A | B | C | D | E | F | G | H | I | J | K | L | M | ||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
1 | Owner | Repository Name | About | Stars | Forks | Issues | Contributors | Releases | Watchers | Time Since Last Commit | License | Languages | URL | |
2 | huggingface | transformers | 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX. | 138,058 | 27,674 | 1,538 | 436 | 175 | 1,130 | 0 days, 9 hrs, 5 mins | Apache License 2.0 | Python, Cuda, Dockerfile, Shell, C++, C, Makefile, Cython, Jsonnet | https://github.com/huggingface/transformers | |
3 | ollama | ollama | Get up and running with Llama 3.3, Phi 4, Gemma 2, and other large language models. | 110,705 | 8,829 | 1,364 | 389 | 110 | 648 | 1 days, 5 hrs, 29 mins | MIT License | Go, C, Shell, TypeScript, Makefile, Dockerfile, PowerShell, Inno Setup, Objective-C, CSS, JavaScript, Assembly, HTML | https://github.com/ollama/ollama | |
4 | ChatGPTNextWeb | ChatGPT-Next-Web | ✨ Local and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows | 78,974 | 60,174 | 577 | 240 | 75 | 420 | 4 days, 18 hrs, 52 mins | MIT License | TypeScript, SCSS, JavaScript, Rust, Shell, Dockerfile | https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web | |
5 | nomic-ai | gpt4all | GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use. | 71,930 | 7,813 | 704 | 114 | 35 | 652 | 2 days, 13 hrs, 15 mins | MIT License | C++, QML, Python, CMake, JavaScript, C, Qt Script, Shell, Makefile, Batchfile, PowerShell, Objective-C++, CSS | https://github.com/nomic-ai/gpt4all | |
6 | ggerganov | llama.cpp | LLM inference in C/C++ | 71,458 | 10,337 | 624 | 462 | 2,841 | 563 | 0 days, 10 hrs, 44 mins | MIT License | C++, C, Python, Cuda, Objective-C, Metal, CMake, Shell, Makefile, Nix, Dockerfile, Batchfile, JavaScript, Swift | https://github.com/ggerganov/llama.cpp | |
7 | binary-husky | gpt_academic | 为GPT/GLM等LLM大语言模型提供实用化交互接口,特别优化论文阅读/润色/写作体验,模块化设计,支持自定义快捷按钮&函数插件,支持Python和C++等项目剖析&自译解功能,PDF/LaTex论文翻译&总结功能,支持并行问询多种LLM模型,支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。 | 67,116 | 8,243 | 419 | 98 | 32 | 283 | 5 days, 14 hrs, 43 mins | GNU General Public License v3.0 | Python, JavaScript, HTML, CSS, Dockerfile | https://github.com/binary-husky/gpt_academic | |
8 | xtekky | gpt4free | The official gpt4free repository | various collection of powerful language models | 63,216 | 13,517 | 27 | 227 | 226 | 487 | 0 days, 15 hrs, 41 mins | GNU General Public License v3.0 | Python, JavaScript, HTML, CSS, Dockerfile, Shell | https://github.com/xtekky/gpt4free | |
9 | open-webui | open-webui | User-friendly AI Interface (Supports Ollama, OpenAI API, ...) | 60,041 | 7,315 | 170 | 311 | 83 | 298 | 2 days, 15 hrs, 49 mins | BSD 3-Clause "New" or "Revised" License | JavaScript, Svelte, Python, TypeScript, CSS, Shell, Dockerfile, HTML, Batchfile, Mako, Makefile | https://github.com/open-webui/open-webui | |
10 | imartinez | privateGPT | Interact with your documents using the power of GPT, 100% privately, no data leaks | 54,985 | 7,397 | 255 | 90 | 10 | 463 | 74 days, 13 hrs, 0 mins | Apache License 2.0 | Python, MDX, Makefile | https://github.com/imartinez/privateGPT | |
11 | lobehub | lobe-chat | 🤯 Lobe Chat - an open-source, modern-design AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / Qwen / DeepSeek), Knowledge Base (file upload / knowledge management / RAG ), Multi-Modals (Vision/TTS/Plugins/Artifacts). One-click FREE deployment of your private ChatGPT/ Claude application. | 52,225 | 11,307 | 549 | 181 | 1,227 | 237 | 0 days, 8 hrs, 3 mins | Other | TypeScript, MDX, JavaScript, Shell, Dockerfile, CSS, TeX | https://github.com/lobehub/lobe-chat | |
12 | oobabooga | text-generation-webui | A Gradio web UI for Large Language Models with support for multiple inference backends. | 41,814 | 5,441 | 239 | 336 | 56 | 333 | 1 days, 5 hrs, 5 mins | GNU Affero General Public License v3.0 | Python, CSS, JavaScript, Shell, Batchfile, Dockerfile, Jupyter Notebook | https://github.com/oobabooga/text-generation-webui | |
13 | vllm-project | vllm | A high-throughput and memory-efficient inference and serving engine for LLMs | 34,871 | 5,322 | 1,642 | 458 | 46 | 282 | 0 days, 8 hrs, 28 mins | Apache License 2.0 | Python, Cuda, C++, C, Shell, CMake, Dockerfile | https://github.com/vllm-project/vllm | |
14 | Mintplex-Labs | anything-llm | The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, and more. | 30,978 | 3,109 | 217 | 91 | 9 | 231 | 2 days, 7 hrs, 38 mins | MIT License | JavaScript, CSS, Dockerfile, HTML, Shell, HCL | https://github.com/Mintplex-Labs/anything-llm | |
15 | mudler | LocalAI | :robot: The free, Open Source alternative to OpenAI, Claude and others. Self-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 | 29,764 | 2,240 | 410 | 120 | 68 | 205 | 0 days, 10 hrs, 46 mins | MIT License | Go, Python, JavaScript, C++, HTML, Makefile, Shell, Dockerfile, CSS, CMake, C, Earthly | https://github.com/mudler/LocalAI | |
16 | mckaywrigley | chatbot-ui | AI chat for any model. | 29,410 | 8,217 | 196 | 47 | 0 | 255 | 177 days, 7 hrs, 54 mins | MIT License | TypeScript, PLpgSQL, JavaScript, CSS, Shell | https://github.com/mckaywrigley/chatbot-ui | |
17 | janhq | jan | Jan is an open source alternative to ChatGPT that runs 100% offline on your computer | 26,785 | 1,545 | 135 | 60 | 61 | 149 | 0 days, 16 hrs, 28 mins | GNU Affero General Public License v3.0 | TypeScript, JavaScript, SCSS, Makefile, Shell, Batchfile, Dockerfile, NSIS | https://github.com/janhq/jan | |
18 | Bin-Huang | chatbox | User-friendly Desktop Client App for AI Models/LLMs (GPT, Claude, Gemini, Ollama...) | 25,590 | 2,518 | 398 | 34 | 47 | 160 | 3 days, 6 hrs, 25 mins | GNU General Public License v3.0 | TypeScript, JavaScript, CSS, EJS, Shell, Dockerfile | https://github.com/Bin-Huang/chatbox | |
19 | Mozilla-Ocho | llamafile | Distribute and run LLMs with a single file. | 21,391 | 1,106 | 171 | 47 | 33 | 178 | 21 days, 9 hrs, 42 mins | Other | C++, C, JavaScript, Metal, Objective-C, AGS Script, Roff, HTML, Makefile, Python, Shell, Cuda, CSS, Batchfile | https://github.com/Mozilla-Ocho/llamafile | |
20 | danny-avila | LibreChat | Enhanced ChatGPT Clone: Features Agents, Anthropic, AWS, OpenAI, Assistants API, Azure, Groq, o1, GPT-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. | 20,876 | 3,523 | 219 | 176 | 49 | 132 | 0 days, 8 hrs, 30 mins | MIT License | TypeScript, JavaScript, CSS, Handlebars, Shell, Python, HTML, Smarty, Dockerfile | https://github.com/danny-avila/LibreChat | |
21 | PromtEngineer | localGPT | Chat with your documents on your local device using GPT models. No data leaves your device and 100% private. | 20,268 | 2,260 | 479 | 44 | 0 | 170 | 82 days, 18 hrs, 38 mins | Apache License 2.0 | Python, HTML, Dockerfile, Roff | https://github.com/PromtEngineer/localGPT | |
22 | exo-explore | exo | Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚ | 20,026 | 1,135 | 280 | 48 | 11 | 153 | 0 days, 12 hrs, 1 mins | GNU General Public License v3.0 | Python, JavaScript, HTML, CSS, Shell | https://github.com/exo-explore/exo | |
23 | mlc-ai | mlc-llm | Universal LLM Deployment Engine with ML Compilation | 19,731 | 1,627 | 229 | 134 | 1 | 182 | 2 days, 11 hrs, 43 mins | Apache License 2.0 | Python, C++, Kotlin, Swift, Shell, Groovy, CMake, SCSS, Objective-C++, Java, HTML, Makefile, Objective-C, C, Batchfile, Ruby | https://github.com/mlc-ai/mlc-llm | |
24 | GaiZhenbiao | ChuanhuChatGPT | GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI. | 15,351 | 2,292 | 126 | 51 | 26 | 86 | 45 days, 17 hrs, 32 mins | GNU General Public License v3.0 | Python, JavaScript, CSS, HTML, Shell, Dockerfile, Batchfile | https://github.com/GaiZhenbiao/ChuanhuChatGPT | |
25 | mlc-ai | web-llm | High-performance In-browser LLM Inference Engine | 14,397 | 930 | 84 | 45 | 1 | 131 | 6 days, 0 hrs, 15 mins | Apache License 2.0 | TypeScript, SCSS, Shell, HTML, JavaScript | https://github.com/mlc-ai/web-llm | |
26 | h2oai | h2ogpt | Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/ | 11,606 | 1,273 | 304 | 69 | 2 | 157 | 10 days, 23 hrs, 53 mins | Apache License 2.0 | Python, Jupyter Notebook, TeX, HTML, Shell, Groovy, Makefile, Smarty, Dockerfile | https://github.com/h2oai/h2ogpt | |
27 | bentoml | OpenLLM | Run any open-source LLMs, such as Llama, Mistral, as OpenAI compatible API endpoint in the cloud. | 10,436 | 661 | 17 | 31 | 134 | 56 | 6 days, 9 hrs, 56 mins | Apache License 2.0 | Python, Shell | https://github.com/bentoml/OpenLLM | |
28 | chathub-dev | chathub | All-in-one chatbot client | 10,110 | 1,044 | 205 | 12 | 0 | 71 | 101 days, 2 hrs, 29 mins | GNU General Public License v3.0 | TypeScript, JavaScript, SCSS, HTML, CSS | https://github.com/chathub-dev/chathub | |
29 | huggingface | text-generation-inference | Large Language Model Text Generation Inference | 9,643 | 1,129 | 201 | 131 | 53 | 103 | 0 days, 18 hrs, 12 mins | Apache License 2.0 | Python, Rust, Cuda, C++, Nix, Dockerfile, CMake, JavaScript, Shell, Makefile, C | https://github.com/huggingface/text-generation-inference | |
30 | SillyTavern | SillyTavern | LLM Frontend for Power Users. | 9,625 | 2,630 | 221 | 191 | 88 | 64 | 0 days, 10 hrs, 20 mins | GNU Affero General Public License v3.0 | JavaScript, HTML, CSS, Less, Jupyter Notebook, Batchfile, Dockerfile, Shell, Nix | https://github.com/SillyTavern/SillyTavern | |
31 | FMInference | FlexGen | Running large language models on a single GPU for throughput-oriented scenarios. | 9,254 | 557 | 58 | 19 | 0 | 112 | 91 days, 5 hrs, 28 mins | Apache License 2.0 | Python, Shell | https://github.com/FMInference/FlexGen | |
32 | NVIDIA | TensorRT-LLM | TensorRT-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. | 9,230 | 1,081 | 441 | 20 | 12 | 97 | 2 days, 12 hrs, 16 mins | Apache License 2.0 | C++, Python, Cuda, CMake, Shell, Smarty, PowerShell, C, Makefile, Dockerfile | https://github.com/NVIDIA/TensorRT-LLM | |
33 | triton-inference-server | server | The Triton Inference Server provides an optimized cloud and edge inferencing solution. | 8,635 | 1,513 | 681 | 123 | 74 | 147 | 0 days, 8 hrs, 13 mins | BSD 3-Clause "New" or "Revised" License | Python, Shell, C++, CMake, Java, Roff, Smarty, Dockerfile | https://github.com/triton-inference-server/server | |
34 | abetlen | llama-cpp-python | Python bindings for llama.cpp | 8,471 | 1,022 | 563 | 163 | 284 | 78 | 6 days, 11 hrs, 38 mins | MIT License | Python, CMake, Shell, Dockerfile, Makefile | https://github.com/abetlen/llama-cpp-python | |
35 | huggingface | chat-ui | Open source codebase powering the HuggingChat app | 7,951 | 1,174 | 294 | 120 | 15 | 84 | 2 days, 21 hrs, 29 mins | Apache License 2.0 | TypeScript, Svelte, JavaScript, Dockerfile, HTML, Shell, CSS, Smarty | https://github.com/huggingface/chat-ui | |
36 | nat | openplayground | An LLM playground you can run on your laptop | 6,314 | 487 | 90 | 15 | 0 | 60 | 10 days, 4 hrs, 4 mins | MIT License | TypeScript, Python, CSS, JavaScript, HTML | https://github.com/nat/openplayground | |
37 | LostRuins | koboldcpp | Run GGUF models easily with a KoboldAI UI. One File. Zero Install. | 6,173 | 395 | 289 | 461 | 94 | 67 | 1 days, 23 hrs, 43 mins | GNU Affero General Public License v3.0 | C++, C, Cuda, Python, Objective-C, Metal, Beef, C#, Lua, D, Makefile, CMake, Jupyter Notebook, Shell, Batchfile, Nix | https://github.com/LostRuins/koboldcpp | |
38 | xorbitsai | inference | Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop. | 6,054 | 498 | 185 | 89 | 95 | 45 | 1 days, 3 hrs, 13 mins | Apache License 2.0 | Python, JavaScript, CSS, Dockerfile, HTML | https://github.com/xorbitsai/inference | |
39 | enricoros | big-agi | AI suite powered by state-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. | 5,891 | 1,362 | 218 | 46 | 16 | 71 | 1 days, 14 hrs, 18 mins | MIT License | TypeScript, JavaScript, CSS, Dockerfile | https://github.com/enricoros/big-agi | |
40 | simonw | llm | Access large language models from the command-line | 5,710 | 324 | 280 | 34 | 39 | 47 | 2 days, 13 hrs, 38 mins | Apache License 2.0 | Python, Just, Shell | https://github.com/simonw/llm | |
41 | InternLM | lmdeploy | LMDeploy is a toolkit for compressing, deploying, and serving LLMs. | 5,305 | 467 | 389 | 89 | 43 | 42 | 0 days, 23 hrs, 57 mins | Apache License 2.0 | Python, C++, Cuda, CMake, Shell, PowerShell, Dockerfile, C | https://github.com/InternLM/lmdeploy | |
42 | ParisNeo | lollms-webui | Lord of Large Language and Multi modal Systems Web User Interface | 4,468 | 558 | 163 | 39 | 24 | 63 | 0 days, 9 hrs, 59 mins | Apache License 2.0 | CSS, Vue, Python, JavaScript, Shell, Batchfile, Inno Setup, HTML, Jupyter Notebook, Dockerfile | https://github.com/ParisNeo/lollms-webui | |
43 | turboderp | exllamav2 | A fast inference library for running LLMs locally on modern consumer-class GPUs | 3,877 | 293 | 108 | 51 | 38 | 34 | 17 days, 21 hrs, 55 mins | MIT License | Python, Cuda, C++, C | https://github.com/turboderp/exllamav2 | |
44 | minimaxir | simpleaichat | Python package for easily interfacing with chat apps, with robust features and minimal code complexity. | 3,499 | 231 | 55 | 11 | 6 | 35 | 207 days, 15 hrs, 59 mins | MIT License | Python | https://github.com/minimaxir/simpleaichat | |
45 | deep-diver | LLM-As-Chatbot | LLM as a Chatbot Service | 3,297 | 380 | 19 | 7 | 0 | 51 | 433 days, 17 hrs, 59 mins | Apache License 2.0 | Python, Jupyter Notebook | https://github.com/deep-diver/LLM-As-Chatbot | |
46 | SciSharp | LLamaSharp | A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently. | 2,844 | 371 | 144 | 59 | 24 | 56 | 5 days, 15 hrs, 32 mins | MIT License | C#, JavaScript, HTML, CSS | https://github.com/SciSharp/LLamaSharp | |
47 | turboderp | exllama | A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights. | 2,803 | 221 | 65 | 15 | 0 | 37 | 484 days, 13 hrs, 26 mins | MIT License | Python, Cuda, JavaScript, C++, CSS, Shell, HTML, Dockerfile, C | https://github.com/turboderp/exllama | |
48 | janhq | nitro | Local AI API Platform | 2,354 | 144 | 115 | 36 | 168 | 24 | 3 days, 20 hrs, 25 mins | Apache License 2.0 | C++, C, Python, Shell, Inno Setup, CMake, Dockerfile, Makefile, Batchfile | https://github.com/janhq/nitro | |
49 | janhq | cortex.cpp | Local AI API Platform | 2,354 | 144 | 115 | 36 | 168 | 24 | 3 days, 20 hrs, 26 mins | Apache License 2.0 | C++, C, Python, Shell, Inno Setup, CMake, Dockerfile, Makefile, Batchfile | https://github.com/janhq/cortex.cpp | |
50 | n4ze3m | page-assist | Use your locally running AI models to assist you in your web browsing | 1,859 | 182 | 112 | 16 | 32 | 17 | 0 days, 18 hrs, 20 mins | MIT License | TypeScript, CSS, HTML, JavaScript | https://github.com/n4ze3m/page-assist | |
51 | marella | ctransformers | Python bindings for the Transformer models implemented in C/C++ using GGML library. | 1,830 | 140 | 112 | 6 | 30 | 18 | 365 days, 0 hrs, 55 mins | MIT License | C, C++, Cuda, Metal, Objective-C, Python, CMake, Shell | https://github.com/marella/ctransformers | |
52 | a-ghorbani | pocketpal-ai | An app that brings language models directly to your phone. | 1,724 | 136 | 39 | 7 | 9 | 19 | 3 days, 12 hrs, 25 mins | MIT License | TypeScript, Ruby, Kotlin, JavaScript, Objective-C, Objective-C++ | https://github.com/a-ghorbani/pocketpal-ai | |
53 | Mobile-Artificial-Intelligence | maid | Maid is a cross-platform Flutter app for interfacing with GGUF / llama.cpp models locally, and with Ollama and OpenAI models remotely. | 1,629 | 182 | 18 | 22 | 31 | 32 | 83 days, 8 hrs, 33 mins | MIT License | Dart, C++, CMake, Shell, Ruby, Swift, C, Batchfile, Kotlin, Objective-C | https://github.com/Mobile-Artificial-Intelligence/maid | |
54 | ivanfioravanti | chatbot-ollama | Chatbot Ollama is an open source chat UI for Ollama. | 1,531 | 262 | 24 | 7 | 1 | 17 | 174 days, 14 hrs, 15 mins | Other | TypeScript, JavaScript, Dockerfile, CSS, Makefile | https://github.com/ivanfioravanti/chatbot-ollama | |
55 | guinmoon | LLMFarm | llama and other large language models on iOS and MacOS offline using GGML library. | 1,521 | 102 | 32 | 1 | 33 | 21 | 40 days, 23 hrs, 0 mins | MIT License | Swift, Shell | https://github.com/guinmoon/LLMFarm | |
56 | ggozad | oterm | a text-based terminal client for Ollama | 1,220 | 74 | 7 | 15 | 44 | 12 | 5 days, 14 hrs, 6 mins | MIT License | Python | https://github.com/ggozad/oterm | |
57 | srush | llama2.rs | A fast llama2 decoder in pure Rust. | 1,030 | 56 | 15 | 4 | 0 | 11 | 424 days, 8 hrs, 32 mins | MIT License | Rust, Python | https://github.com/srush/llama2.rs | |
58 | semperai | amica | Amica is an open source interface for interactive communication with 3D characters with voice synthesis and speech recognition. | 852 | 135 | 13 | 19 | 4 | 17 | 5 days, 12 hrs, 49 mins | MIT License | TypeScript, JavaScript, Shell, Dockerfile, Rust, HTML, CSS | https://github.com/semperai/amica | |
59 | Vali-98 | ChatterUI | Simple frontend for LLMs built in react-native. | 813 | 47 | 17 | 4 | 54 | 14 | 3 days, 18 hrs, 25 mins | GNU Affero General Public License v3.0 | TypeScript, JavaScript | https://github.com/Vali-98/ChatterUI | |
60 | mlc-ai | web-llm-chat | Chat with AI large language models running natively in your browser. Enjoy private, server-free, seamless AI conversations. | 582 | 81 | 13 | 181 | 0 | 7 | 5 days, 13 hrs, 22 mins | Apache License 2.0 | TypeScript, SCSS, CSS, JavaScript, Shell, Dockerfile | https://github.com/mlc-ai/web-llm-chat | |
61 | KoljaB | LocalAIVoiceChat | Local AI talk with a custom voice based on Zephyr 7B model. Uses RealtimeSTT with faster_whisper for transcription and RealtimeTTS with Coqui XTTS for synthesis. | 563 | 63 | 11 | 2 | 1 | 13 | 167 days, 23 hrs, 36 mins | Other | Python, Batchfile | https://github.com/KoljaB/LocalAIVoiceChat | |
62 | turboderp | exui | Web UI for ExLlamaV2 | 466 | 44 | 32 | 9 | 0 | 9 | 2 days, 13 hrs, 3 mins | MIT License | JavaScript, Python, CSS, HTML | https://github.com/turboderp/exui | |
63 | withcatai | catai | Run AI ✨ assistant locally! with simple API for Node.js 🚀 | 462 | 31 | 1 | 4 | 25 | 10 | 219 days, 15 hrs, 9 mins | MIT License | TypeScript, Svelte, JavaScript, CSS, HTML | https://github.com/withcatai/catai | |
64 | psugihara | FreeChat | llama.cpp based AI chat app for macOS | 453 | 41 | 24 | 4 | 0 | 12 | 62 days, 15 hrs, 11 mins | MIT License | Swift, MDX, TypeScript, CSS, JavaScript, Shell | https://github.com/psugihara/FreeChat | |
65 | pythops | tenere | 🤖 TUI interface for LLMs written in Rust | 443 | 15 | 7 | 10 | 13 | 8 | 19 days, 0 hrs, 19 mins | GNU General Public License v3.0 | Rust, Just | https://github.com/pythops/tenere | |
66 | cztomsik | ava | All-in-one desktop app for running LLMs locally. | 437 | 16 | 3 | 3 | 0 | 9 | 86 days, 11 hrs, 40 mins | Other | TypeScript, Zig, Shell, JavaScript, HTML | https://github.com/cztomsik/ava | |
67 | lmg-anon | mikupad | LLM Frontend in a single html file | 309 | 32 | 27 | 11 | 64 | 5 | 11 days, 17 hrs, 29 mins | Creative Commons Zero v1.0 Universal | HTML, JavaScript, Batchfile, Shell | https://github.com/lmg-anon/mikupad | |
68 | run-llama | chat-ui | Chat UI components for LLM apps | 167 | 11 | 0 | 5 | 0 | 7 | 5 days, 23 hrs, 59 mins | MIT License | TypeScript, CSS, JavaScript | https://github.com/run-llama/chat-ui | |
69 | ptsochantaris | emeltal | Local ML voice chat using high-end models. | 156 | 11 | 1 | 1 | 0 | 4 | 19 days, 10 hrs, 16 mins | MIT License | C++, C, Metal, Objective-C, Swift, Shell, HTML, CSS | https://github.com/ptsochantaris/emeltal | |
70 | ortegaalfredo | neurochat | Native gui to serveral AI services plus llama.cpp local AIs. | 108 | 11 | 2 | 1 | 6 | 5 | 378 days, 15 hrs, 12 mins | BSD 2-Clause "Simplified" License | Pascal, Inno Setup, Shell | https://github.com/ortegaalfredo/neurochat | |
71 | LostRuins | lite.koboldai.net | A zero dependency web UI for any LLM backend, including KoboldCpp, OpenAI and AI Horde | 97 | 47 | 14 | 22 | 0 | 8 | 1 days, 22 hrs, 32 mins | GNU Affero General Public License v3.0 | HTML, JavaScript | https://github.com/LostRuins/lite.koboldai.net | |
72 | nathanlesage | local-chat | LocalChat is a ChatGPT-like chat that runs on your computer | 90 | 3 | 5 | 1 | 12 | 6 | 22 days, 20 hrs, 11 mins | GNU General Public License v3.0 | TypeScript, Vue, JavaScript, Shell, HTML, CSS | https://github.com/nathanlesage/local-chat | |
73 | elgatopanzon | gatogpt | Local LLM inference & management server with built-in OpenAI API | 31 | 3 | 0 | 1 | 0 | 3 | 282 days, 5 hrs, 21 mins | GNU Affero General Public License v3.0 | C#, Dockerfile | https://github.com/elgatopanzon/gatogpt | |
74 | dbddv01 | GPT-Sequencer | A chatbot for local gguf llm models with easy sequencing via csv file. A toy tool for everyone to build advanced prompt engineering sequences. | 8 | 0 | 0 | 1 | 0 | 3 | 204 days, 18 hrs, 8 mins | MIT License | Python | https://github.com/dbddv01/GPT-Sequencer |