Stars
Forks
Watchers
Developer links
WeKnora
WeKnora turns scattered corporate documents into a searchable, reasoning-capable knowledge asset that your team can query in plain language and receive cited, sourced answers. Upload PDFs, Word files, web pages, Feishu wikis, Notion databases, Yuque docs, GitLab repositories, or RSS feeds into structured knowledge bases, and three distinct modes make the content actionable: RAG Quick Q&A retrieves relevant chunks and generates answers with source citations; the ReAct Agent autonomously orchestrates multi-step reasoning across knowledge retrieval, MCP tool calls, web search, and sandboxed code execution to produce comprehensive research reports; and Wiki Mode deploys LLM agents to distill raw documents into an interlinked markdown knowledge base with an interactive knowledge graph, revision history, and one-click rollback. Connect 20+ LLM providers including OpenAI, DeepSeek, Qwen, Claude, and local Ollama models without vendor lock-in, and choose from seven vector database backends (Qdrant, Milvus, Weaviate, and more) for embedding storage. Enterprise features include four-tier RBAC with per-resource ownership and per-workspace audit logs, AES-256-GCM credential encryption, scoped API keys, Langfuse observability tracing for every agent loop and tool call, and a runtime task-queue dashboard for worker-pool governance. Cross-session long-term memory preserves conversational context across interactions. The Agent Skills catalog lets teams install and share sandboxed scripts executed in Docker or E2B containers. A Chrome Extension captures web content directly into knowledge bases. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Benefits
- Three Knowledge Modes in One Platform
- RAG retrieval for instant cited answers, a ReAct Agent for multi-step autonomous reasoning with tool orchestration, and Wiki Mode for LLM-generated interlinked knowledge bases, all sharing the same infrastructure.
- Connect 20+ LLM Providers Freely
- Swap between OpenAI, DeepSeek, Qwen, Claude, Ollama, and LiteLLM without reindexing or vendor lock-in. Per-knowledge-base model selection lets teams optimize cost and quality independently.
- Enterprise-Grade Access Control
- Four-tier RBAC with per-resource ownership, per-workspace audit logging, AES-256-GCM credential encryption, and scoped API keys provide the governance controls required for production enterprise deployments.
- Full Agent Observability with Langfuse
- Trace every ReAct loop iteration, tool call, token consumption, and retrieval step through integrated Langfuse observability. The runtime task-queue dashboard monitors worker pools and job throughput in real time.
Features
- Multi-Source Document Ingestion
- Import from Feishu wiki, Feishu Drive, GitLab, Notion, Yuque, RSS feeds, URLs, and local files with automatic document parsing and chunk indexing.
- Interactive Wiki Mode
- LLM agents distill raw documents into interlinked markdown pages with an interactive knowledge graph, revision history, and one-click rollback.
- Agent Skills Sandbox
- Install and execute sandboxed scripts in Docker or E2B containers. The skill catalog lets teams share reusable automation for data analysis and document generation.
- Seven Vector DB Backends
- Choose Qdrant, Milvus, Weaviate, Doris, or other vector stores for embedding storage, swappable without re-ingestion via the modular retriever architecture.
- Cross-Session Long-Term Memory
- The platform remembers user context and query patterns across sessions, enabling personalized retrieval and increasingly relevant agent responses over time.