TOP AI Developers by monthly star count
TOP AI Organization Account by AI repo star count
Top AI Project by Category star count
Top Growing Speed list by the speed of gaining stars
Top List of who create influential repos with little people known
Projects and developers that are thriving yet have not been updated for a long time.
Rankings | Developers | Related Project | Project intro | Star count |
---|---|---|---|---|
1 | agenticSeek | Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity. 🔔 Official updates only via twitter @Martin993886460 (Beware of fake) | 18.9K | |
2 | deep-research | An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic. | 13.7K | |
3 | deep-searcher | Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python. | 6.3K | |
4 | VLM-R1 | Solve Visual Understanding with Reinforced VLMs | 5.2K | |
5 | R1-V | Witness the aha moment of VLM with less than $3. | 3.8K | |
6 | deepchat | 🐬DeepChat - A smart assistant that connects powerful AI to your personal world | 3.5K | |
7 | local-deep-research | Local Deep Research is an AI-powered assistant that transforms complex questions into comprehensive, cited reports by conducting iterative analysis using any LLM across diverse knowledge sources including academic databases, scientific repositories, web content, and private document collections. | 2.9K | |
8 | DeepClaude | Unleash Next-Level AI! 🚀 💻 Code Generation: DeepSeek r1 + Claude 3.7 Sonnet - Unparalleled Performance! 📝 Content Creation: DeepSeek r1 + Gemini 2.5 Pro - Superior Quality! 🔌 OpenAI-Compatible. 🌊 Streaming & Non-Streaming Support. ✨ Experience the Future of AI – Today! Click to Try Now! ✨ | 2.6K | |
9 | deep-research-web-ui | (Supports DeepSeek R1) An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. | 1.9K | |
10 | HiveChat | An AI chat bot for small and medium-sized teams, supporting models such as Deepseek, Open AI, Claude, and Gemini. 专为中小团队设计的 AI 聊天应用,支持 Deepseek、Open AI、Claude、Gemini 等模型。 | 795 | |
11 | open-deep-research | An open-source alternative to OpenAI and Gemini's deep research. | 782 | |
12 | lmm-r1 | Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks. | 744 | |
13 | deepseek4j | deepseek java sdk | 668 | |
14 | bytebot | Bytebot is the container for desktop agents. | 667 | |
15 | GamingAgent | LLM/VLM gaming agents and model evaluation through games. | 643 | |
16 | agentica | TypeScript AI Framework specialized AI Function Calling enhanced by compiler skills. | 636 | |
17 | bd3lms | Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models | 525 | |
18 | VisualThinker-R1-Zero | Explore the Multimodal “Aha Moment” on 2B Model | 507 | |
19 | Awesome-MCoT | Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey | 486 | |
20 | SWELancer-Benchmark | This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?" | 484 | |
21 | train-deepseek-r1 | Building DeepSeek R1 from Scratch | 471 | |
22 | lmstudio-python | LM Studio Python SDK | 436 | |
23 | ReasonFlux | ReasonFlux Series - Open-Sourced LLM Family for Reasoning, Coding, Reward Modeling and Data Selection | 405 | |
24 | r1_vlm | Build your own visual reasoning model | 383 | |
25 | Flame-Code-VLM | Flame is an open-source multimodal AI system designed to translate UI design mockups into high-quality React code. It leverages vision-language modeling, automated data synthesis, and structured training workflows to bridge the gap between design and front-end development. | 367 | |
26 | LanPaint | High quality training free inpaint for every stable diffusion model. Supports ComfyUI | 358 | |
27 | bedrock-engineer | Universal AI agent building apps using Amazon Bedrock, capable of customize to create/edit files, execute commands, search the web, use knowledge base, use multi-agents, generative images and more. | 312 | |
28 | gemini | 使用 Deno 免费代理 Google Gemini,国内直连,不限地区/网络环境,打开即用。 | 312 | |
29 | open-cuak | Reliable Automation Agents at Scale | 279 | |
30 | elimination_game | A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private conversations, form alliances, and vote to eliminate each other | 277 | |
31 | My-Dream-Moments | 推荐使用DeepSeekV3。可以接入微信、QQBot。基于LLM的更逼真的情感陪伴程序。内置了 Atri-My dear moments 的 prompt。Built-in prompt for Atri My dear moments.Support WeChat& QQBot. More realistic emotional companionship program based LLM, meet the characters in your dream. | 259 | |
32 | Kolo | A one stop shop for data generation, fine tuning and testing LLMs locally using the best tools available. Keeping it simple and versatile! | 231 | |
33 | oat-zero | A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior. | 222 | |
34 | deepseek2api | DeepSeek 逆向 API | 210 | |
35 | ai-guide | 鱼皮的 AI 知识库,汇总热门的 AI 大模型和工具,比如 Deepseek 使用指南、提示词技巧分享、知识干货、应用场景、AI 变现、行业资讯、教程资源等一系列内容,帮助你快速掌握 AI 技术,走在时代前沿。涉及的大模型:chatGPT、Deepseek、Deepseek-r1、QWEN、GROK 等等 | 206 | |
36 | VimLM | VimLM is a Vim plugin that provides an LLM-powered assistant for code editing by allowing users to interact with a local LLM model through Vim commands and automatically ingesting code context. | 199 | |
37 | r1-computer-use | Applying the ideas of Deepseek R1 to computer use | 198 | |
38 | aidermacs | Emacs AI Pair Programming Solution | 187 | |
39 | r1-ktransformers-guide | run DeepSeek-R1 GGUFs on KTransformers | 152 | |
40 | small-doge | Doge Family of Small Language Model | 148 | |
41 | deeppowers | An open-source, high-performance inference accelerator engine supporting various large language models such as DEEPSEEK, GPT, GEMINI, and CLAUDE. | 147 | |
42 | Mirror-Flowers | 基于 AI 的代码安全审计工具,支持多种编程语言的代码分析,可以帮助开发者快速发现代码中的潜在安全漏洞。支持DeepSeek-R1,ChatGPT-4o等多种大模型。 | 142 | |
43 | Namo-R1 | A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease. | 133 | |
44 | GeminiMixSuper | 基于DeepseekR1/Gemini2/GoogleVison2/GoogleSearch API实现的深度思考联网多模态大模型。 | 127 | |
45 | synalinks | 🧠🔗 Graph-Based Programmable Neuro-Symbolic LM Framework - a production-first LM framework built with decade old Deep Learning best practices | 127 | |
46 | DeepSeek-Chat-UI | DeepSeek Chat UI, Build your own deepseek service through the API of public cloud vendors。支持上下文、历史会话、联网搜索、TXT/DOC/PDF文件上传、用户管理、流式输出。 | 115 | |
47 | arxiv_summarizer | This repository provides a Python script to fetch and summarize research papers from arXiv using the free Gemini API | 112 | |
48 | BreezeApp | BreezeAPP 是一款為 Android 和 iOS 平台開發的純手機 AI 應用程式。從 App Store下載,即可在不連網的狀態下享受多項 AI 功能。源碼由聯發創新基地(MediaTek Research)提供。我們旨在推廣兩個概念: 人人都可以在自己的手機上自由選擇並運行不同的LLM - one is free to choose one's own LLM to run on a phone,以及任何app開發者都可以輕鬆寫作創意的純手機AI應用 - any dev can create purely phone-based AI apps easily。 | 104 | |
49 | deepseek-r1-llama-8b | fine-tune deepseek r1 | 103 | |
50 | DeepSeek-R1-Distill-Qwen-32B-Medical-Fine-tune | 基于200万条医疗数据对DeepSeek-R1-Distill-Qwen-32B进行fine tune且部署 | 103 | |
51 | On-device-Sora | [arXiv] On-device Sora: Enabling Diffusion-Based Text-to-Video Generation for Mobile Devices | 102 | |
52 | LangGraphChatBot | 使用LangGraph+DeepSeek-R1+FastAPI+Gradio实现一个带有记忆功能的流量包推荐智能客服web端用例,同时也支持gpt大模型、国产大模型(OneApi方式)、Ollama本地开源大模型、阿里通义千问大模型 | 97 | |
53 | NanoSage | Local LLM Powered Recursive Search & Smart Knowledge Explorer | 96 | |
54 | CoSER | Official Code for "Coser: Coordinating LLM-Based Persona Simulation of Established Roles" | 95 | |
55 | Logic-RL-Lite | Lightweight replication study of DeepSeek-R1-Zero. Interesting findings include "No Aha Moment", "Longer CoT ≠ Accuracy", and "Language Mixing in Instruct Models". | 81 | |
56 | reflect-vlm | Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation | 80 | |
57 | tokens | A token management platform that reverse-engineers the conversation interfaces of ChatGPT, Cursor, Grok, Claude, Windsurf, Gemini, and Sora, converting them into the OpenAI format./Token管理平台,逆向ChatGPT、Cursor、Grok、Claude、Windsurf、Gemini、Sora平台的对话接口转OpenAI格式 | 74 | |
58 | jailbreak-reasoning-openai-o1o3-deepseek-r1 | 67 | ||
59 | deepseek-free | DeepSeek 部署教程 / 免费 API 接口 / 官方平替 / 入门指南【2025年6月更新】 提供 DeepSeek 部署教程,包括 PC 电脑端本地部署最新 DeepSeek-R1 模型,手机端通过 Termux 快速部署 DeepSeek-R1 模型。收录各大云平台服务(英伟达、微软、亚马逊AWS、阿里云、腾讯云、硅基流动 x 华为云)提供的(免费) API 接口服务,以及收录支持 DeepSeek API 应用等等。 | 66 | |
60 | Awesome-LRM-Safety | Awesome Large Reasoning Model(LRM) Safety.This repository is used to collect security-related research on large reasoning models such as DeepSeek-R1 and OpenAI o1, which are currently very popular. | 64 | |
61 | ollama-webui-traefik-docker | 64 | ||
62 | awesome-deepseek-prompts | Prompts for deepseek, deepseek R1 | 62 | |
63 | ReStyle3D | [SIGGRAPH 2025] ReStyle3D: Scene-level Appearance Transfer with Semantic Correspondences | 57 | |
64 | aperture | 🔬 Visualize attention layers from Stable Diffusion | 56 | |
65 | MoondreamObjectTracking | Using the moondream VLM with optical flow for promptable object tracking | 48 | |
66 | deepseek-r1-finetune | A step by step guide to fine-tuning the DeepSeek R1 Distilled models on Apple Silicon machines. | 47 | |
67 | ai4free-wrapper | A Free AI OpenAI compatible API for Different AI models like GPT-4o, Claude 3.7 Sonnet, Deepseek R1, o3-mini, etc | 45 | |
68 | local-rag-researcher-deepseek | Local RAG researcher agent built using Langgraph, DeepSeek R1 and Ollama | 44 | |
69 | Chinese-Data-Distill-From-R1 | 中文基于满血DeepSeek-R1蒸馏数据集 | 44 | |
70 | llm-context-limits | Since OpenAI and friends refuse to give us a max_ctx param in /models, here's the current context window, input token and output token limits for OpenAI (API), Anthropic, Qwen, Deepseek, llama, Phi, Gemini and Mistral | 43 | |
71 | moe-pruner | A repository aimed at pruning DeepSeek V3, R1 and R1-zero to a usable size | 42 | |
72 | GhostEscape | 利用SDL3、GLM开发一款逃生类型的游戏 | 41 | |
73 | laravel-py | interact with python in Laravel applications . | 40 | |
74 | PURE | SOTA RL fine-tuning solution for advanced math reasoning of LLM | 38 | |
75 | 1chat | 1chat is an iOS app that lets you chat with the DeepSeek-R1 model locally. | 37 | |
76 | R1-Nature | 最简易的R1结果在小模型上的复现,阐述类O1与DeepSeek R1最重要的本质。Think is all your need。利用实验佐证,对于强推理能力,think思考过程性内容是AGI/ASI的核心。 | 36 | |
77 | Inst3D-LMM | [CVPR 2025] Official code repository for "Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning" | 35 | |
78 | VLM2-Bench | VLM^2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues | 33 | |
79 | company-research-agent | An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies using a multi-agent framework. It leverages Google Gemini 2.0 Flash and Chat GPT-4o-mini on the backend for inference. | 32 | |
80 | NativeChat | NativeChat is a powerful application designed to bring seamless, context-aware interactions to your mobile device. Using Gemini under the hood, it offers a wide range of features to assist with tasks like fetching system specs, analyzing call logs, summarizing SMS messages, and providing insights into your device’s status. NativeChat makes your cha | 32 | |
81 | peak-ai-agent-stack | RinAI agentic chat stack. Includes graphRAG memory, parallel tool calling, DeepSeek R1 powered web search, advanced LLM gateway and active context summarization. | 32 | |
82 | AIFoundry-DeepSeek-SDK | Notebooks to demo the use of Azure AI Python SDK / LangChain with DeepSeek R1 reasoning model in Azure AI Foundry. | 31 | |
83 | MCP-server-Deepseek_R1 | A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3) | 31 | |
84 | awesome-turkish-language-models | A curated list of Turkish AI models, datasets, papers | 30 | |
85 | DeepSeek-R1-AI-Voice-Agent | 26 | ||
86 | deepseek-r1-gsm8k | 26 | ||
87 | deepseek-local | Run DeepSeek R1 Locally with One Command! | 25 | |
88 | GRPO-Training | An overview of GRPO & DeepSeek-R1 Training with Open Source GRPO Model Fine Tuning | 24 | |
89 | art-prompt-system | AI绘画提示词生成器,AI绘画咒语生成,中文提示词工具,AI绘画助手,设计师AI工具,提示词优化器,AI作画提示词,智能提示词生成,提示词模板库,AI绘画教程,设计师工具,创作助手,提示词转换,AI艺术创作,新媒体配图工具,电商主图生成,商业设计工具,插画生成器,概念设计工具,人物肖像生成,AI Prompt Generator,Midjourney Helper,Stable Diffusion Tool,AI Art Assistant,Prompt Engineering,Design AI Tool,Art Prompt System,AI Drawing Guide,Prompt Template,Creative AI Assistant🔮🤖🚀 | 24 | |
90 | hobo-llm-from-scratch | From Llama to Deepseek, grpo/mtp implemented. With pt/sft/lora/qlora included | 24 | |
91 | awesome-deepseek-r1 | A collection on the recent reproduction papers and projects on DeepSeek-R1 | 24 | |
92 | FunctionCallBridge | 通过Prompt 让deepseek-r1 以及其他模型来支持函数调用 | 23 | |
93 | Guide-GRPO | Aims for memory-efficient training (24GB VRAM) on consumer GPUs. Optimizing language models through guidance tokens in reasoning chains, based on DeepSeekRL-Extended. | 23 | |
94 | LLaSE-G1 | LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement | 23 | |
95 | EnhancedBurpGPT | Enhanced BurpGPT 是一个强大的 Burp Suite 插件。通过分析指定的 HTTP 请求和响应,帮助安全测试人员更快速地发现潜在的安全漏洞。 | 21 | |
96 | sora-movie-module | READ THE README | 21 | |
97 | awesome-deepseek-r1-resource | This repo contains the resources for DeepSeek R1. | 21 | |
98 | StableDiffusionSharp | Use Stable Diffusion with C# | 20 | |
99 | LLM-AutoHotkey-Assistant | An AutoHotkey v2 application that utilizes OpenRouter.ai to seamlessly integrate Large Language Models into your daily workflow. Process texts with customizable prompts by pressing a hotkey and interact with multiple AI models simultaneously. | 20 | |
100 | DeepRetrieval | DeepRetrieval - Hacking Search Engines and Retrievers with LLM+RL | 20 |