Verified project record
danny-avila/LibreChat
danny-avila/librechat is a self-hosted, multi-user AI chat platform that consolidates multiple AI providers into a single interface with native agent capabilities. It is intended for enterprise teams, developers, and AI engineers who require centralized configuration, multi-user authentication, and tool integration without vendor lock-in.
Project overview
danny-avila/librechat is a self-hosted, multi-user AI chat platform that consolidates multiple AI providers into a single interface with native agent capabilities. It is intended for enterprise teams, developers, and AI engineers who require centralized configuration, multi-user authentication, and tool integration without vendor lock-in.
- Project type
- MCP · AI Agent · AI Coding
- Use cases
- Chat Assistants · Coding & Development · Automation
- Deployment
- Refer to project documentation
- License
- MIT
Best for
- Enterprise teams requiring a self-hosted chat platform with multi-user authentication, role management, and token spend tracking.
- Developers and AI engineers needing a unified interface to evaluate and switch between various AI providers and OpenAI-compatible APIs.
Key capabilities
- Select and switch between multiple AI providers including Anthropic, OpenAI, Azure, Google, AWS Bedrock, and OpenAI-compatible APIs.
- Build no-code custom assistants with access to MCP servers, tools, file search, code execution, and an agent marketplace.
- Native support for Model Context Protocol to enable external tools and integrations.
- Secure multi-user authentication with OAuth2, LDAP, Email login, built-in moderation, and token spend tools.
- Browser-based UI to manage users, groups, roles, and configuration overrides live without redeploying.
- Secure, sandboxed execution in Python, Node.js, Go, C/C++, Java, PHP, Rust, and Fortran with file handling.
- Search the internet and retrieve relevant information to enhance AI context using search providers, content scrapers, and result rerankers.
- Text-to-image and image-to-image generation using OpenAI, DALL-E, Stable Diffusion, Flux, or MCP servers.
Limitations and risks
- There is a potential for breaking changes during updates, requiring consultation of the changelog before upgrading.
Getting started
- Setup requires configuring environment variables, deployment options, and external or local endpoints. The difficulty is rated medium due to these configuration requirements.
Evidence and sources
- GitHub project description: Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, A…
- README: - 🤖 **AI Model Selection**: - Anthropic (Claude), AWS Bedrock, OpenAI, Azure OpenAI, Google, Vertex AI, OpenAI Responses API (incl. Azure) - [Custom Endpoints](https://www.librech…
- README: LibreChat is a self-hosted AI chat platform that unifies all major AI providers in a single, privacy-focused interface.
- README: - 🔧 Code Interpreter API: - Secure, Sandboxed Execution in Python, Node.js (JS/TS), Go, C/C++, Java, PHP, Rust, and Fortran - Seamless File Handling: Upload, process, and download…
- README: - 🔍 **Web Search**: - Search the internet and retrieve relevant information to enhance your AI context - Combines search providers, content scrapers, and result rerankers for opti…
AI 搜索
把需求说清楚,让项目选择更有依据
告诉我们你要解决什么、运行在哪里、哪些条件不能妥协。雷达会从已核验项目中给出主推荐、备选和采用前检查。