WeKnora
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
What is WeKnora?
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
Overview of WeKnora
What it is
WeKnora is an open-source, LLM-powered knowledge framework for enterprise document understanding, semantic retrieval and reasoning. It brings a team's documents together so they can be searched, reasoned over and kept up to date.
Key features
- Three modes on the same knowledge bases: RAG for lookup, an autonomous agent for multi-step tasks, and a wiki for organizing knowledge.
- The agent's toolbox: skills installed from ClawHub / SkillHub / Git / ZIP run in session-persistent Docker / E2B / Cube sandboxes, with an interactive terminal and graphical desktop. BrowserSkill extension operates the user's own Chrome or Edge, and external MCP services (OAuth included) can be connected.
- Memory and curation: cross-session long-term memory stores user profile, preferences and confirmed facts. Folder uploads keep directory trees; retrieval chunks can be edited, diffed and rolled back.
- Data sources and formats: auto-sync from Feishu wiki / Feishu Drive / Confluence / GitLab / Tencent IMA / Notion / Yuque / DingTalk Docs / Seafile / RSS. Supports 10+ document formats including PDF, Word, images, Excel and XMind.
- Channels and integrations: Q&A in WeCom, Feishu, Slack, Telegram and other IM apps; an embed widget for external websites; a built-in MCP Server for Cursor, Claude and other AI tools; scoped API keys with a principal model.
- Models: 29 built-in vendors with a generated model catalog, including OpenAI, DeepSeek, Qwen, Zhipu, Hunyuan, Gemini, MiniMax, NVIDIA, LiteLLM and Ollama.
- Permissions and operations: multi-workspace RBAC (four roles, per-resource ownership, per-workspace audit log), several storage instances per workspace, a runtime task-queue dashboard with worker-pool governance, and Langfuse tracing.
Use cases
- Enterprise document understanding and semantic retrieval.
- Multi-step reasoning tasks using an autonomous agent.
- Team knowledge management with a self-maintaining wiki.
Getting started
Run with Docker Compose (requires Docker, Docker Compose and Git):bashgit clone https://github.com/Tencent/WeKnora.gitcd WeKnoracp .env.example .env # Edit .env as needed, see comments in the filedocker compose pull # Pull the latest imagesdocker compose up -d # Start core servicesThen open http://localhost and follow the onboarding guide. For other deployment options (Kubernetes, Lite single binary, Desktop app) see the repository README.
License and pricing
The license is not explicitly stated in the repository metadata (NOASSERTION), but the project is marked as open source.
Based on the project's public README and repository metadata.