Tencent/WeKnora

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

What it solves

WeKnora is an enterprise-grade knowledge framework designed to transform scattered, raw documents into a queryable, reasoning-capable, and evolving knowledge asset. It solves the problem of fragmented information by combining semantic retrieval (RAG), autonomous agent reasoning, and a self-maintaining wiki system to ensure knowledge is not just stored but actively organized and accessible.

How it works

The system operates through three primary modes:

  1. RAG-based Quick Q&A: Uses semantic retrieval to provide fast answers from uploaded knowledge bases.
  2. ReAct Agent: An autonomous agent that orchestrates retrieval, web search, and external tools (via MCP) to handle complex, multi-step tasks.
  3. Wiki Mode: Agents distill raw documents into a structured, interlinked Markdown knowledge base featuring an interactive knowledge graph.

It supports multi-source ingestion (e.g., Notion, GitLab, Feishu), processes various document formats (PDF, Word, XMind, etc.), and utilizes a modular architecture where LLMs, vector databases, and storage backends can be swapped based on needs.

Who it’s for

It is built for enterprises and organizations that need to manage large volumes of internal documentation and want to deploy a self-hostable, secure knowledge system with robust access control (RBAC) and observability.

Highlights

  • Autonomous Wiki Generation: Automatically converts raw documents into a structured, interlinked wiki with version history and rollback capabilities.
  • Skill Sandboxing: Executes tools in session-persistent Docker, E2B, or Cube sandboxes for secure, isolated computation.
  • Advanced Knowledge Curation: Features a tree-structured folder view for uploads and direct editing of retrieval chunks with revision history.
  • Long-term Memory: Maintains cross-session memory of user profiles, preferences, and facts.
  • Broad Integration: Supports 20+ LLM providers, multiple vector databases, and various IM channels like Slack, Telegram, and WeCom.

Related

  • Project
    nashsu/llm_wiki

    A desktop application that automatically transforms documents into a structured, interlinked personal wiki using LLMs, featuring a knowledge graph and automated deep research.

  • Project
    VectifyAI/OpenKB

    An open-source system that compiles raw documents into a structured, interlinked wiki-style knowledge base using LLMs and vectorless, reasoning-based retrieval.

  • Project
    nvk/llm-wiki

    llm‑wiki is a cross‑runtime tool that lets Claude, Codex, OpenCode, Pi and other LLM agents build and query a structured, Obsidian‑compatible wiki. It provides ingestion, parallel research, session memory, private adapters, and exportable knowledge checkpoints, with install scripts for each supported agent.

  • Project
    atomicstrata/llm-wiki-compiler

    A compiler that turns raw sources into a structured, citation-traceable Markdown wiki, moving knowledge extraction from query-time to compile-time for better agent and human retrieval.

  • Project
    clusterzx/paperless-ai

    Paperless‑AI is an open‑source extension for the self‑hosted document manager Paperless‑ngx. It automatically classifies new documents, adds AI‑generated titles/tags, and builds a vector index so you can ask natural‑language questions across your whole archive (RAG chat). It works with any OpenAI‑compatible model—including local Ollama servers—and ships as a Docker image with a simple web UI for configuration and manual processing.