mirror of
https://github.com/danny-avila/LibreChat.git
synced 2025-12-24 12:20:14 +01:00
Enhanced ChatGPT Clone: Features Agents, MCP, 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 Auth, Presets, open-source for self-hosting. Active.
https://librechat.ai/
aianthropicartifactsawsazurechatgptchatgpt-cloneclaudeclonedeepseekgeminigooglegpt-5librechatmcpo1openairesponses-apivisionwebui
95011ce349
* refactor: Agent CodeFiles, abortUpload WIP * feat: code environment file upload * refactor: useLazyEffect * refactor: - Add `watch` from `useFormContext` to check if code execution is enabled - Disable file upload button if `agent_id` is not selected or code execution is disabled * WIP: primeCodeFiles; refactor: rename sessionId to session_id for uniformity * Refactor: Rename session_id to sessionId for uniformity in AuthService.js * chore: bump @librechat/agents to version 1.7.1 * WIP: prime code files * refactor: Update code env file upload method to use read stream * feat: reupload code env file if no longer active * refactor: isAssistantTool -> isEntityTool + address type issues * feat: execute code tool hook * refactor: Rename isPluginAuthenticated to checkPluginAuth in PluginController.js * refactor: Update PluginController.js to use AuthType constant for comparison * feat: verify tool authentication (execute_code) * feat: enter librechat_code_api_key * refactor: Remove unused imports in BookmarkForm.tsx * feat: authenticate code tool * refactor: Update Action.tsx to conditionally render the key and revoke key buttons * refactor(Code/Action): prevent uncheck-able 'Run Code' capability when key is revoked * refactor(Code/Action): Update Action.tsx to conditionally render the key and revoke key buttons * fix: agent file upload edge cases * chore: bump @librechat/agents * fix: custom endpoint providerValue icon * feat: ollama meta modal token values + context * feat: ollama agents * refactor: Update token models for Ollama models * chore: Comment out CodeForm * refactor: Update token models for Ollama and Meta models |
||
|---|---|---|
| .devcontainer | ||
| .github | ||
| .husky | ||
| .vscode | ||
| api | ||
| charts/librechat | ||
| client | ||
| config | ||
| e2e | ||
| packages/data-provider | ||
| utils | ||
| .dockerignore | ||
| .env.example | ||
| .eslintrc.js | ||
| .gitignore | ||
| bun.lockb | ||
| deploy-compose.yml | ||
| docker-compose.override.yml.example | ||
| docker-compose.yml | ||
| Dockerfile | ||
| Dockerfile.multi | ||
| index.html | ||
| librechat.example.yaml | ||
| LICENSE | ||
| package-lock.json | ||
| package.json | ||
| prettier.config.js | ||
| rag.yml | ||
| README.md | ||
LibreChat
📃 Features
- 🖥️ UI matching ChatGPT, including Dark mode, Streaming, and latest updates
- 🤖 AI model selection:
- Anthropic (Claude), AWS Bedrock, OpenAI, Azure OpenAI, BingAI, ChatGPT, Google Vertex AI, Plugins, Assistants API (including Azure Assistants)
- ✅ Compatible across both Remote & Local AI services:
- groq, Ollama, Cohere, Mistral AI, Apple MLX, koboldcpp, OpenRouter, together.ai, Perplexity, ShuttleAI, and more
- 🪄 Generative UI with Code Artifacts
- Create React, HTML code, and Mermaid diagrams right in chat
- 💾 Create, Save, & Share Custom Presets
- 🔀 Switch between AI Endpoints and Presets, mid-chat
- 🔄 Edit, Resubmit, and Continue Messages with Conversation branching
- 🌿 Fork Messages & Conversations for Advanced Context control
- 💬 Multimodal Chat:
- Upload and analyze images with Claude 3, GPT-4 (including
gpt-4oandgpt-4o-mini), and Gemini Vision 📸 - Chat with Files using Custom Endpoints, OpenAI, Azure, Anthropic, & Google. 🗃️
- Advanced Agents with Files, Code Interpreter, Tools, and API Actions 🔦
- Available through the OpenAI Assistants API 🌤️
- Non-OpenAI Agents in Active Development 🚧
- Upload and analyze images with Claude 3, GPT-4 (including
- 🌎 Multilingual UI:
- English, 中文, Deutsch, Español, Français, Italiano, Polski, Português Brasileiro,
- Русский, 日本語, Svenska, 한국어, Tiếng Việt, 繁體中文, العربية, Türkçe, Nederlands, עברית
- 🎨 Customizable Dropdown & Interface: Adapts to both power users and newcomers
- 📧 Verify your email to ensure secure access
- 🗣️ Chat hands-free with Speech-to-Text and Text-to-Speech magic
- Automatically send and play Audio
- Supports OpenAI, Azure OpenAI, and Elevenlabs
- 📥 Import Conversations from LibreChat, ChatGPT, Chatbot UI
- 📤 Export conversations as screenshots, markdown, text, json
- 🔍 Search all messages/conversations
- 🔌 Plugins, including web access, image generation with DALL-E-3 and more
- 👥 Multi-User, Secure Authentication with Moderation and Token spend tools
- ⚙️ Configure Proxy, Reverse Proxy, Docker, & many Deployment options:
- Use completely local or deploy on the cloud
- 📖 Completely Open-Source & Built in Public
- 🧑🤝🧑 Community-driven development, support, and feedback
For a thorough review of our features, see our docs here 📚
🪶 All-In-One AI Conversations with LibreChat
LibreChat brings together the future of assistant AIs with the revolutionary technology of OpenAI's ChatGPT. Celebrating the original styling, LibreChat gives you the ability to integrate multiple AI models. It also integrates and enhances original client features such as conversation and message search, prompt templates and plugins.
With LibreChat, you no longer need to opt for ChatGPT Plus and can instead use free or pay-per-call APIs. We welcome contributions, cloning, and forking to enhance the capabilities of this advanced chatbot platform.
Click on the thumbnail to open the video☝️
🌐 Resources
GitHub Repo:
- RAG API: github.com/danny-avila/rag_api
- Website: github.com/LibreChat-AI/librechat.ai
Other:
- Website: librechat.ai
- Documentation: docs.librechat.ai
- Blog: blog.librechat.ai
📝 Changelog
Keep up with the latest updates by visiting the releases page and notes:
⚠️ Please consult the changelog for breaking changes before updating.
⭐ Star History
✨ Contributions
Contributions, suggestions, bug reports and fixes are welcome!
For new features, components, or extensions, please open an issue and discuss before sending a PR.