An open-source, self-hostable AI chat platform that unifies every major model provider, agents, MCP tools, and code execution in one interface.

LibreChat works by combining Universal Model Switching: Select between Anthropic, OpenAI, Azure OpenAI, Google, Vertex AI, AWS Bedrock, Mistral, DeepSeek, Groq, Cohere, OpenRouter, Perplexity and any OpenAI-compatible custom endpoint from one chat, including local providers like Ollama and Apple MLX, without a proxy., No-Code Agents and Marketplace: Build specialized assistants with file handling, tools, and API actions, share them with specific users or groups, and discover community-built agents in an in-app marketplace., Skills and Subagents: Package reusable SKILL.md instruction bundles for manual, automatic, or always-on workflows, and delegate focused work to isolated child agent runs with their own context windows., Sandboxed Code Interpreter: Execute Python, Node.js, Go, C/C++, Java, PHP, Rust, and Fortran in a fully isolated environment with direct file upload, processing, and download and no data leaving the sandbox., Model Context Protocol Support: Connect agents to any MCP server for external tools and services, with OAuth-backed MCP sessions for controlled access. to help users with Private Team ChatGPT: Self-hosting a shared AI workspace so conversations, files, and API keys stay inside an organization's own infrastructure., Multi-Provider Cost Control: Routing routine prompts to cheaper or local models and heavy reasoning to frontier models from a single interface, without separate subscriptions., Internal Agent Building: Creating no-code agents connected to company tools over MCP and sharing them with specific departments through role-based access., Data Analysis and Scripting: Running analysis, transformations, and one-off scripts through the sandboxed Code Interpreter with uploaded files, then downloading results., Research with Live Sources: Combining web search, reranking, and file search so models answer from current information rather than training data alone..

Key features include Universal Model Switching: Select between Anthropic, OpenAI, Azure OpenAI, Google, Vertex AI, AWS Bedrock, Mistral, DeepSeek, Groq, Cohere, OpenRouter, Perplexity and any OpenAI-compatible custom endpoint from one chat, including local providers like Ollama and Apple MLX, without a proxy., No-Code Agents and Marketplace: Build specialized assistants with file handling, tools, and API actions, share them with specific users or groups, and discover community-built agents in an in-app marketplace., Skills and Subagents: Package reusable SKILL.md instruction bundles for manual, automatic, or always-on workflows, and delegate focused work to isolated child agent runs with their own context windows., Sandboxed Code Interpreter: Execute Python, Node.js, Go, C/C++, Java, PHP, Rust, and Fortran in a fully isolated environment with direct file upload, processing, and download and no data leaving the sandbox., Model Context Protocol Support: Connect agents to any MCP server for external tools and services, with OAuth-backed MCP sessions for controlled access..

LibreChat is useful for anyone interested in Private Team ChatGPT: Self-hosting a shared AI workspace so conversations, files, and API keys stay inside an organization's own infrastructure., Multi-Provider Cost Control: Routing routine prompts to cheaper or local models and heavy reasoning to frontier models from a single interface, without separate subscriptions., Internal Agent Building: Creating no-code agents connected to company tools over MCP and sharing them with specific departments through role-based access., Data Analysis and Scripting: Running analysis, transformations, and one-off scripts through the sandboxed Code Interpreter with uploaded files, then downloading results., Research with Live Sources: Combining web search, reranking, and file search so models answer from current information rather than training data alone..

LibreChat is free to use.

Visit https://www.librechat.ai/ to sign up and explore LibreChat.