ChinaTencent/WeKnora
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
Thành tựu nổi bật
Những danh hiệu mới nhất của dự án
#1 Repository Của Tuần
#1 Repository Của Tháng
#1 Repository Của Tháng
💡 WeKnora — Documents to Living Knowledge
Raw docs → RAG Q&A + autonomous agent + self-maintaining Wiki.
WeKnora — open-source LLM knowledge framework, Tencent. Converts scattered documents into queryable, reasoning-capable knowledge asset. Three modes: quick RAG Q&A, ReAct agent for complex tasks, Wiki mode for structured interlinked knowledge base. Ingests 10+ formats: PDF, Word, Excel, images. Connects Feishu, Notion, Yuque. 20+ LLM providers: OpenAI, DeepSeek, Qwen, Zhipu, Hunyuan, Gemini, MiniMax, NVIDIA, Ollama. Enterprise RBAC with 4-tier roles. Self-hostable modular Go architecture.
✨ Highlights
- RAG Quick Q&A: semantic retrieval for everyday lookups across ingested documents
- ReAct Agent: autonomously orchestrates retrieval, MCP tools, web search for multi-step tasks
- Wiki Mode: agents generate structured, interlinked Markdown pages with interactive knowledge graph
- Multi-Source Ingestion: Feishu, Notion, Yuque connectors, more sources planned
- 20+ LLM Providers: OpenAI, DeepSeek, Qwen, Zhipu, Hunyuan, Gemini, MiniMax, NVIDIA, Ollama
- Enterprise RBAC: 4-tier role matrix (Owner, Admin, Contributor, Viewer) plus per-resource ownership, audit logs
- Modular Architecture: swappable LLMs, vector databases, storage backends; self-hostable with full data sovereignty
- Langfuse Observability: comprehensive tracing of agent reasoning, token usage, pipeline spans
💡 Why it matters
Usual RAG tools stop at keyword search. WeKnora adds autonomous reasoning via ReAct agent and self-evolving Wiki mode — knowledge base maintains itself. Enterprise RBAC, multi-tenant support, audit logs make it production-ready. Modular design means swap components without vendor lock-in. Go implementation ensures lightweight self-hosting. Fits enterprises needing searchable, reasoning-capable knowledge from scattered document sources.
#RAG #LLM #Agent #Go #OpenSource #TiniX
Similar Projects
Discover other similar projects and AI models.
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Knowledge infrastructure to make your agents smarter. Search, scrape and access 550+ data providers through one API.