Illustration of what WeKnora does: Self-hosted platform that turns documents into RAG search, an agent and a wiki

Tencent /

WeKnora

Self-hosted platform that turns documents into RAG search, an agent and a wiki

Open on GitHub (opens in a new tab) Website (opens in a new tab)

WeKnora is a knowledge platform from Tencent, written in Go. You upload documents (PDF, Word, Excel, images and more) or sync them from tools like Feishu, Confluence, Notion and GitLab. They become knowledge bases that three features share: RAG question answering with citations, an agent for multi-step tasks, and a wiki that organizes the content.

The agent can search the knowledge bases, call external MCP tools, run installed skills in Docker, E2B or Cube sandboxes, and operate your own Chrome or Edge through a browser extension. It also keeps long-term memory across sessions, which the user confirms.

Compared with a plain RAG chatbot, it adds workspaces with role-based access, audit logs, chat channels such as WeCom, Slack and Telegram, and a built-in MCP server so tools like Cursor or Claude can query your knowledge bases. Models, vector databases and storage are swappable, including local Ollama models.

What it does

  • RAG with citations

    Hybrid search and multimodal document parsing give answers over your own knowledge bases, with sources you can check.

  • Agent with tools and sandboxes

    Multi-step reasoning with skills installed from ClawHub, SkillHub, Git or ZIP, run in sandboxes with a terminal and desktop. It can also use MCP tools and your local browser.

  • Wiki and knowledge graph

    Documents can be organized into a wiki with a knowledge graph (the neo4j profile) and rollback of changes.

  • Many data sources and models

    Auto-sync from Feishu, Confluence, Notion, Yuque, GitLab, RSS and others. 27 built-in model vendors include OpenAI, DeepSeek, Qwen, Gemini and Ollama.

  • Team controls and deployment options

    Multi-workspace roles, audit logs and Langfuse tracing. Deploy with Docker Compose, Helm, or a Lite single binary that needs no external services.

What you could build

  • Build a searchable internal knowledge base that answers staff questions with cited sources.
  • Run an agent that reads company documents and finishes multi-step tasks using sandboxed skills.
  • Sync Feishu, Confluence or Notion content and keep it organized as a wiki.
  • Answer questions from your documents inside WeCom, Slack or Telegram.
  • Expose a knowledge base over MCP so Cursor or Claude can query it.

Get started

Clone the repo, copy .env.example to .env and edit it, then run docker compose pull and docker compose up -d. Open http://localhost and follow the onboarding guide. For local models, start Ollama first. Docker, Docker Compose and Git are required.

git clone https://github.com/Tencent/WeKnora.git
cd WeKnora
cp .env.example .env

Commands are copied from the project's README. Read it on GitHub for the full setup.

More in Memory, RAG & data

See all
firecrawl Web API that turns sites and search results into markdown or JSON for LLMs 194.3k6.7k markitdown Python tool that turns PDFs, Office files, audio and more into Markdown for LLMs 191.7k3.8k graphify Maps a codebase and its docs into a knowledge graph your AI assistant can query 133.1k9.9k claude-mem Saves what your coding agent does and feeds the useful parts back into later sessions 102.3k7.2k vectorize-io/hindsight Memory server that lets AI agents store, search and learn from past interactions 52.8k8.1k OpenViking A context database that stores agent memory, docs and skills as browsable files 40.6k1.5k open-notebook Self-hosted research notebook that chats with your documents using any AI provider 40.5k776 supermemory Memory layer that lets AI assistants and apps remember users across conversations 31.4k296 gbrain A shared memory for AI agents that stores sourced facts and answers with citations 31.1k593 qmd Local command-line search for your notes, docs and transcripts, with AI re-ranking 30.6k421

    ↑↓ to move, Enter to open, Esc to close