WeKnora

Active
GitHub Go NOASSERTION

Description

Tencent's open-source LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG.

Key Features

  • RAG-based Quick Q&A for everyday document lookups with semantic retrieval
  • ReAct Agent autonomously orchestrating retrieval, MCP tools, and web search for complex multi-step tasks
  • Wiki Mode where agents distill raw documents into self-maintaining, interlinked markdown knowledge bases with interactive knowledge graphs
  • Multi-source ingestion from Feishu, Notion, and Yuque with 20+ LLM provider integrations
  • Enterprise-ready multi-tenant RBAC with 4-tier role matrix, per-resource ownership, and per-tenant audit logs
  • Full Langfuse observability integration for agent reasoning, token usage, and pipeline tracing

Use Cases

πŸ’‘ Enterprise knowledge base construction from scattered documents with auto-syncing from team tools
πŸ’‘ Building intelligent Q&A chatbots for internal teams via WeCom, Feishu, Slack, or Telegram
πŸ’‘ Automated wiki generation and maintenance from raw documentation sources
πŸ’‘ Multi-step research tasks requiring tool orchestration and web search capabilities
πŸ’‘ Compliance-sensitive deployments requiring full data sovereignty and audit trails

Tags

go rag llm framework agent database

Categories

πŸ€– Agent Framework πŸ“š RAG Tools

Quick Start

Clone the repo, configure your environment variables with LLM API keys and database settings, run `docker compose up` to start the full stack (Go backend + React frontend + vector DB), then open the Web UI to create your first knowledge base and start querying.
Visit GitHub

Related Projects