Vibe Coding DiscoverWeKnora
View on GitHubOpen-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
WeKnora is a self-hostable, LLM-powered knowledge platform in Go: it ingests 10+ document formats into a RAG pipeline, adds a ReAct agent with MCP tools and sandboxes, and auto-generates a self-maintaining markdown wiki. Supports pluggable vector stores, 20+ LLM providers, multi-tenant RBAC, and IM channel integration.
Use Cases
Enterprise document Q&A over private filesBuild a queryable RAG knowledge base from PDFs/Word/Excel/imagesAutonomous ReAct agent doing multi-step retrieval + tool useAuto-generate a self-maintaining interlinked markdown wiki with knowledge graphServe knowledge Q&A through IM channels (WeCom, Feishu, Slack, Telegram)Sync and search knowledge from Feishu, Notion, Yuque, GitLab, RSSSemantic search with hybrid vector + rerank retrievalRun sandboxed agent skills with per-tenant network policyExpose knowledge base as an MCP server to external agentsCross-session long-term memory for personalized answersMulti-tenant / multi-workspace RBAC knowledge platformEvaluate and observe RAG pipelines via Langfuse tracing
Built With
- Language
- Go
- Frameworks
- Go · Gin · Milvus · Qdrant · pgvector · Elasticsearch · OpenSearch · Neo4j · Ollama · Docker · E2B · Langfuse · mcp-go · DuckDB · Redis · PostgreSQL
Tags
rag · knowledge-base · document-qa · agentic-rag · embeddings · vector-search · semantic-search · reranking · mcp-server · wiki-generation · multi-tenant · multi-agent · long-term-memory · self-hosted · evaluation · chatbot