Stars
Forks
Watchers
Developer links
LibreChat
Every major model provider behind one ChatGPT-style interface: LibreChat spans OpenAI, Anthropic, Google, Azure, AWS Bedrock, Vertex AI, Groq, Mistral, OpenRouter, DeepSeek, and any OpenAI-compatible endpoint including local Ollama. You can switch models mid-conversation and compare providers without changing tools. Its Agents framework builds no-code custom assistants with tool access via Model Context Protocol servers, file search over uploaded documents through an optional pgvector-backed RAG service, and a sandboxed Code Interpreter that executes Python, JavaScript, Go, C++, Java, PHP, and Rust. Artifacts render React components, HTML, and Mermaid diagrams directly in chat, and image generation works through DALL-E and other configured providers. Multi-user support is enterprise-grade, with OAuth, SAML, LDAP, and two-factor authentication, per-user conversation history in MongoDB, and Meilisearch-powered search across all messages and files, plus reusable presets, forkable threads, and persistent memory across conversations. The economics favor teams: instead of a ChatGPT Plus seat per person, everyone shares one instance billed per API token, with access to every provider rather than one - and providers see individual API calls, not your accumulated organizational knowledge. Deployment is Docker Compose; API keys and endpoints are configured through .env and librechat.yaml.
Benefits
- Pay Per Token, Not Per Seat
- Instead of buying a ChatGPT Plus seat for every team member, the whole team shares one instance using API keys, which is usually far cheaper and gives access to every provider rather than one.
- One Interface for Every Model
- Compare Claude, GPT, Gemini, and a local Llama on the same prompt without switching apps, and swap models mid-conversation when one is better suited to the task.
- Conversations Stay on Your Server
- Chat history, uploaded files, and agent configurations live in your MongoDB instance. Providers see individual API calls, not your accumulated organizational knowledge.
- Ready for Team Deployment
- OAuth, SAML, LDAP, two-factor auth, and per-user isolation are built in, so rolling LibreChat out across a company does not require bolting on an auth layer.
Features
- Every Major Provider Plus Local Models
- OpenAI, Anthropic, Google, Azure, AWS Bedrock, Vertex AI, Groq, Mistral, OpenRouter, and DeepSeek, plus any OpenAI-compatible endpoint such as Ollama or LocalAI.
- No-Code Agents with MCP Tools
- Build custom assistants with instructions, files, and tool access through Model Context Protocol servers; share them with users and groups or publish to the agent marketplace.
- Sandboxed Code Interpreter
- Agents execute Python, Node.js, Go, C/C++, Java, PHP, and Rust in an isolated sandbox with file upload, processing, and download.
- RAG File Search
- An optional RAG API service indexes uploaded documents into pgvector for semantic search, grounding responses in your files at agent or conversation level.
- Artifacts and Image Generation
- Render React components, HTML, and Mermaid diagrams beside the conversation, and generate images through DALL-E and other configured providers.
- Search, Presets, and Memory
- Meilisearch-backed search across all messages and files, reusable conversation presets, forkable threads, and persistent memory across conversations.