Open-Source Local LLM Projects

• chatbot-ui
• open-webui - friendly AI Interface (Supports Ollama, OpenAI API, ...) | 94,121 | 12,028 | 194 | 393 | 106 | Other | 1 days, 3 hrs, 10 mins |
• transformers - of-the-art Machine Learning for Pytorch, TensorFlow, and JAX. | 144,162 | 28,900 | 1,792 | 438 | 203 | Apache License 2.0 | 0 days, 8 hrs, 1 mins |
• ollama - R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models. | 140,144 | 11,701 | 1,819 | 459 | 125 | MIT License | 0 days, 20 hrs, 36 mins |
• gpt4all - source and available for commercial use. | 73,293 | 7,993 | 713 | 114 | 38 | MIT License | 52 days, 22 hrs, 42 mins |
• gpt_academic
• llama.cpp
• gpt4free - 4.1, gemini 2.5 | 64,201 | 13,633 | 22 | 240 | 284 | GNU General Public License v3.0 | 5 days, 8 hrs, 49 mins |
• text-generation-webui
• localGPT
• mlc-llm
• llamafile
• chathub - in-one chatbot client | 10,016 | 1,022 | 281 | 12 | 0 | GNU General Public License v3.0 | 14 days, 8 hrs, 53 mins |
• text-generation-inference
• server - Clause "New" or "Revised" License | 2 days, 4 hrs, 4 mins |
• llama-cpp-python
• chat-ui
• SillyTavern
• openplayground
• koboldcpp
• lollms-webui
• inference - source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop. | 7,790 | 662 | 198 | 102 | 106 | Apache License 2.0 | 2 days, 6 hrs, 4 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. | 2,027 | 214 | 12 | 27 | 38 | MIT License | 12 days, 17 hrs, 28 mins |
• page-assist
• amica
• catai
• FreeChat
• exui
• LocalAIVoiceChat
• tenere
• mikupad
• lobe-chat - an open-source, modern-design AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / DeepSeek / Qwen), Knowledge Base (file upload / knowledge management / RAG ), Multi-Modals (Plugins/Artifacts) and Thinking. One-click FREE deployment of your private ChatGPT/ Claude / DeepSeek application. | 60,338 | 12,709 | 832 | 236 | 1,633 | Other | 0 days, 8 hrs, 55 mins |
• h2ogpt - docs.h2o.ai/ | 11,801 | 1,293 | 321 | 69 | 2 | Apache License 2.0 | 3 days, 13 hrs, 43 mins |
• OpenLLM - source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud. | 11,237 | 719 | 2 | 30 | 147 | Apache License 2.0 | 6 days, 3 hrs, 18 mins |
• TensorRT-LLM - LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support 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 performant way. | 10,456 | 1,419 | 799 | 134 | 20 | Apache License 2.0 | 1 days, 21 hrs, 7 mins |
• ava - in-one desktop app for running LLMs locally. | 446 | 17 | 4 | 3 | 0 | Other | 0 days, 9 hrs, 36 mins |
• ChatterUI - native. | 1,423 | 99 | 12 | 6 | 68 | GNU Affero General Public License v3.0 | 0 days, 8 hrs, 34 mins |
• cortex.cpp
• web-llm-chat - free, seamless AI conversations. | 735 | 124 | 17 | 180 | 0 | Apache License 2.0 | 6 days, 13 hrs, 58 mins |
• vllm - throughput and memory-efficient inference and serving engine for LLMs | 47,035 | 7,342 | 2,425 | 453 | 60 | Apache License 2.0 | 0 days, 11 hrs, 0 mins |
• anything-llm - in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more. | 43,913 | 4,291 | 261 | 121 | 16 | MIT License | 1 days, 17 hrs, 50 mins |
• LocalAI - hosted 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. Features: Generate Text, Audio, Video, Images, Voice Cloning, Distributed, P2P inference | 32,503 | 2,475 | 458 | 128 | 71 | MIT License | 0 days, 14 hrs, 29 mins |
• jan
• chatbox - friendly Desktop Client App for AI Models/LLMs (GPT, Claude, Gemini, Ollama...) | 34,692 | 3,312 | 717 | 45 | 47 | GNU General Public License v3.0 | 14 days, 7 hrs, 25 mins |
• LibreChat - 4o, 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 project. | 25,419 | 4,371 | 197 | 202 | 53 | MIT License | 1 days, 9 hrs, 16 mins |
• exo
• ChuanhuChatGPT - based QA, GPT finetuning and query with web search. All with a neat UI. | 15,421 | 2,283 | 124 | 51 | 26 | GNU General Public License v3.0 | 59 days, 12 hrs, 42 mins |
• web-llm - performance In-browser LLM Inference Engine | 15,422 | 1,010 | 105 | 44 | 1 | Apache License 2.0 | 6 days, 19 hrs, 1 mins |
• 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. | 6,397 | 1,475 | 249 | 47 | 16 | MIT License | 3 days, 2 hrs, 4 mins |
• llm - line | 7,424 | 442 | 379 | 46 | 50 | Apache License 2.0 | 1 days, 0 hrs, 6 mins |
• exllamav2 - class GPUs | 4,167 | 312 | 140 | 53 | 40 | MIT License | 2 days, 3 hrs, 51 mins |
• pocketpal-ai
• oterm
• chat-ui
• Alpaca
• emeltal - end models. | 163 | 11 | 1 | 1 | 0 | MIT License | 0 days, 12 hrs, 29 mins |
• lite.koboldai.net
• nitro