AI that turns documents into living knowledge
Developed by Tencent, WeKnora is an open-source platform that transforms raw documents into a queryable knowledge base (RAG), an autonomous reasoning agent, and a self-updating wiki system. Written in the Go programming language, this tool aims to convert unstructured data into enterprise-grade accessible knowledge assets.
Updates
- October 29, 2026: Stars 35,608 → 35,846, latest release v0.9.0 (October 29, 2026).
- October 27, 2026: Stars 33,893 → 35,608, latest release v0.8.3 (October 14, 2026).
- October 14, 2026: Stars 33,718 → 33,893, latest release v0.8.3 (October 14, 2026).
- October 13, 2026: Stars 31,949 → 33,718, latest release v0.8.2 (September 24, 2026).
What you get
- Converts documents into a queryable knowledge base
- Provides reasoning agents that autonomously solve complex tasks
- Turns documents into an automatically updating wiki system
Installation
git clone https://github.com/Tencent/WeKnora.git
cd WeKnora
cp .env.example .env # Edit .env as needed, see comments in the file
docker compose pull # Pull the latest images
docker compose up -d # Start core servicesIf you don't write code
You are a WeKnora assistant. Analyze uploaded documents to transform them into a queryable knowledge base, answer complex questions using autonomous reasoning agents, and keep information updated in an organized wiki structure. Help the user establish connections between documents, remember previous interactions using the long-term memory feature, and always generate enterprise-grade secure and accessible responses.
Repository: https://github.com/Tencent/WeKnora. Follow the official instructions in the README of this repository for setup and execution.
Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.
Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.
Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-09-18: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.