ChatGPT

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Runs open-weight models on your own machine behind a local API. Pair it with a chat app for the interface.

Langage

Go

Licence

MIT

Étoiles

182k

Dernière release

v0.35.1

Dernier push

2026-10-06

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

The chat app, self-hosted, in front of Ollama or any OpenAI-compatible API. The model comes from elsewhere.

Langage

Python

Licence

Other

Étoiles

154k

Dernière release

v0.11.4

Dernier push

2026-10-06

LLM inference in C/C++

Runs open-weight models on CPU or GPU, with a built-in server and a minimal web chat.

Langage

C++

Licence

MIT

Étoiles

130k

Dernière release

v0.6.0

Dernier push

2026-10-06

A high-throughput and memory-efficient inference and serving engine for LLMs

Serves open-weight models behind an OpenAI-compatible API, tuned for GPU throughput.

Langage

Python

Licence

Apache-2.0

Étoiles

93k

Dernière release

v0.31.0

Dernier push

2026-10-06

✨ Zero-config AI chat assistant. No API key needed — sign up and instantly chat with GPT-5, Claude 4, Gemini 2.5, DeepSeek & 100+ top models. Pay-as-you-go saves you more. Available on Web, iOS, macOS, Android, Linux, Windows.

A chat app you deploy yourself in front of OpenAI, Anthropic, Google or a local model. The model comes from elsewhere.

Langage

TypeScript

Licence

MIT

Étoiles

89k

Dernière release

v2.16.1

Dernier push

2026-08-11

🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

Chat app with plugins and agents, self-hosted or on the desktop, for most model providers.

Langage

TypeScript

Licence

Other

Étoiles

83k

Dernière release

v2.2.18

Dernier push

2026-10-06

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

Desktop or self-hosted app built around chatting with your own documents, with any model provider.

Langage

JavaScript

Licence

MIT

Étoiles

67k

Dernière release

v1.17.0

Dernier push

2026-10-06

AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

Desktop app for many hosted providers and local models, with assistants, knowledge bases and MCP. The model comes from elsewhere.

Langage

TypeScript

Licence

AGPL-3.0

Étoiles

52k

Dernière release

v2.1.4

Dernier push

2026-10-06

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

OpenAI-compatible API for local text, image and audio models, on CPU or GPU.

Langage

Go

Licence

MIT

Étoiles

49k

Dernière release

v4.11.0

Dernier push

2026-10-06

Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

Desktop and web app that runs open models locally through llama.cpp and other backends, or calls a hosted API.

Langage

Python

Licence

AGPL-3.0

Étoiles

48k

Dernière release

v4.9

Dernier push

2026-08-17

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 Auth, Presets, open-source for self-hosting. Active

Self-hosted chat app for Anthropic, OpenAI, Google and local models, with agents and file uploads.

Langage

TypeScript

Licence

MIT

Étoiles

45k

Dernière release

v0.8.8

Dernier push

2026-10-06

Dépôt déplacé

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

Desktop app that downloads open models and runs them offline, or calls a hosted API.

Langage

Rust

Licence

Other

Étoiles

45k

Dernière release

v0.8.4

Dernier push

2026-10-06

Fabric is an open-source framework for augmenting humans using AI. It provides a modular system for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

Runs a library of reusable prompts over text piped in from the terminal.

Langage

Go

Licence

MIT

Étoiles

44k

Dernière release

v1.4.515

Dernier push

2026-10-05

Powerful AI Client

Desktop app in front of OpenAI, Anthropic, Google or a local model through Ollama. The model comes from elsewhere.

Langage

TypeScript

Licence

GPL-3.0

Étoiles

42k

Dernière release

v1.23.5

Dernier push

2026-09-24

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

A self-hosted assistant that answers from your documents and the web, in front of a local or hosted model.

Langage

Python

Licence

AGPL-3.0

Étoiles

38k

Dernière release

2.0.0-beta.28

Dernier push

2026-08-02

SGLang is a high-performance serving framework for large language models and multimodal models.

Serves open-weight models behind an OpenAI-compatible API, tuned for GPU throughput.

Langage

Python

Licence

Apache-2.0

Étoiles

37k

Dernière release

v0.5.21

Dernier push

2026-10-06

LLM Frontend for Power Users.

A self-hosted chat front end aimed at character roleplay, in front of hosted APIs or local models.

Langage

JavaScript

Licence

AGPL-3.0

Étoiles

34k

Dernière release

1.19.0

Dernier push

2026-10-02

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

Serves open-weight models on NVIDIA GPUs behind an OpenAI-compatible API.

Langage

Python

Licence

Other

Étoiles

15k

Dernière release

v1.2.1

Dernier push

2026-10-06

Access large language models from the command-line

Prompts hosted and local models from the terminal and logs every exchange to SQLite.

Langage

Python

Licence

Apache-2.0

Étoiles

13k

Dernière release

0.36

Dernier push

2026-09-22

A command-line productivity tool powered by AI large language models like GPT-5, will help you accomplish your tasks faster and more efficiently.

A terminal assistant that answers questions and suggests shell commands.

Langage

Python

Licence

MIT

Étoiles

12k

Dernière release

1.5.1

Dernier push

2026-07-02

The open source codebase powering HuggingChat

The chat app behind HuggingChat, self-hosted in front of any OpenAI-compatible API.

Langage

TypeScript

Licence

Apache-2.0

Étoiles

11k

Dernière release

v0.10.0

Dernier push

2026-10-06

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

Serves open-weight language, embedding and speech models behind an OpenAI-compatible API.

Langage

Python

Licence

Apache-2.0

Étoiles

9.6k

Dernière release

v3.5.0

Dernier push

2026-10-06

Use your locally running AI models to assist you in your web browsing

A browser sidebar and web UI for chatting with local models through Ollama or an OpenAI-compatible API.

Langage

TypeScript

Licence

MIT

Étoiles

8.2k

Dernière release

v1.5.86

Dernier push

2026-10-04

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Serves open-weight models behind an OpenAI-compatible API, with quantisation and batching.

Langage

Python

Licence

Apache-2.0

Étoiles

8.1k

Dernière release

v0.18.0

Dernier push

2026-09-28

AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. Includes AI personas, AGI functions, world-class Beam multi-model chats, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy on-prem or in the cloud.

Web chat in front of hosted or local models, with answers from several models side by side.

Langage

TypeScript

Licence

MIT

Étoiles

7.1k

Dernière release

v2.1.0

Dernier push

2026-10-05

🐬DeepChat - A smart assistant that connects powerful AI to your personal world

Desktop chat app for hosted and local models, with MCP tool calling.

Langage

TypeScript

Licence

Apache-2.0

Étoiles

6.4k

Dernière release

v1.1.2

Dernier push

2026-10-03

A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.

Manages a cluster of GPUs and serves open-weight models across it behind an OpenAI-compatible API.

Langage

Python

Licence

Apache-2.0

Étoiles

5.8k

Dernière release

v2.2.3

Dernier push

2026-09-30

5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and tools via model context protocol servers .

Desktop chat app for hosted and local models, with MCP tools and a local knowledge base.

Langage

TypeScript

Licence

Other

Étoiles

5.4k

Dernière release

v0.15.4

Dernier push

2026-09-14

AI Chatbots in terminal for free

Terminal chat with several providers, some usable without an API key.

Langage

Go

Licence

GPL-3.0

Étoiles

3.3k

Dernière release

v2.15.0

Dernier push

2026-10-05

the terminal client for LLMs

A terminal chat client for Ollama models.

Langage

Python

Licence

MIT

Étoiles

2.4k

Dernière release

0.25.0

Dernier push

2026-10-03

🦙 Local and online AI hub

A GNOME desktop app for chatting with local models through Ollama.

Langage

Python

Licence

GPL-3.0

Étoiles

1.6k

Dernière release

9.2.5

Dernier push

2026-10-02

A minimal LLM chat app that runs entirely in your browser

A minimal web chat in front of Ollama or an OpenAI-compatible server.

Langage

TypeScript

Licence

MIT

Étoiles

1.2k

Dernière release

0.36.0

Dernier push

2026-10-05