</>MCP Agents Market
Agent

LibreChat

by danny-avila44.8kTypeScriptUpdated 2026-09-24

Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User A

LibreChat is a self-hosted AI sub-agent platform that consolidates multiple large language model providers—including OpenAI, Anthropic Claude, AWS Bedrock, Google Gemini, Azure, DeepSeek, and Mistral—into a unified chat interface with advanced agent capabilities. It features a no-code Agent Builder for creating custom assistants, Model Context Protocol (MCP) server support for extensible tools, Skills for reusable instruction bundles, and a sandboxed Code Interpreter for executing Python, JavaScript, Go, and other languages. The platform supports human-in-the-loop workflows, artifact generation for React and Mermaid content, image generation with DALL-E and Stable Diffusion, and enterprise-ready multi-user authentication with role-based access control.

Key Features

Unified Agent Builder with MCP server integration, Skills marketplace, Code Interpreter, and per-tool orchestration controls
Human-in-the-loop agents that stream progress, pause for user input or tool approval, and allow mid-run interruption or steering
Multi-provider AI model switching across OpenAI (GPT-5.6, o1), Anthropic (Claude Opus 5, Sonnet 5), Google Gemini, AWS Bedrock, Azure, DeepSeek, Mistral, and OpenRouter
Sandboxed Code Interpreter supporting Python, Node.js, Go, C/C++, Java, PHP, Rust, and Fortran with secure file upload and download
Generative UI with Code Artifacts for creating React components, HTML, and Mermaid diagrams directly in chat with fullscreen preview and SVG/PNG export
Agent Plugins that bundle deployment Skills and MCP servers into startup-loaded packages with optional per-agent memory isolation
Web search with customizable Jina reranking, content scrapers, and result aggregation to enhance AI context
Multi-user authentication via OAuth2, LDAP, and email with admin panel for managing users, groups, roles, and live configuration overrides

Use Cases

  • 01Building custom AI assistants with specialized tools and MCP servers for internal teams without writing code
  • 02Creating workflow automation agents that require human approval for sensitive operations before proceeding
  • 03Running secure code execution environments for data analysis, visualization, and file processing tasks
  • 04Deploying a private, self-hosted ChatGPT alternative with unified access to multiple AI providers for organizations
  • 05Developing agents with subagent delegation to handle complex, multi-step reasoning tasks with isolated context windows
  • 06Sharing reusable agent Skills and configurations across teams via marketplace and collaborative permission controls

Related Agents

View more

LibreChat — FAQ

What is LibreChat and what does it do?+

LibreChat is an open-source, self-hosted AI sub-agent platform that provides a unified interface for interacting with multiple AI providers (OpenAI, Anthropic, Google, AWS Bedrock, Azure) while offering advanced features like a no-code Agent Builder, MCP server integration, sandboxed Code Interpreter, and human-in-the-loop workflows. It functions as both a ChatGPT alternative and a complete agent development environment.

How do I install and deploy LibreChat?+

LibreChat supports multiple deployment methods including Docker Compose (recommended for quick setup), Railway, Zeabur, and Sealos one-click deploys, or manual installation from the GitHub repository. The Docker Compose stack includes the admin panel and all dependencies for a complete setup. Detailed installation instructions are available in the official documentation at librechat.ai/docs.

What AI clients and providers does LibreChat work with?+

LibreChat natively integrates with OpenAI (including GPT-5.6, GPT-4o, o1), Anthropic Claude (Opus 5, Sonnet 5), Google Gemini, AWS Bedrock, Azure OpenAI, DeepSeek, Mistral, Groq, OpenRouter, Vertex AI, and any OpenAI-compatible API endpoint. It also supports local providers like Ollama, together.ai, and koboldcpp.

Do I need API keys to use LibreChat?+

Yes, you need API keys from the AI providers you want to use (OpenAI, Anthropic, Google, etc.). LibreChat allows administrators to configure these keys centrally or let individual users provide their own keys. For local models like Ollama, no commercial API keys are required.

Is LibreChat free to use?+

Yes, LibreChat is completely open-source and free to self-host under its license. However, you will incur costs from the AI provider APIs (OpenAI, Anthropic, etc.) based on your usage. Local model integrations like Ollama have no API costs beyond infrastructure.

How do I add MCP servers and Skills to LibreChat agents?+

Use the unified Agent Builder interface to add MCP servers by configuring their connection details and selecting which tools to enable. Skills are created as reusable SKILL.md instruction bundles that can be set to manual invocation, automatic triggering, or always-on mode, and shared via the Skills marketplace with specific users and groups.

How do I install LibreChat?+

Open the source repository on GitHub and follow its README. LibreChat is a agent — MCP Agents Market links you directly to the official repo.

Is LibreChat free?+

LibreChat is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches