Developers
Ranking
Graph Report Top AI Developers
TOP AI Developers by monthly star count
Top AI Organizations
TOP AI Organization Account by AI repo star count
Top AI Project
Top AI Project by Category star count
Top Growing Speed
Top Growing Speed list by the speed of gaining stars
The Least Known Devs
Top List of who create influential repos with little people known
A Year Without Refresh
Projects and developers that are thriving yet have not been updated for a long time.
Top Open Source AI Dev Influencers in
Discover the month's top-trending AI project authors, ranked by the rapid growth in their GitHub star counts. ( Data sourced from GitHub, updated automatically everyday.)
Top AI DevelopersTop AI OrganizationsTop AI ProjectTop Growing SpeedThe Least Known DevsA Year Without Refresh
| Rankings | Developers | Related Project | Project intro | Star count |
|---|---|---|---|---|
1 | screenpipe | AI app store powered by 24/7 desktop history. open source | 100% local | dev friendly | 24/7 screen, mic recording | 12.5K | |
2 | Foundations-of-LLMs | 8.2K | ||
3 | llama-stack | Composable building blocks to build Llama Apps | 8.0K | |
4 | llama-models | Utilities intended for use with Llama models. | 7.0K | |
5 | Hands-On-Large-Language-Models | Official code repo for the O'Reilly Book - "Hands-On Large Language Models" | 5.4K | |
6 | TEN-Agent | TEN Agent is a conversational voice AI agent powered by TEN, integrating Deepseek, Gemini, OpenAI, RTC, and hardware like ESP32. It enables realtime AI capabilities like seeing, hearing, and speaking, and is fully compatible with platforms like Dify and Coze. | 4.9K | |
7 | DictionaryByGPT4 | 一本 GPT4 生成的单词书📚，超过 8000 个单词分析，涵盖了词义、例句、词根词缀、变形、文化背景、记忆技巧和小故事 | 4.0K | |
8 | Mooncake | Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. | 3.8K | |
9 | RouteLLM | A framework for serving and evaluating LLM routers - save LLM costs without compromising quality | 3.5K | |
10 | gptpdf | Using GPT to parse PDF | 3.2K | |
11 | SwarmUI | SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an emphasis on making powertools easily accessible, high performance, and extensibility. | 3.0K | |
12 | datachain | ETL, Analytics, Versioning for Unstructured Data | 2.3K | |
13 | cambrian | Cambrian-1 is a family of multimodal LLMs with a vision-centric design. | 1.8K | |
14 | LlamaGen | Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation | 1.6K | |
15 | latitude-llm | Latitude is the open-source prompt engineering platform to build, evaluate, and refine your prompts with AI | 1.5K | |
16 | colpali | The code used to train and run inference with the ColPali architecture. | 1.5K | |
17 | WordLlama | Things you can do with the token embeddings of an LLM | 1.4K | |
18 | Agentless | Agentless🐱: an agentless approach to automatically solve software development problems | 1.4K | |
19 | ragbuilder | A toolkit to create optimal Production-readyRetrieval Augmented Generation(RAG) setup for your data | 1.4K | |
20 | ComfyUI-Florence2 | Inference Microsoft Florence2 VLM | 1.4K | |
21 | korvus | Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C. | 1.3K | |
22 | Speech-AI-Forge | 🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI. | 1.3K | |
23 | ttt-lm-pytorch | Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States | 1.1K | |
24 | LazyLLM | Easiest and laziest way for building multi-agent LLMs applications. | 1.1K | |
25 | ShareGPT4Video | [NeurIPS 2024] An official implementation of "ShareGPT4Video: Improving Video Understanding and Generation with Better Captions" | 1.1K | |
26 | ik_llama.cpp | llama.cpp fork with additional SOTA quants and improved performance | 1.0K | |
27 | theLMbook | This is the official repository for The Hundred-Page Language Models Book by Andriy Burkov | 1.0K | |
28 | llm-compressor | Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM | 950 | |
29 | Index-1.9B | A SOTA lightweight multilingual LLM | 942 | |
30 | ChatGPT-Mirror | 🚀 一键部署个人的 ChatGPT 镜像站 | 894 | |
31 | LLM-workshop-2024 | A 4-hour coding workshop to understand how LLMs are implemented and used | 864 | |
32 | KVCache-Factory | Unified KV Cache Compression Methods for Auto-Regressive Models | 864 | |
33 | Awesome-Jailbreak-on-LLMs | Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses. | 858 | |
34 | dingllm.nvim | Yacine's LLM nvim scripts | 825 | |
35 | nerve | Create LLM agents without writing code. | 796 | |
36 | EAGLE | Eagle Family: Exploring Model Designs, Data Recipes and Training Strategies for Frontier-Class Multimodal LLMs | 751 | |
37 | StableNormal | [SIGGRAPH Asia 2024 (Journal Track)] StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal | 697 | |
38 | flash-diffusion | ⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation (AAAI 2025 Oral) | 618 | |
39 | voicechat2 | Local SRT/LLM/TTS Voicechat | 609 | |
40 | gemini-ui-to-code | A Streamlit application to generate code from images | 608 | |
41 | magpie | Official repository for ICLR 2025 paper "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline! | 606 | |
42 | Ovis | A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings. | 603 | |
43 | Awesome-Audio-LLM | Audio Large Language Models | 589 | |
44 | buffer-of-thought-llm | [NeurIPS 2024 Spotlight] Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models | 587 | |
45 | LARS | An application for running LLMs locally on your device, with your documents, facilitating detailed citations in generated responses. | 536 | |
46 | esp-ai | The simplest and lowest-cost AI integration solution. If you like this project, please give it a Star~ | 最简单、最低成本的AI接入方案。喜欢本项目的话点个 Star 吧~ | 508 | |
47 | LiveBench | LiveBench: A Challenging, Contamination-Free LLM Benchmark | 487 | |
48 | chatgpt-artifacts | Bring Claude's Artifacts feature to ChatGPT | 483 | |
49 | awesome-production-llm | A curated list of awesome open-source libraries for production LLM | 446 | |
50 | meme-search | The open source Meme Search Engine and Finder. Free and built to self-host locally with Python, Ruby, and Docker. | 436 | |
51 | rust-genai | Rust multiprovider generative AI client (Ollama, OpenAi, Anthropic, Gemini, DeepSeek, xAI/Grok, Groq,Cohere, ...) | 419 | |
52 | mlx-gpt2 | gpt-2 from scratch in mlx | 370 | |
53 | rai | RAI is a vendor-agnostic agentic framework for robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more. | 369 | |
54 | swiftide | Fast, streaming indexing, query, and agentic LLM applications in Rust | 364 | |
55 | EVE | EVE Series: Encoder-Free Vision-Language Models from BAAI | 337 | |
56 | llama3.cuda | llama3.cuda is a pure C/CUDA implementation for Llama 3 model. | 324 | |
57 | GPTQModel | Production ready LLM model compression/quantization toolkit with accelerated inference support for both cpu/gpu via HF, vLLM, and SGLang. | 321 | |
58 | Awesome-Model-Merging-Methods-Theories-Applications | Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. arXiv:2408.07666. | 319 | |
59 | llamanet | Replace OpenAI with Llama.cpp Automagically. | 306 | |
60 | chrome-ai | Vercel AI provider for Chrome built-in model (Gemini Nano) | 295 | |
61 | llama.ttf | A font for writing tiny stories | 294 | |
62 | LLM-Finetune | 大语言模型微调，Qwen2VL、Qwen2、GLM4指令微调 | 293 | |
63 | VideoGPT-plus | Official Repository of paper VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding | 280 | |
64 | llama-zip | LLM-powered lossless compression tool | 265 | |
65 | GoMaxAI-ChatGPT-Midjourney-Pro | 基于Node.js、Vue3、uniapp的ChatGPT+智能体+Midjourney绘画+PPT生成+Suno音乐+Pika/Runway/Sora视频 网页服务 | 个人、团队、企业私有化AIGC平台 | 260 | |
66 | omniai | OmniAI standardizes the APIs for multiple AI providers like OpenAI's Chat GPT, Mistral's LeChat, Claude's Anthropic, Google's Gemini and DeepSeek's Chat.. | 247 | |
67 | llama-box | LM inference server implementation based on *.cpp. | 241 | |
68 | HuatuoGPT-Vision | Medical Multimodal LLMs | 231 | |
69 | flute | Fast Matrix Multiplications for Lookup Table-Quantized LLMs | 225 | |
70 | ComfyUI-ppm | Attention Couple, NegPip (negative weights in prompts) for SDXL, FLUX and HunyuanVideo, more CFG++ and SMEA DY samplers, etc. | 213 | |
71 | GPT-SoVITS2 | GPT-SoVITS2 | 211 | |
72 | llm2sh | Ask GPT to run a command | 197 | |
73 | LLaRA | 🔥[ICLR'25] LLaRA: Supercharging Robot Learning Data for Vision-Language Policy | 190 | |
74 | llm-router | Tutorial for building LLM router | 179 | |
75 | semantic-kernel-java | Semantic Kernel for Java. Integrate cutting-edge LLM technology quickly and easily into your Java based apps. See https://aka.ms/semantic-kernel. | 178 | |
76 | obsidian-tars | Obsidian tars plugin that supports text generation based on tag suggestions, using services like DeepSeek, Claude, OpenAI, OpenRouter, SiliconFlow, Gemini, Ollama, Kimi, Doubao, Qwen, Zhipu, QianFan & more. | 174 | |
77 | lilypad | An open-source prompt engineering framework. | 159 | |
78 | voice-chat-ai | 🎙️ Speak with AI - Run locally using Ollama, OpenAI or xAI - Speech uses XTTS, OpenAI or ElevenLabs | 154 | |
79 | StableFace | Build your own Face App with Stable Diffusion 2.1 | 147 | |
80 | ceLLama | Cell type annotation with local Large Language Models (LLMs) - Ensuring privacy and speed with extensive customized reports | 146 | |
81 | laravel-ai-translator | Automatic translate your language files into many languages using AI like Claude, GPT and etc. | 145 | |
82 | Belullama | Belullama is a comprehensive AI application that bundles Ollama, Open WebUI, and Automatic1111 (Stable Diffusion WebUI) into a single, easy-to-use package. | 143 | |
83 | Train-llm-from-scratch | 使用deepspeed从头开始训练一个LLM,经过pretrain和sft阶段,验证llm学习知识、理解语言、回答问题的能力 | 139 | |
84 | TypeGPT | Integrate LLM's into your OS. For any issues or ideas, message us in the discord server below! | 139 | |
85 | appworld | 🌍 Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL'24 Best Resource Paper. | 139 | |
86 | The-Creator-AI | AI Coding assistant for large and complex codebases. | 136 | |
87 | dive-into-spring-ai | 《动手学SpringAI》包含SSE流/Agent智能体/知识图谱RAG/FunctionCall/历史消息/图片生成/图片理解/Embedding/VectorDatabase/RAG | 132 | |
88 | poixe | Platform of Open Intelligence eXperiences for Everyone. 面向所有人的开放智能体验平台，一站式AI对话工具聚合 | 129 | |
89 | MMTrustEval | A toolbox for benchmarking trustworthiness of multimodal large language models (MultiTrust, NeurIPS 2024 Track Datasets and Benchmarks) | 126 | |
90 | VLM-Visualizer | Visualizing the attention of vision-language models | 123 | |
91 | LLaMA-Factory-Doc | LLaMA Factory Document | 123 | |
92 | MM-NIAH | [NeurIPS 2024] Needle In A Multimodal Haystack (MM-NIAH): A comprehensive benchmark designed to systematically evaluate the capability of existing MLLMs to comprehend long multimodal documents. | 109 | |
93 | sd_embed | Generate long weighted prompt embeddings for Stable Diffusion | 105 | |
94 | A3VLM | [CoRL2024] Official repo of `A3VLM: Actionable Articulation-Aware Vision Language Model` | 104 | |
95 | llm-interface | A simple NPM interface for seamlessly interacting with 36 Large Language Model (LLM) providers, including OpenAI, Anthropic, Google Gemini, Cohere, Hugging Face Inference, NVIDIA AI, Mistral AI, AI21 Studio, LLaMA.CPP, and Ollama, and hundreds of models. | 103 | |
96 | Claude-React-Jumpstart | 📖 A step-by-step guide for beginners to running Claude-generated React code locally. | 102 | |
97 | FFAIVideo | A node.js project that generates short videos using popular AI LLM. | 101 | |
98 | awesome-ai-repositories | A curated list of open source repositories for AI Engineers | 100 | |
99 | VoCo-LLaMA | VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models". | 95 | |
100 | gemini-demos | 92 |
