#157 · Primary category： Knowledge Base & RAG
docsagent
DocsAgent is a local-first AI documents assistant that lets you securely index and chat with thousands of desktop documents with zero cloud leakage.
Project last updated：05/19/26
GitHub Stars
615
Forks
8
Contributors
2
License
Apache-2.0
Why we included this project
DocsAgent is a local-first document assistant that indexes the files on your desktop and lets an AI agent actually read them. It parses PDF, Word, and PowerPoint into a searchable index that combines semantic and text matching, so you can find a specific clause in a contract or a passage buried in a long research paper. The index is exposed through a CLI and a Model Context Protocol server, which means tools like Claude Code, Cursor, and OpenClaw can query your documents without the data ever leaving the machine. There are also ready-made MCP integrations for Zotero libraries and Obsidian vaults, so researchers and note-takers can point an agent at collections they already maintain. If privacy matters to you, or you just want a self-contained assistant that does not depend on the cloud, this is a practical option.
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