[opensourcedex]

LibreChat is a free, open source ai interaction & interfaces project written in TypeScript and released under MIT. It has 44,217 GitHub stars, 9,087 forks and 732 open issues, and was last pushed 5 hours ago. On this registry it ranks #9 of 76 tracked projects in AI Interaction & Interfaces, and is listed as an open source replacement for 1 paid product, with 5 head-to-head comparisons available. It gained 1,146 stars over the last 6 tracked days.

LibreChat — One interface for all your AI models and conversations

What is LibreChat?

What it is

LibreChat is an open-source, self-hostable chat interface designed as an enhanced ChatGPT clone. It unifies access to multiple AI models—including OpenAI, Anthropic, Google Gemini, DeepSeek, Mistral, AWS Bedrock, Azure OpenAI, and others—within a single web application. Built in TypeScript, it supports real-time streaming, multi-model switching, and advanced agent workflows while providing features like message search, artifacts, code interpreter, and secure multi-user authentication.

It solves the fragmentation problem of AI model access by eliminating the need to switch between separate dashboards or APIs for each provider. Users can manage prompts, presets, tools, and agents centrally, while administrators gain control over security, tenant isolation, and observability without relying on proprietary interfaces.

Key capabilities

  • Unified interface supporting OpenAI (including GPT-5, o1, Responses API), Anthropic (Claude Fable, Opus, Sonnet), Google (Gemini 3.8/3.7/3.6 Flash), DeepSeek, Mistral, AWS Bedrock, Azure OpenAI, Groq, and OpenRouter
  • Agent framework with human-in-the-loop control, subagent graphs, tool orchestration, and durable queuing for long-running workflows
  • Code Interpreter sandbox with scoped environments, file downloads, and guarded permissions
  • Skills, MCP, and OpenAPI Actions configurable in a single Tools marketplace for tool calling, background execution, and runtime authoring
  • Secure multi-user authentication with SAML, JWT refresh, per-user Code Interpreter tokens, and tenant-aware content filtering
  • Message and conversation search, project-based chat organization, and stable shared links with personal copies
  • Langfuse integration for encrypted observability, telemetry export control, and session-linked analytics

Who uses it and how

Enterprises deploy it as an internal AI gateway to standardize model access, enforce security policies, and audit model-bound data via source-aware filters. Developers use it to prototype and debug agent workflows with built-in event tracing, circuit breakers, and durable state management. Researchers and educators run self-hosted instances to experiment with multiple models, manage student work via projects, and control costs through presets and token tracking.

Getting started

Deploy via Docker (docker run -p 3080:3080 librechat.ai/librechat) or use the official hosted option at librechat.ai. Install dependencies with npm install, then run npm run start for local development. Configuration uses environment variables for model keys, database (MongoDB), and optional SMTP or storage backends.

When to use it — and when not to

Use LibreChat when you need a self-hosted, multi-model interface with agent orchestration, observability, and secure multi-tenancy—especially where vendor lock-in or API cost control matters. Avoid it if you require zero-configuration hosted support, minimal resource usage (it requires MongoDB, Redis for scaling, and SMTP for email), or strict compliance with non-MIT licenses. It trades simplicity for flexibility: more operational overhead than proprietary tools, but full control over data, models, and extensibility.

project readme (upstream, from github) — read inline

LibreChat

English · 中文

Deploy on Railway Deploy on Zeabur Deploy on Sealos

Translation Progress

🚀 What's New in v0.8.8-rc2

  • Agent run control: Interrupt an Agent before visible answer text, steer runs with files and quoted excerpts, durably queue follow-ups, and recover saved partial work with Keep going or Answer now.
  • Agent activity: Optional generated labels group reasoning and tool work, fold completed groups into live phase cards, keep generated files visible, summarize multi-step phases, and show the current reasoning direction.
  • Human-in-the-loop Agents: Stream up to four related questions, pause for input or tool approval, and resume durably.
  • Unified Agent Builder: Configure Skills, MCP, Code Interpreter, orchestration, Programmatic Tool Calling, model-spec controls, and per-tool background and intent settings in one Tools marketplace; Skills can be enabled for standalone runtime authoring without exposing the existing catalog.
  • Durable Agent automation: Authenticated Agent Events support bound child actors, expected-action receipts, per-actor mailboxes, event batching, durable human pauses, and automatic detached Actions across built-in stream stores.
  • Deeper Subagent history: Browse branch-aware child turns with bounded reasoning and stable live event views, load earlier activity, inspect event details, continue completed child chats, and automatically wake saved parent Agents when detached work settles.
  • Background tools: Eligible Code Interpreter, MCP, Plugin, and Action tools can run while an Agent keeps working, with automatic delivery for supported completions and polling controls when needed.
  • Code Interpreter workflows: Sandbox images return as viewable artifacts; highly experimental stateful sessions add scoped managed, attached, or personal environments, per-message file downloads, and guarded file-write and command permissions.
  • Agent extensibility: Experimental Agent Plugins bundle deployment Skills, MCP servers, and opt-in command hooks; saved Agent teams run as isolated Subagent graphs.
  • Scheduled Chats (experimental): Run saved Agents with presets or custom cron, selectable time zones, multi-day weekly cadence, and optional Chat Project destinations.
  • Memory and context: Agents can use optionally isolated memory, preserve adaptive context fading across turns, and show categorized current-window usage, tokens, and optional cost.
  • Editable long pastes: Long pasted text becomes an editable attachment that can be moved back into the composer; attachment-only turns and reliable Upload as Text downloads are also supported.
  • Projects, settings, and navigation: Search conversation titles and message contents, manage project chats, use searchable settings and shortcuts, pin chats, choose clock/week conventions, and navigate faster on mobile.
  • Sharing and artifacts: Stable shared links support personal copies; fullscreen previews, Mermaid export, PowerPoint templates, shell scripts, and original Office downloads expand file workflows.
  • Web search: Keenable adds keyless search and page fetch, while SearXNG and Tavily gain richer controls and all web-tool egress uses stronger SSRF protection.
  • Security and authentication: Default HTTP security headers, opt-in nonce CSP, authenticated local images, per-user Code Interpreter JWTs, stable SAML identity binding, live-session OpenID token refresh, and retired JWT-secret rejection harden deployments.
  • Models and reasoning: Added GPT-5.6 with Responses reasoning controls, Claude Fable 5.1, Opus 5, and Sonnet 5, plus Gemini 3.8/3.7/3.6 Flash and Gemini 3.5 Flash-Lite.
  • Langfuse observability: Configure encrypted in-app connections, tenant fanout, authenticated gateways, export-decision telemetry, and authorized session links in chats and shared views.
  • Administration: Source-aware content filters can audit or block model-bound data, while tenant Insights, delegated configuration, encrypted secrets, and expiring violation scores improve operations.
  • Streaming and reliability: Adaptive smoothing, Redis delta batching and failover recovery, automatic generation protocol v2, live MCP catalog refresh, Agent circuit breakers, and DocumentDB support improve long runs and scaled deployments.

Read the full v0.8.8-rc2 changelog.

✨ Features

  • 🖥️ UI & Experience inspired by ChatGPT with enhanced design and features

  • 🤖 AI Model Selection:

    • Anthropic (Claude), AWS Bedrock, OpenAI, Azure OpenAI, Google, Vertex AI, OpenAI Responses API (incl. Azure)
    • Custom Endpoints: Use any OpenAI-compatible API with LibreChat, no proxy required
    • Compatible with Local & Remote AI Providers:
      • Ollama, AMD Lemonade, groq, Cohere, Mistral AI, Apple MLX, koboldcpp, together.ai,
      • OpenRouter, Helicone, Perplexity, ShuttleAI, Deepseek, Qwen, and more

  • 🔧 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 files directly
    • No Privacy Concerns: Fully isolated and secure execution
    • Open-Source & Self-Hostable: powered by ClickHouse/code-interpreter

  • 🔦 Agents & Tools Integration:

    • LibreChat Agents:
      • No-Code Custom Assistants: Build specialized, AI-driven helpers
      • Agent Marketplace: Discover and deploy community-built agents
      • Collaborative Sharing: Share agents with specific users and groups
      • Flexible & Extensible: Use MCP Servers, tools, file search, code execution, and more
      • Skills: Create reusable SKILL.md instruction bundles for manual, automatic, or always-on agent workflows
      • Agent Plugins: Experimentally bundle deployment Skills and MCP servers into startup-loaded packages
      • Subagents: Delegate focused work to isolated child agent runs with their own context windows
      • Compatible with Custom Endpoints, OpenAI, Azure, Anthropic, AWS Bedrock, Google, Vertex AI, Responses API, and more
      • Model Context Protocol (MCP) Support for Tools

  • 🔍 Web Search:

    • Search the internet and retrieve relevant information to enhance your AI context
    • Combines search providers, content scrapers, and result rerankers for optimal results
    • Customizable Jina Reranking: Configure custom Jin

readme truncated — read the full docs on github

Frequently asked questions

Is LibreChat free to use?

LibreChat is open source under the MIT licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does LibreChat do?

One interface for all your AI models and conversations

What is LibreChat written in?

LibreChat is primarily written in TypeScript. Its source is publicly available at https://github.com/danny-avila/librechat, and it has 44,217 GitHub stars.

What is a good open source alternative to OpenAI API?

LibreChat is one of the open source options listed as an alternative to OpenAI API. Compare licences, stars and activity side by side on the LibreChat profile.