WeKnora

What is WeKnora?

WeKnora is Tencent's document understanding and retrieval platform. It parses PDFs, Office files and images (with OCR), builds knowledge bases with vector, keyword and knowledge-graph retrieval, and answers questions through a chat UI, agents with MCP tools, a web embed, IM integrations and an API. Workspaces have member roles and can share knowledge bases through organizations. It runs as a Docker Compose stack (Go backend, docreader parser, PostgreSQL, Redis) and works with Ollama or hosted model APIs.

Where it fits in a 10–200 person business

• Company knowledge base over manuals, contracts and scanned documents, answered in chat
• Team workspaces with separate permissions that can still share selected knowledge bases
• Customer-facing Q&A widget or IM bot backed by your own documents

These use cases are our editorial suggestions, not claims made by the project.

Can a business use WeKnora? (license)

This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.

Data & compliance: does WeKnora phone home?

Checked against the project's own docs and repository on Oct 31, 2026. "Not documented" means we could not find the answer in official sources; it does not mean the feature is missing or that no data is sent. Third-party services you connect (model APIs, vector databases, search engines) have their own data policies. Compare all apps.

What hardware does WeKnora need?

Official guidance is to start from 4 CPU cores and 8 GB RAM because docreader bundles LibreOffice and Playwright. Disk depends on knowledge-base size. Optional Milvus, OpenSearch or Langfuse need more memory.

Source: weknora.weixin.qq.com/docs/01-getting-started/02-installation

How much does it cost to host WeKnora per month?

How to deploy WeKnora

Method: Docker Compose

git clone https://github.com/Tencent/WeKnora.git && cd WeKnora
cp .env.example .env
# set DB_USER/DB_PASSWORD/DB_NAME, REDIS_PASSWORD, JWT_SECRET (openssl rand -hex 32) and SYSTEM_AES_KEY
docker compose pull
docker compose up -d
# web UI at http://localhost (FRONTEND_PORT, default 80); backend health at http://localhost:8080/health

From the official instructions: weknora.weixin.qq.com/docs/01-getting-started/02-installation. Always check the source for the current version before you run it.

Known gotchas when self-hosting WeKnora

• Registration defaults to self_serve (anyone who can reach it can sign up). Set DISABLE_REGISTRATION=true or switch to invite registration before exposing it; a registration mode saved in the database settings is also checked on every request, so changing the env alone may not take effect. source
• JWT_SECRET and SYSTEM_AES_KEY are empty in .env.example. Generate them once at first deploy and keep them safe, along with the database and Redis passwords. source
• The backend port 8080 is mapped to the host as well as the frontend port; firewall it if the frontend is your only intended entry point. source
• docker compose up -d alone reuses cached images. Run docker compose pull before upgrading and read the upgrade notes. source

Alternatives in Knowledge base & RAG

• RAGFlow RAG engine with deep document parsing (OCR, layout and tables) and cited answers. Compare RAGFlow vs WeKnora
• AFFiNE Notion- and Miro-style workspace (docs, whiteboards, databases) with built-in AI, self-hostable with Docker. Compare AFFiNE vs WeKnora
• AnythingLLM All-in-one private chat with your documents, agents and an embeddable widget. Compare AnythingLLM vs WeKnora
• PrivateGPT API-first private document Q&A that sits on top of your own LLM server. Compare PrivateGPT vs WeKnora
• Open Notebook Private, self-hosted alternative to Google NotebookLM with your choice of AI models. Compare Open Notebook vs WeKnora
• LightRAG Graph-based RAG server that builds a knowledge graph from your documents, with a web UI and REST API. Compare LightRAG vs WeKnora
• Langchain-Chatchat Chinese-first local knowledge-base Q&A and agent app built on LangChain, wired to local model servers. Compare Langchain-Chatchat vs WeKnora
• Onyx (formerly Danswer) AI chat and enterprise search connected to 50+ workplace apps. Compare Onyx (formerly Danswer) vs WeKnora
• FastGPT Knowledge-base Q&A and visual AI workflow platform. Compare FastGPT vs WeKnora
• kotaemon Open-source RAG web app for chatting with your documents, with citations and GraphRAG. Compare kotaemon vs WeKnora
• MaxKB Enterprise knowledge-base and agent platform with RAG and workflows. Compare MaxKB vs WeKnora
• DocsGPT Open-source platform for AI agents and assistants that answer from your documents with sources. Compare DocsGPT vs WeKnora
• PipesHub Self-hosted workplace search and AI answers across 50+ connected apps, filtered by each user's permissions. Compare PipesHub vs WeKnora

Sources

• GitHub repository: github.com/Tencent/WeKnora
• Official documentation, Hardware requirements, Deploy instructions, Gotcha 2, Gotcha 3, Gotcha 4: weknora.weixin.qq.com/docs/01-getting-started/02-installation
• License text: github.com/Tencent/WeKnora/blob/main/LICENSE
• Gotcha 1: weknora.weixin.qq.com/docs/03-features/01-tenant-auth
• Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
• GitHub stars, commits and releases: GitHub REST API, fetched Oct 31, 2026