# Tencent/WeKnora

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

Repository: https://github.com/Tencent/WeKnora
Canonical: https://ross.abutalabs.com/products/weknora
Homepage: https://weknora.weixin.qq.com
Language: Go
License: NOASSERTION
License Family: other
Topics: agent, agentic, ai, golang, llm, ollama, rag, chatbot, generative-ai, embeddings, knowledge-base, openai, question-answering, reranking, vector-search, evaluation, multi-tenant, semantic-search, wiki, dsh-plugin
Last push: 2026-08-26T12:16:03+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 96, longevity 29
- inputs: {"age_days": 407, "days_push": 7, "days_rel": 26, "gap_med": 7, "n_releases_24m": 38}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 20700, forks 2968 (observed 2026-08-28T04:11:30.373105+00:00)

## What it is
WeKnora is an open-source, LLM-powered knowledge platform by Tencent that turns raw documents into a queryable RAG system, an autonomous ReAct agent, and a self-maintaining Wiki with knowledge graphs. It supports multi-source document ingestion, semantic retrieval with reranking, chunk editing with revision history, and multi-tenant deployment.

## Use cases
- build a RAG chatbot over company documents
- turn PDFs and wikis into a searchable knowledge base
- self-host a document Q&A assistant with Ollama or OpenAI
- auto-generate an interlinked wiki from raw documents
- answer complex multi-step questions with an agent that searches the web and tools
- manage enterprise knowledge with multi-tenant access and revision history

## When to choose
- you need an enterprise-grade, self-hosted RAG platform with document ingestion pipelines
- you want both quick Q&A and autonomous agent workflows over the same knowledge base
- you need multi-tenancy, chunk editing, and revision history for curated knowledge
- you prefer flexible LLM backends like Ollama or OpenAI-compatible APIs

## When to avoid
- you only need a lightweight embedding library or vector store without a full application
- you require a fully permissive license for commercial redistribution (license is non-standard)
- you need a simple single-user note-taking tool rather than a multi-tenant platform

## Facets
- artifact type: application
- maturity: active
- function: rag, agent-framework, llm-inference, search-engine, vector-database, chatbot, web-framework, documentation, mcp
- domain: large-language-models, self-hosted, developer-tools
- platform: self-hosted, go, browser-extension, cross-platform
- tags: knowledge-management, wiki-generation, semantic-search, question-answering, document-ingestion, multi-tenant, reranking, embeddings, ollama, openai-compatible, knowledge-graph, react-agent, retrieval-augmented-generation, ai-agents, natural-language-processing, search, knowledge-base, docker, web-server

## Member repositories
- Tencent/WeKnora (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:30.373105+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:58:33.898248+00:00, confidence not recorded.
  - readme: https://github.com/Tencent/WeKnora (fetched 2026-08-28T04:11:30.373105+00:00, sha 812046ee8cc2)
- Data as of 2026-08-30T08:39:29.467469+00:00.