#24 · Primary category： Knowledge Base & RAG
WeKnora
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
Project last updated：08/29/26
GitHub Stars
20.9K
Forks
3.0K
Contributors
199
License
Other
Why we included this project
Teams that want to query their internal documents without building a RAG stack from scratch can point WeKnora at their files and start asking questions. It ingests PDFs, Word, images, Excel, and sources like Feishu, Notion, Yuque, and RSS, then answers through a web UI, embeddable widgets, IM channels (WeCom, Slack, Telegram), and a CLI. For multi-step questions, a ReAct agent can pull in retrieval, MCP tools, and web search, while wiki mode turns documents into an editable, interlinked knowledge base with revision history. You can swap LLM providers, vector stores, and storage backends, and multi-workspace RBAC with audit logs covers enterprise needs. It's a self-hostable option if you want both quick Q&A and agentic reasoning over your own data.
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