Chat UI

Open WebUI is a feature-rich, user-friendly self-hosted AI platform supporting Ollama and OpenAI-compatible APIs, with RAG, agents, and MCP capabilities.

llmself-hostedollama +2

· Ollama/OpenAI API integration — Supports local Ollama models and OpenAI-compatible APIs (LMStudio, Groq, Mistral, etc.)
· Local RAG engine — 9 vector databases (ChromaDB, PGVector, Qdrant, etc.) with multiple document extraction engines
· Voice/video calls — Integrated STT (Whisper, Deepgram) and TTS (ElevenLabs, OpenAI) for hands-free communication

NextChat

88.7k · TypeScript

chatbotcross-platformtypescript

NextChat is a lightweight, cross-platform AI assistant client supporting GPT-4, Claude, Gemini and more, with Web, desktop, and mobile experiences.

· Multi-model compatible - supports OpenAI GPT-4, Claude, DeepSeek, Gemini Pro and other LLM backends
· One-click deploy - deploy to Vercel/Zeabur in one click, or build as ~5MB cross-platform desktop client
· Privacy first - all data stored locally in browser, no server-side persistence required

ChatGPT Next Web

88.7k · TypeScript

Cross-platform ChatGPT-style frontend, multi-provider and one-click deploy.

chat-uiself-hostednextjs

· One-click deploy — Vercel / Docker / self-host
· Multi-provider — OpenAI, Azure, Gemini, Claude
· Multi-device — Cross-device conversation sync

Lobe Chat

82.2k · TypeScript

Lobe Chat is an open-source ChatGPT-style chat application with a plugin system and multi-model support, suitable as an agent conversation interface.

chatbotpluginstypescript

· Agents as the unit of work - Organize workflows around agents, supporting hiring, scheduling, and managing entire AI teams
· Unified intelligence - Seamlessly access any model and modality with full user control over model selection and switching
· 10,000+ skill ecosystem - Over ten thousand tools and MCP-compatible plugins connecting agents to everyday tools

LobeHub

82.2k · TypeScript

chatbottypescriptagent +2

The ultimate space for work and life to find, build and collaborate with agent teammates that grow with you, enabling multi-agent collaboration and team design.

· Agent Collaboration Space — organize work and life tasks with multiple agent teammates
· Multi-model Access — connect to mainstream LLM services and switch by scenario
· Role and Knowledge Configuration — configure prompts, data, and capability boundaries for each agent

GPT4All

77.4k · C++

Stale B

Run Local LLMs on Any Device. Open-source and available for commercial use. Provides fully offline local inference and chat for AI agents.

pythonllmagent +3

· Fully offline local inference - No API calls or GPU required, run LLMs privately on everyday laptops and desktops
· Cross-platform desktop app - Native installers for Windows, macOS, and Linux, download and run immediately
· Python SDK integration - Wraps llama.cpp via gpt4all Python package, load models and inference in a few lines of code

AnythingLLM

65.5k · JavaScript

chatbotragknowledge-base +3

AnythingLLM is an all-in-one AI productivity app with a self-hosted chat UI, RAG knowledge base, AI agents, and multi-model management, privacy-first with zero configuration.

· Multi-model support — Supports 30+ LLM providers including OpenAI, Anthropic, Ollama, LM Studio, and local llama.cpp models
· Dynamic model routing — Automatically routes conversations to the best provider and model based on user-defined rules
· AI Agent builder — No-code AI Agent builder with built-in tools like web browsing and MCP protocol compatibility

Warp

64.7k · Rust

The agentic development environment built for coding with multiple AI agents, providing a next-generation terminal experience.

chatbotagentcli +2

· Agentic development environment — Next-gen terminal-based dev environment with built-in AI coding agent, supports external CLI agents (Claude Code, Codex, etc.)
· Rust-native build — Core engine written in Rust delivering high-performance terminal experience and rendering capabilities
· Multi-agent collaboration — Simultaneously use multiple AI agents for collaborative coding in the terminal, including Warp's built-in and third-party agents

chatgptdesktopcross-platform +2

ChatGPT

54.5k · Rust

Stale C

ChatGPT is an open-source desktop client that wraps ChatGPT Web in a Tauri cross-platform shell, freeing you from the browser.

· Tauri cross-platform — native desktop feel on macOS, Windows and Linux
· No-browser shell — dedicated window, tray icon and shortcuts
· Local-first — lower memory than a browser, multi-account support

VibeVoice

53.6k · Python

Open-source frontier voice AI from Microsoft, providing high-quality speech synthesis and recognition for building real-time conversational voice agent applications.

voiceagentpython +1

· 60-minute single-pass ASR — Processes up to 60 minutes of continuous audio in one pass with consistent speaker tracking throughout
· Structured transcription output — Jointly produces speaker identity, timestamps, and content (Who/When/What) without post-processing
· Custom hotword guidance — Accepts domain-specific terms and proper nouns to significantly improve recognition accuracy on specialized content

Cherry Studio

51.4k · TypeScript

chat-uimulti-modelagent +2

Cherry Studio is an AI productivity studio with smart chat, autonomous agents, and 300+ assistants, providing unified access to frontier LLMs.

· Multi-provider LLM support — Integrates OpenAI, Gemini, Anthropic cloud services plus Ollama, LM Studio local models
· 300+ pre-configured assistants — Built-in library of assistants with custom creation and multi-model simultaneous conversations
· Document processing — Supports text, images, Office, PDF formats with Mermaid chart rendering and code syntax highlighting

tldraw

50.1k · TypeScript

canvasgenerative-uireact +1

tldraw is an infinite canvas SDK for the web; its AI integrations let agents draw, annotate, and reason visually over a shared whiteboard.

· Infinite canvas SDK as React components embeddable in any web app
· Generative-UI friendly — adopted as the visual frontend by multiple agent products
· Complete design system with shapes, connectors, text, images, and layers

text-generation-webui

47.6k · Python

chat-uilocal-llmtext-generation +3

The original local LLM interface supporting text generation, vision, tool-calling, and training with both a web UI and API. Runs 100% offline and private.

· Multiple backends — Integrates llama.cpp, ExLlamaV3, Transformers, TensorRT-LLM with hot-swapping between backends
· OpenAI/Anthropic-compatible API — Provides Chat, Completions, and Messages endpoints as a local drop-in replacement
· Vision multimodal — Supports image attachments for visual understanding, plus PDF and DOCX file uploads for content chat

Text Generation WebUI

47.6k · Python

local-llmchat-uidesktop +2

Text Generation WebUI is oobabooga's all-in-one local LLM desktop tool supporting text, vision, tool calling and agent workflows.

· Web-based UI — fully featured interface out of the box
· Multi-model — GGUF, GPTQ, AWQ, EXL2 formats
· Tool calling — OpenAI-style function calling and execution

Jan

44.3k · TypeScript

chat-uidesktop-appoffline-ai +3

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer, supporting multiple local LLMs with a full desktop chat UI and API server.

· Local LLM Execution — Download and run Llama, Gemma, Qwen from HuggingFace locally
· Cloud Model Integration — OpenAI GPT, Anthropic Claude, Mistral, Groq and more cloud APIs
· Local OpenAI-compatible API — Local API server at localhost:1337 for other applications

LibreChat

42.7k · TypeScript

chat-uimulti-modelagents +3

LibreChat is an enhanced open-source ChatGPT clone featuring Agents, MCP tools, multi-model support, code interpreter, AI search, and more.

· Multi-model switching — Supports OpenAI, Anthropic, Google, AWS Bedrock, Azure OpenAI, and custom OpenAI-compatible endpoints without a proxy
· Agent & MCP tool integration — No-code custom assistants with MCP protocol, subagent delegation, skills system, and agent marketplace
· Sandboxed code interpreter — Secure isolated execution in Python, Node.js, Go, C/C++, Java, PHP, Rust, Fortran with direct file handling

Chatbox

41.6k · TypeScript

chat-uimulti-modeldesktop +2

Chatbox is a powerful cross-platform AI client supporting OpenAI, Claude, Gemini, and other LLMs with desktop and mobile apps.

· Multi-model support — Seamlessly integrate OpenAI, Azure OpenAI, Claude, Gemini Pro, Ollama and more
· Local data storage — All data stays on your device for privacy and persistence
· Cross-platform desktop — Windows, macOS, Linux with ready-to-use installers

AstrBot

39.9k · Python

chatbotim-integrationmcp +2

An AI Agent assistant that integrates multiple IM platforms, LLMs, plugins and AI features, supporting QQ, Telegram, Discord and more.

· Multi-platform IM Integration — Connect QQ, WeChat Work, Feishu, DingTalk, Telegram, Slack and more via plugins
· LLM Conversations & Multimodal — Multi-LLM support with text dialogue, image understanding, and multimodal capabilities
· Agent & MCP Protocol — Built-in agent orchestration and MCP protocol support for tool calls and skill chaining

novu

39.7k · TypeScript

notificationinfrastructureagent-tools +1

Novu is the open-source notification infrastructure for developers, providing a unified API to deliver in-app, email, SMS, and push notifications triggered by agent events.

· Unified notification infrastructure for email, SMS, push, in-app, and webhook
· Built for AI agents with event-driven workflow triggers
· Multi-channel routing with intelligent distribution by priority and user preference

Langchain-Chatchat

38.6k · Python

Stale B

A local knowledge base RAG and Agent application platform built on Langchain with support for ChatGLM, Qwen, Llama and other LLMs, offering conversation, knowledge base management, and agent capabilities.

ragllmpython +3

· Local knowledge base QA — Document loading, text splitting, vectorization and semantic retrieval via Langchain with BM25+KNN hybrid search
· Multi-framework model inference — Supports Xinference, Ollama, FastChat, LocalAI for GLM-4, Qwen2, Llama3 and more
· Agent tool calling — Optimized for ChatGLM3/Qwen with auto tool selection, single tool parameter parsing, and multimodal image chat

CopilotKit

37.2k · TypeScript

frontendgenerative-uireact +2

The Frontend Stack for Agents & Generative UI. React + Angular component library, makers of the AG-UI Protocol, enabling AI agents to work directly in application UIs.

· Chat UI — React-based chat interface with message streaming, tool calls, and agent responses
· Generative UI — Agents dynamically generate and update UI components at runtime based on user intent
· Shared State — Synchronized state layer that agents and UI components read/write in real time

second-brainragself-hosted +2

Khoj

37.0k · Python

Normal A

Khoj is a self-hostable AI second brain that answers questions from the web or your docs, builds custom agents, schedules automations, and performs deep research.

· Multi-LLM support — Switch between local and cloud LLMs including llama3, qwen, gemma, mistral, gpt, claude, gemini, deepseek
· Multi-format document retrieval — Get answers from PDFs, Markdown, Word, Notion, org-mode, images and more
· Custom agent creation — Build custom agents with custom knowledge, persona, chat model and tools

QwenPaw

34.8k · Python

personal-assistantmulti-channelmemory +2

Personal AI assistant from the AgentScope team with an Agent OS architecture, three-layer memory, kernel-level sandboxing, and one instance serving DingTalk, WeChat, Telegram and more.

· Three-layer memory — live working context, full verbatim history, and a ReMe-powered self-evolving knowledge base that becomes searchable Markdown memory
· Local or cloud, runs free — bundled QwenPaw-Flash models (2B/4B/9B) need no API key, and Ollama plus 14+ cloud providers also work
· Security built in — kernel-level Sandbox, Tool Guard, File Guard, Skill Scanner, and Access Policy block dangerous commands before they run

chat-uiopenaimulti-model +2

Chatbot UI

33.3k · TypeScript

Stale B

Chatbot UI is an open-source AI chat interface supporting OpenAI, Claude, Gemini and more, with a modern conversation UI and flexible deployment options.

· Multi-model Support — OpenAI, Claude, Gemini, Azure OpenAI, Ollama and more LLMs
· Supabase Backend — User auth, data persistence, and real-time sync via Supabase
· Modern Chat UI — Markdown rendering, code highlighting, streaming message output