WeKnora is an open-source LLM-powered knowledge platform that transforms scattered raw documents into a queryable retrieval-augmented generation pipeline, an autonomous reasoning agent, and a self-maintaining Wiki. It requires an external or local LLM provider to function and supports a modular pipeline for swapping language models, vector databases, and storage backends.
Project overview
The platform provides agents that distill raw documents into a self-maintaining, interlinked markdown knowledge base alongside a fully modular design for swapping language models, vector databases, and storage backends.
Project type
AI Agent · RAG · Infrastructure
Use cases
Knowledge Q&A · Search & Research · Automation
Deployment
Refer to project documentation
License
License pending
Best for
Enterprise teams and developers needing a modular pipeline to transform raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
Key capabilities
Auto-generation of structured, interlinked markdown Wiki pages from raw documents with a visual knowledge graph.
Limitations and risks
Requires an external or local LLM provider (e.g., OpenAI, DeepSeek, Ollama) to function.
Deploying services directly to public networks may cause information leakage.
Getting started
Clone the repository, configure the environment file, run the Docker Compose command, and access the Web UI. No coding is required.
Evidence and sources
GitHub project description: Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
README: It 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…
README: - **v0.7.0** — Fine-grained **scoped API keys & principal model** (capability-level grants + per-KB restriction + API integration playground); **runtime task-queue observability d…