What it does
WeKnora gathers a team's documents so AI can search them, reason over them and keep them organized. It offers three ways to work: ask questions answered from your documents, hand multi-step tasks to an AI agent, or organize knowledge as a wiki.
It can sync from tools such as Confluence, Notion and Feishu, reads more than ten file types, and can answer questions inside chat apps like Slack, Telegram and WeCom. It supports many AI model providers, including local models through Ollama.
It can be deployed on your own servers so the data stays in your environment, and it includes team permissions and audit logs.
Who it's for
Companies and teams who want a private, AI-powered knowledge base.
Can I use it without coding?
With some setup. Self-hosting uses Docker Compose; there is also an online platform tied to WeChat. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Server, Cloud
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Not needed
Try it
- Use the online WeChat platform, or set WeKnora up on your own server with Docker.
- Open it in your web browser and follow the onboarding guide.
- Choose an AI model, either from an online provider or one running locally.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- No standard license listed. Check the GitHub page before using it for business.
- More on staying safe