Open-Source Local LLM Projects

• lobe-chat - an open-source, modern-design LLMs/AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / Bedrock / Azure / Mistral / Perplexity ), Multi-Modals (Vision/TTS) and plugin system. One-click FREE deployment of your private ChatGPT chat application. | 32,395 | 7,757 | 373 | 116 | 688 | MIT License | 0 days, 8 hrs, 29 mins |
• chatbot-ui
• open-webui - friendly WebUI for LLMs (Formerly Ollama WebUI) | 26,615 | 2,850 | 121 | 147 | 33 | MIT License | 0 days, 9 hrs, 18 mins |
• LocalAI - hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. It allows to generate Text, Audio, Video, Images. Also with voice cloning capabilities. | 21,092 | 1,609 | 302 | 96 | 48 | MIT License | 0 days, 15 hrs, 15 mins |
• transformers - of-the-art Machine Learning for Pytorch, TensorFlow, and JAX. | 127,442 | 25,261 | 1,112 | 433 | 151 | Apache License 2.0 | 0 days, 8 hrs, 1 mins |
• ollama
• ChatGPT-Next-Web - platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。 | 71,529 | 57,065 | 333 | 183 | 60 | MIT License | 2 days, 0 hrs, 44 mins |
• gpt4all - source LLMs anywhere | 65,760 | 7,241 | 430 | 101 | 16 | MIT License | 0 days, 13 hrs, 5 mins |
• gpt_academic
• llama.cpp
• gpt4free
• text-generation-webui
• vllm - throughput and memory-efficient inference and serving engine for LLMs | 20,855 | 2,882 | 1,145 | 358 | 27 | Apache License 2.0 | 0 days, 9 hrs, 13 mins |
• jan - LLM) | 19,900 | 1,150 | 165 | 48 | 24 | GNU Affero General Public License v3.0 | 0 days, 23 hrs, 48 mins |
• localGPT
• chatbox - friendly Desktop Client App for AI Models/LLMs (GPT, Claude, Gemini, Ollama...) | 19,360 | 1,969 | 290 | 28 | 62 | GNU General Public License v3.0 | 3 days, 19 hrs, 13 mins |
• mlc-llm
• llamafile
• anything-llm - in-one Desktop & Docker AI application with full RAG and AI Agent capabilities. | 15,859 | 1,665 | 157 | 49 | 0 | MIT License | 0 days, 11 hrs, 22 mins |
• ChuanhuChatGPT - based QA, GPT finetuning and query with web search. All with a neat UI. | 14,943 | 2,259 | 121 | 49 | 21 | GNU General Public License v3.0 | 14 days, 17 hrs, 49 mins |
• LibreChat - 4 Vision, Mistral, Bing, Anthropic, OpenRouter, Vertex AI, Gemini, AI model switching, message search, langchain, DALL-E-3, ChatGPT Plugins, OpenAI Functions, Secure Multi-User System, Presets, completely open-source for self-hosting. More features in development | 12,300 | 2,203 | 90 | 122 | 41 | MIT License | 0 days, 21 hrs, 33 mins |
• web-llm - performance In-browser LLM Inference Engine | 11,127 | 692 | 45 | 33 | 1 | Apache License 2.0 | 0 days, 9 hrs, 5 mins |
• h2ogpt
• chathub - in-one chatbot client | 9,708 | 968 | 311 | 12 | 0 | GNU General Public License v3.0 | 11 days, 2 hrs, 14 mins |
• FlexGen - oriented scenarios. | 9,052 | 527 | 56 | 18 | 0 | Apache License 2.0 | 53 days, 16 hrs, 5 mins |
• text-generation-inference
• server - Clause "New" or "Revised" License | 0 days, 8 hrs, 18 mins |
• TensorRT-LLM - LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines. | 7,100 | 762 | 612 | 13 | 6 | Apache License 2.0 | 0 days, 8 hrs, 34 mins |
• llama-cpp-python
• chat-ui
• OpenLLM - source LLMs, such as Llama 2, Mistral, as OpenAI compatible API endpoint in the cloud. | 9,108 | 581 | 56 | 26 | 118 | Apache License 2.0 | 0 days, 20 hrs, 10 mins |
• SillyTavern
• openplayground
• big-agi - of-the-art models and providing advanced AI/AGI functions. It features AI personas, AGI functions, 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. | 4,619 | 1,054 | 151 | 37 | 16 | MIT License | 0 days, 8 hrs, 41 mins |
• koboldcpp - file way to run various GGML and GGUF models with KoboldAI's UI | 4,187 | 304 | 216 | 470 | 79 | GNU Affero General Public License v3.0 | 0 days, 11 hrs, 21 mins |
• lollms-webui
• llm - line | 3,272 | 163 | 188 | 19 | 25 | Apache License 2.0 | 9 days, 23 hrs, 32 mins |
• exllamav2 - class GPUs | 3,112 | 228 | 110 | 39 | 26 | MIT License | 1 days, 10 hrs, 49 mins |
• inference - source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop. | 3,088 | 258 | 327 | 53 | 64 | Apache License 2.0 | 0 days, 8 hrs, 1 mins |
• lmdeploy
• LLamaSharp
• chatbot-ollama
• LLMFarm
• maid - platform Flutter app for interfacing with GGUF / llama.cpp models locally, and with Ollama and OpenAI models remotely. | 945 | 93 | 8 | 15 | 29 | MIT License | 0 days, 8 hrs, 24 mins |
• oterm - based terminal client for Ollama | 827 | 40 | 9 | 9 | 18 | MIT License | 20 days, 17 hrs, 48 mins |
• page-assist
• amica
• catai
• FreeChat
• exui
• LocalAIVoiceChat
• ava - in-one desktop app for running LLMs locally. | 358 | 15 | 9 | 3 | 0 | Other | 34 days, 14 hrs, 39 mins |
• tenere
• mikupad
• emeltal - end models. | 123 | 6 | 0 | 1 | 0 | MIT License | 0 days, 13 hrs, 33 mins |
• privateGPT
• nitro - in, local AI alternative to the OpenAI stack. Multi-engine (llama.cpp, TensorRT-LLM). Powers 👋 Jan | 1,698 | 89 | 69 | 26 | 84 | No license | 0 days, 8 hrs, 24 mins |
• ChatterUI - native. | 164 | 9 | 4 | 2 | 22 | GNU Affero General Public License v3.0 | 1 days, 5 hrs, 18 mins |