BigHugger
GH Repository · Tencent

WeKnora

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

stars
25,878
30-day movement
+917306/day
Related entries
60
Connections
1
nodeagent-appdsh-pluginsemantic-searchvector-searchrerankingagentagenticaiwikillmevaluationchatbotgolangollamaGoembeddingsgoraggenerative-aimakedockerknowledge-basemulti-tenant

WeKnora is Tencent's open-source LLM knowledge platform that ingests raw documents and turns them into three outputs: a queryable RAG system, an autonomous reasoning agent, and a self-maintaining Wiki. It is written in Go, ships with a Docker/Make/Node toolchain, and covers embeddings, vector search, reranking, and multi-tenant knowledge bases.

You want one open-source platform that combines document-backed RAG, an agentic layer, and a wiki generator instead of wiring separate tools together.

Use it to

  • Build a RAG pipeline over your own documents
  • Run an autonomous reasoning agent on a knowledge base
  • Generate a self-maintaining wiki from raw documents
  • Set up multi-tenant semantic search
  • Use local models via Ollama or OpenAI-compatible endpoints

For Developers building document-powered LLM applications and knowledge bases

Role
agent-app
Language
Go
Licence
custom (licence file present)
Forks
3,528
Open issues
374
Last push
2026-09-17
Latest release
v0.1.2 · 2025-09-10
topicsragknowledge-basellmagenticsemantic-searchgolang