Top Open Source AI Dev Influencers in February 2025

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.)
RankingsDevelopers
Related Project
Project intro
Star count
1

Fosowl

431 followers
Nice, France
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 account)
19.9K
2

dzhng

605 followers
-
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

zilliztech

698 followers
United States of America
deep-searcher
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
6.5K
4

om-ai-lab

682 followers
-
VLM-R1
Solve Visual Understanding with Reinforced VLMs
5.3K
5

StarsfieldAI

129 followers
-
R1-V
Witness the aha moment of VLM with less than $3.
3.8K
6

ThinkInAIXYZ

120 followers
-
deepchat
🐬DeepChat - A smart assistant that connects powerful AI to your personal world
3.6K
7

LearningCircuit

46 followers
-
local-deep-research
Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini) and includes benchmark tools to test on your own data. Searches 10+ sources - arXiv, PubMed, GitHub, web, and your private documents.
3.1K
8

ErlichLiu

167 followers
China / Chongqing
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! ✨
2.7K
9

AnotiaWang

65 followers
China
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

ravitemer

22 followers
India
mcphub.nvim
An MCP client for Neovim that seamlessly integrates MCP servers into your editing workflow with an intuitive interface for managing, testing, and using MCP servers with your favorite chat plugins.
1.2K
11

thu-pacman

195 followers
Beijing, China
chitu
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
1.2K
12

HazyResearch

1.3K followers
Palo Alto, CA
minions
Big & Small LLMs working together
1.1K
13

HiveNexus

10 followers
-
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。
1.0K
14

fdarkaou

56 followers
Everywhere
open-deep-research
An open-source alternative to OpenAI and Gemini's deep research.
782
15

bytebot-ai

16 followers
-
bytebot
Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, operating within a containerized Linux desktop environment.
779
16

TideDra

71 followers
Beijing, CN
lmm-r1
Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.
744
17

lmgame-org

35 followers
United States of America
GamingAgent
LLM/VLM gaming agents and model evaluation through games.
705
18

yaotingwangofficial

14 followers
-
Awesome-MCoT
Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey
677
19

pig-mesh

421 followers
-
deepseek4j
deepseek java sdk
668
20

wrtnlabs

82 followers
Korea, South
agentica
TypeScript AI Framework specialized AI Function Calling enhanced by compiler skills.
636
21

kuleshov-group

104 followers
-
bd3lms
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
525
22

turningpoint-ai

20 followers
United States of America
VisualThinker-R1-Zero
Explore the Multimodal “Aha Moment” on 2B Model
507
23

openai

99.5K followers
-
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
24

FareedKhan-dev

575 followers
Karachi, Pakistan
train-deepseek-r1
Building DeepSeek R1 from Scratch
471
25

Gen-Verse

80 followers
-
ReasonFlux
ReasonFlux Series - Open-source innovative LLM post-training algorithms focusing on data selection, reinforcement learning, and inference scaling
441
26

agiresearch

221 followers
United States of America
A-mem
A-MEM: Agentic Memory for LLM Agents
436
27

lmstudio-ai

9.2K followers
United States of America
lmstudio-python
LM Studio Python SDK
436
28

groundlight

58 followers
United States of America
r1_vlm
Build your own visual reasoning model
383
29

scraed

14 followers
-
LanPaint
High quality training free inpaint for every stable diffusion model. Supports ComfyUI
370
30

Flame-Code-VLM

10 followers
-
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
31

aws-samples

15.3K followers
-
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.
352
32

trueai-org

99 followers
-
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。
350
33

Aident-AI

5 followers
United States of America
open-cuak
Reliable Automation Agents at Scale
279
34

lechmazur

64 followers
-
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
35

umaru-233

28 followers
HongKong
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
36

MaxHastings

16 followers
-
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
37

sail-sg

591 followers
Singapore
oat-zero
A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.
222
38

iSegaro

1.0K followers
-
Translate-It
Chrome/Firefox extension for translating(Read/Write/Listen) from Any Languages to Any Languages using API of Google Gemini , OpenAi , OpenRouter and WebAi.
219
39

iidamie

2 followers
Huangshan
deepseek2api
DeepSeek 逆向 API
210
40

liyupi

18.9K followers
China Shanghai
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
41

JosefAlbers

32 followers
-
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
42

agentsea

140 followers
-
r1-computer-use
Applying the ideas of Deepseek R1 to computer use
198
43

MatthewZMD

223 followers
Ontario, Canada
aidermacs
Emacs AI Pair Programming Solution
187
44

ubergarm

62 followers
-
r1-ktransformers-guide
run DeepSeek-R1 GGUFs on KTransformers
152
45

SmallDoges

10 followers
China
small-doge
Doge Family of Small Language Model
151
46

deeppowers

27 followers
-
deeppowers
An open-source, high-performance inference accelerator engine supporting various large language models such as DEEPSEEK, GPT, GEMINI, and CLAUDE.
147
47

Ky0toFu

26 followers
Kyoto Japan
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
48

lucasjinreal

2.3K followers
Sanfancisco
Namo-R1
A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease.
133
49

lioensky

11 followers
-
GeminiMixSuper
基于DeepseekR1/Gemini2/GoogleVison2/GoogleSearch API实现的深度思考联网多模态大模型。
127
50

SynaLinks

51 followers
France
synalinks
🧠🔗 Graph-Based Programmable Neuro-Symbolic LM Framework - a production-first LM framework built with decade old Deep Learning best practices
127
51

GenerousMan

20 followers
Zhejiang, Hangzhou
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
52

Shaier

23 followers
-
arxiv_summarizer
This repository provides a Python script to fetch and summarize research papers from arXiv using the free Gemini API
112
53

mtkresearch

101 followers
-
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。
110
54

BinNong

80 followers
chengdu
deepseek-r1-llama-8b
fine-tune deepseek r1
103
55

beita6969

6 followers
云南
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
56

eai-lab

23 followers
Ulsan, South Korea
On-device-Sora
[arXiv] On-device Sora: Enabling Diffusion-Based Text-to-Video Generation for Mobile Devices
102
57

NanGePlus

188 followers
-
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
58

masterFoad

2 followers
-
NanoSage
Local LLM Powered Recursive Search & Smart Knowledge Explorer
96
59

Neph0s

88 followers
Shanghai
CoSER
Official Code for "Coser: Coordinating LLM-Based Persona Simulation of Established Roles"
95
60

DolbyUUU

3 followers
-
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
61

yunhaif

15 followers
-
reflect-vlm
Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation
80
62

FakeOAI

9 followers
-
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
76
63

deepseek-free

10 followers
-
deepseek-free
DeepSeek 部署教程 / 免费 API 接口 / 官方平替 / 入门指南【2025年7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。
68
64

dukeceicenter

1 followers
-
jailbreak-reasoning-openai-o1o3-deepseek-r1
67
65

GradientSpaces

57 followers
United States of America
ReStyle3D
[SIGGRAPH 2025] ReStyle3D: Scene-level Appearance Transfer with Semantic Correspondences
66
66

wonderNefelibata

1 followers
-
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.
65
67

ErickWendel

10.3K followers
São Paulo - Brazil
ollama-webui-traefik-docker
64
68

langgptai

308 followers
-
awesome-deepseek-prompts
Prompts for deepseek, deepseek R1
62
69

The-FinAI

97 followers
United States of America
Fino1
This is the repo of developing reasoning models in the specific domain of financial, aim to enhance models capabilities in handling financial reasoning tasks.
56
70

nathannlu

28 followers
Vancouver, BC
aperture
🔬 Visualize attention layers from Stable Diffusion
56
71

BenCaunt

62 followers
Cary, NC
MoondreamObjectTracking
Using the moondream VLM with optical flow for promptable object tracking
48
72

Azure-Samples

7.2K followers
Redmond, WA
microblog-ai-remix
A full-stack AI-powered microblogging application leveraging Azure Static Web Apps, Azure Functions, and Remix SSR with Azure OpenAI GPT-4o.
47
73

jbarnes850

21 followers
New York, New York
deepseek-r1-finetune
A step by step guide to fine-tuning the DeepSeek R1 Distilled models on Apple Silicon machines.
47
74

SreejanPersonal

127 followers
India
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
75

kaymen99

121 followers
Algeria
local-rag-researcher-deepseek
Local RAG researcher agent built using Langgraph, DeepSeek R1 and Ollama
44
76

YunwenTechnology

25 followers
-
Chinese-Data-Distill-From-R1
中文基于满血DeepSeek-R1蒸馏数据集
44
77

taylorwilsdon

26 followers
New York City
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
78

gabrielolympie

6 followers
-
moe-pruner
A repository aimed at pruning DeepSeek V3, R1 and R1-zero to a usable size
42
79

WispSnow

30 followers
China
GhostEscape
A survival game developed in C++ with SDL3 and glm
42
80

omaralalwi

226 followers
sana'a Yemen
laravel-py
interact with python in Laravel applications .
40
81

CJReinforce

17 followers
Beijing
PURE
SOTA RL fine-tuning solution for advanced math reasoning of LLM
38
82

kesimeg

19 followers
-
awesome-turkish-language-models
A curated list of Turkish AI models, datasets, papers
38
83

OJZen

72 followers
-
1chat
1chat is an iOS app that lets you chat with the DeepSeek-R1 model locally.
37
84

StarRing2022

20 followers
-
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
85

hanxunyu

6 followers
Hangzhou
Inst3D-LMM
[CVPR 2025] Official code repository for "Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning"
35
86

vlm2-bench

3 followers
-
VLM2-Bench
VLM^2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues
33
87

pogjester

1 followers
New York
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
88

dagmawibabi

466 followers
Addis Ababa, Ethiopia
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
89

dleerdefi

10 followers
-
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
90

LazaUK

30 followers
London, UK
AIFoundry-DeepSeek-SDK
Notebooks to demo the use of Azure AI Python SDK / LangChain with DeepSeek R1 reasoning model in Azure AI Foundry.
31
91

66julienmartin

1 followers
France
MCP-server-Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
31
92

smithakolan

338 followers
Vancouver, Canada
DeepSeek-R1-AI-Voice-Agent
26
93

Mryangkaitong

91 followers
-
deepseek-r1-gsm8k
26
94

umbertocappellazzo

8 followers
London
Llama-AVSR
[ICASSP 2025] Official Pytorch implementation of "Large Language Models are Strong Audio-Visual Speech Recognition Learners".
26
95

mischavandenburg

878 followers
-
deepseek-local
Run DeepSeek R1 Locally with One Command!
25
96

ALucek

991 followers
-
GRPO-Training
An overview of GRPO & DeepSeek-R1 Training with Open Source GRPO Model Fine Tuning
24
97

pen9un

46 followers
-
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
98

XU-YIJIE

5 followers
Shanghai
hobo-llm-from-scratch
From Llama to Deepseek, grpo/mtp implemented. With pt/sft/lora/qlora included
24
99

haoyangliu123

0 followers
-
awesome-deepseek-r1
A collection on the recent reproduction papers and projects on DeepSeek-R1
24
100

xuzeyu91

144 followers
hubei,wuhan
FunctionCallBridge
通过Prompt 让deepseek-r1 以及其他模型来支持函数调用
23