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/
Find a file
2023-11-25 09:19:13 -05:00
.devcontainer fix: devcontainer image and networking (#891) 2023-09-07 07:19:03 -04:00
.github feat: Vision Support + New UI (#1203) 2023-11-21 20:12:48 -05:00
.husky
api 🛠️ refactor: Handle .webp, Improve File Life Cycle 📁 (#1213) 2023-11-24 16:45:06 -05:00
client fix: prevent convo overwrite on convo refresh and combine with remote models handling (#1217) 2023-11-25 09:19:13 -05:00
config feat: deploy-compose NGINX volume mapping, add image removal to update script (#1211) 2023-11-22 23:35:08 -05:00
docs feat(OpenAIClient): AZURE_USE_MODEL_AS_DEPLOYMENT_NAME, AZURE_OPENAI_DEFAULT_MODEL (#1165) 2023-11-10 09:58:17 -05:00
e2e style: update graphics (#1138) 2023-11-16 08:42:03 -05:00
packages/data-provider fix: Correct Default Model Name in Response Sender and Update Anthropics 🤖 (#1208) 2023-11-22 18:29:09 -05:00
pyserver
.dockerignore
.env.example feat: Order/disable endpoints with ENDPOINTS env var (#1206) 2023-11-22 13:56:38 -05:00
.eslintrc.js fix(OpenAIClient): use official SDK to identify client and avoid false Rate Limit Error (#1161) 2023-11-09 14:04:36 -05:00
.gitignore WIP: Update UI to match Official Style; Vision and Assistants 👷🏽 (#1190) 2023-11-16 10:42:24 -05:00
bun.lockb chore: remove jose as Bun now supports JWT 🍞 (#1167) 2023-11-12 00:44:46 -05:00
deploy-compose.yml feat: deploy-compose NGINX volume mapping, add image removal to update script (#1211) 2023-11-22 23:35:08 -05:00
docker-compose.yml refactor(docker-compose): Set UID/GID (#1044) 2023-10-13 17:24:27 -04:00
Dockerfile
Dockerfile.multi
index.html
LICENSE doc fix: license ⚖️ (#1171) 2023-11-12 20:49:41 -05:00
mkdocs.yml docs: Add LibreChat reverse proxy setup with Basic Auth & Misc section (#1118) 2023-10-29 12:23:25 -04:00
package-lock.json feat: Vision Support + New UI (#1203) 2023-11-21 20:12:48 -05:00
package.json v0.6.1 (#1189) 2023-11-16 08:53:09 -05:00
prettier.config.js
README.md Update README.md (#1086) 2023-10-21 13:04:15 -04:00

LibreChat

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.

Watch the video Click on the thumbnail to open the video☝️

Features

  • Response streaming identical to ChatGPT through server-sent events
  • UI from original ChatGPT, including Dark mode
  • AI model selection: OpenAI API, BingAI, ChatGPT Browser, PaLM2, Anthropic (Claude), Plugins
  • Create, Save, & Share custom presets - More info on prompt presets here
  • Edit and Resubmit messages with conversation branching
  • Search all messages/conversations - More info here
  • Plugins now available (including web access, image generation and more)

⚠️ Breaking Changes ⚠️

Please read this before updating from a previous version


Changelog

Keep up with the latest updates by visiting the releases page - Releases


Table of Contents

Getting Started
General Information
Features
Cloud Deployment
Contributions

Star History

Star History Chart

Sponsors

Sponsored by @mjtechguy, @SphaeroX, @DavidDev1334, @fuegovic, @Pharrcyde


Contributors

Contributions and suggestions bug reports and fixes are welcome! Please read the documentation before you do!


For new features, components, or extensions, please open an issue and discuss before sending a PR.

This project exists in its current state thanks to all the people who contribute