← Discover
Discover · GitHub · WeKnora↑ +1,125 today

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

  • September 18, 2026: Stars 26,667 → 26,676, latest release v0.8.0 (September 3, 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

Quick installation with Docker
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 services

If you don't write code

🤖 Paste this into your AI agent (Claude Code · Codex · Antigravity)

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.

Related dictionary terms

Who it is forSuitable for professionals and teams looking to transform their corporate documents, wiki pages, and scattered data into an intelligent knowledge system.

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. This page was machine-translated from the Turkish original · the Turkish version prevails.