything-llm
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience