WeKnora

What is WeKnora?

WeKnora is an open-source, LLM-powered knowledge framework developed by Tencent, designed for enterprise-grade document understanding, semantic retrieval, and autonomous reasoning. It transforms scattered raw documents into a queryable RAG system, an autonomous reasoning agent, and a self-maintaining Wiki. The platform is organized around three core capabilities: RAG-based Quick Q&A for everyday lookups, a ReAct Agent that autonomously orchestrates retrieval, MCP tools, and web search to handle complex multi-step tasks, and a new Wiki Mode where agents distill raw documents into a self-maintaining, interlinked markdown knowledge base with an interactive knowledge graph.

Key features include multi-source ingestion from Feishu, Notion, Yuque, and RSS, with more data sources coming soon. It supports over 10 document formats such as PDF, Word, images, and Excel. WeKnora offers website embed widgets for publishing agents to external sites, scoped API keys with a principal model for programmatic integrations, and multi-instance storage backends per workspace for flexible data placement. It integrates with 20+ LLM providers including OpenAI, DeepSeek, Qwen, Zhipu, Hunyuan, Gemini, MiniMax, NVIDIA, and Ollama. For observability, it provides full Langfuse integration and a runtime task-queue dashboard with worker-pool governance. Enterprise features include multi-workspace RBAC with a 4-tier role matrix, per-resource ownership, and per-workspace audit log. The framework is fully self-hostable with a modular architecture, allowing easy swapping of LLMs and components.

Use cases include enterprise knowledge management, customer support automation, research assistance, and internal documentation. Technical details: WeKnora supports auto-syncing knowledge from popular platforms, handles diverse document formats, and can serve Q&A directly through IM channels like WeCom, Feishu, Slack, and Telegram. Its modular design ensures scalability and customization for various enterprise needs.

Use Cases

Key Features

LLM powered knowledge framework multi source document ingestion RAG based Q&A ReAct autonomous agent self maintaining Wiki mode interactive knowledge graph 20+ LLM provider support website embed widgets scoped API keys multi instance storage backends

Who is it for?

enterprise knowledge teams, RAG developers, AI engineers, document management teams, knowledge base administrators, platform engineers

Similar Tools