open-webui/open-webui
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Updated 10:00 UTC.
The most used open source project in the Run AI on your own computer category is open-webui/open-webui (158,689 stars), followed by ggml-org/llama.cpp and odysseus-dev/odysseus. There is no 30 day star data yet, so growth is not ranked (data as of 2026-11-15).
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
License Custom license: Check the licenseMaintenance: Active
LLM inference in C/C++
License MIT: YesMaintenance: Active
Self-hosted AI workspace.
License AGPL-3.0: Yes, with conditionsMaintenance: Active
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
License Apache-2.0: YesMaintenance: Active
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
License MIT: YesMaintenance: Slow
| Project | What it is | License | Maintenance |
|---|---|---|---|
| open-webui/open-webui | User-friendly AI Interface (Supports Ollama, OpenAI API, ...) | Custom license: Check the license | Active |
| ggml-org/llama.cpp | LLM inference in C/C++ | MIT: Yes | Active |
| odysseus-dev/odysseus | Self-hosted AI workspace. | AGPL-3.0: Yes, with conditions | Active |
| unslothai/unsloth | Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more. | Apache-2.0: Yes | Active |
| nomic-ai/gpt4all | GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use. | MIT: Yes | Slow |
22 projects, by 30 day growth, then stars.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
LLM inference in C/C++
Self-hosted AI workspace.
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
The Free Software Media System - Server Backend & API
A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from NVMe. Written in C, runs on the hardware you already own.
Run frontier AI locally.
Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.
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.
Run local AI models on your own computer
AirLLM 2.8T LLM inference with single 4GB GPU
Powerful AI Client
An AI prompt optimizer for writing better prompts and getting better AI results.
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
Hundreds of models & providers. One command to find what runs on your hardware.
Vane is an AI-powered answering engine.
Virtual machines for iOS and macOS
为 DeepSeek Harness (DSH) 插件生态打造的现代化桌面端解决方案。万物皆「插件」,桌面本身也是「插件」。
LLM Inference Engine for Metal, CUDA and Vulkan.