WeKnora

WeKnora is an open-source, LLM-powered knowledge framework for enterprise document understanding, semantic retrieval, and reasoning.

  • AI
  • Productivity
WeKnora is an open-source, LLM-powered knowledge framework for enterprise document understanding, semantic retrieval, and reasoning. It combines Retrieval-Augmented Generation (RAG) lookups, multi-step agent tasks, and a structured knowledge wiki into one self-hosted system so teams can search, reason over, and keep their documents up to date. Built for organisations with complex, heterogeneous document sets, it handles multimodal deep parsing of PDFs, Word files, plain text, and other formats, indexes them with semantic vector search, and returns context-aware, coherent answers.

Platform availability

Available on 1 of 10 platforms

  • Unraid (not listed)
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

73/100 Good

Maintained
100last commit 18 days ago
Popular
9136,824 GitHub stars
Easy to install
351 install platform, install notes, Docker image
Light to run
208 GB minimum RAM, runs on ARM

Availability: platform listings confirmed today

GitHub stars
36,824
Open issues
947
Last commit
2026-11-03
Latest release
v0.9.0
Activity
steady

Checked 13 days ago - source: GitHub (Tencent/WeKnora)

Resources & Compatibility

Minimum requirements: 8 GB RAM, 4 CPU core(s), 20 GB disk. ARM (e.g. Raspberry Pi) is supported.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Start WeKnora with Docker Compose Clone the WeKnora repo, copy .env.example to .env, edit it, then run docker compose pull and docker compose up -d. Docker Compose (a tool that starts many containers from one file) uses your .env settings, so leaving required values blank can make the app fail to start or connect. source
  • Set MCP server variables first If you are also installing the MCP server, run pip install -r requirements.txt and set WEKNORA_BASE_URL and WEKNORA_API_KEY before running python main.py. These tell the MCP server where WeKnora is and how to sign in, so without them it will not be able to talk to the app. source
  • Check the MCP server setup Use python main.py --check-only to verify the environment, and add --verbose if you need more detailed logs. This helps you spot missing settings or connection problems before the server is expected to work. source

Fetched 53 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

Why might WeKnora not start after running docker compose up?

Copy .env.example to .env and edit the required values first. Docker Compose uses those .env settings, and leaving required values blank can make the app fail to start or connect.

What environment variables are required for the WeKnora MCP server?

Set WEKNORA_BASE_URL and WEKNORA_API_KEY before running python main.py. These tell the MCP server where WeKnora is and how to sign in, and without them it cannot talk to the app.

Does WeKnora document support for local Ollama models?

Yes, its system initialization documentation covers Ollama local model management and AI model registration.

Which source documents can WeKnora use for RAG?

It turns uploaded PDFs, Word files, and web pages into a RAG chat with citations.

Answers sourced from deepwiki.com, genztech.blog, github.com, github.com

Community

Collected 48 days ago - public community threads