Vibe Coding Discover

RAG

anything-llm

View on GitHub

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

★ 66K7,404 forksJavaScriptMITMintplex-Labs

Self-hosted, local-first AI app: ingest documents into a vector DB and chat with them privately, with built-in agents, no-code agent flows, MCP support, multi-user permissions and a wide range of local or cloud LLMs and embedders.

Use Cases

Chat privately with your own documents (PDF, DOCX, TXT)Fully local offline LLM chat with no data leaving the machineMulti-user AI workspace with per-user permissionsRAG pipeline with swappable vector DBs (LanceDB, Chroma, Qdrant, PGVector, Pinecone, Weaviate, Milvus)No-code AI agent builder and agent flowsMCP-compatible tool calling in chatScheduled cron tasks run with agent capabilitiesEmbeddable website chat widgetDeveloper API for custom integrationsMultimodal document Q&AAudio transcription and text-to-speech in chatCustom agents that browse the web

Built With

Language
JavaScript
Frameworks
Node.js · Express · React · Vite · Tailwind CSS · Prisma · LangChain · Docker

Tags

rag · local-first · self-hosted · ai-agents · vector-database · document-chat · multi-user · mcp · llm-providers · multimodal · no-code-agent-builder · desktop-app · docker-deployment · openai-compatible · citations · privacy

anything-llm — Vibe Coding Discover