Top Open Source AI Dev Influencers in January 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

deepseek-ai

77.5K followers
-
DeepSeek-R1
90.2K
2

huggingface

50.4K followers
NYC + Paris
open-r1
Fully open reproduction of DeepSeek-R1
24.8K
3

bytedance

11.9K followers
Singapore
UI-TARS-desktop
A GUI Agent application based on UI-TARS(Vision-Language Model) that allows you to control your computer using natural language.
14.7K
4

Jiayi-Pan

1.3K followers
Bay Area, CA
TinyZero
Minimal reproduction of DeepSeek R1-Zero
11.9K
5

getAsterisk

142 followers
United States of America
deepclaude
A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthropic Claude models.
5.2K
6
YuE
YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open
4.2K
7

simstudioai

68 followers
-
sim
Sim Studio is an open-source AI agent workflow builder. Sim Studio's interface is a lightweight, intuitive way to quickly build and deploy LLMs that connect with your favorite tools.
4.0K
8

jina-ai

3.2K followers
Germany
node-DeepResearch
Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)
3.6K
9

hkust-nlp

261 followers
Hong Kong
simpleRL-reason
This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data
3.2K
10

MiniMax-AI

1.4K followers
-
MiniMax-01
The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention
2.9K
11

ammaarreshi

88 followers
-
Gemini-Search
Perplexity style AI Search engine clone built with Gemini 2.0 Flash and Grounding
1.9K
12

bodo-run

16 followers
-
yek
A fast Rust based tool to serialize text-based files in a repository or directory for LLM consumption
1.6K
13

sauravpanda

63 followers
San Francisco
BrowserAI
Run local LLMs like llama, deepseek-distill, kokoro and more inside your browser
1.1K
14

tech-shrimp

1.6K followers
-
gemini-playground
Deploy a Gemini multimodal chat website in 10 seconds, Severless! 只需准备一个Gemini API Key,10秒即可部署一个Gemini多模态对话的网站。
719
15

ggml-org

1.3K followers
United States of America
llama.vscode
VS Code extension for LLM-assisted code/text completion
704
16

exa-labs

204 followers
United States of America
exa-deepseek-chat
A simple open-source chat app that uses Exa's API for web search and Deepseek R1 for reasoning
693
17

CoderSJX

4 followers
-
AI-Resources-Central
Bringing together outstanding artificial intelligence (AI) open source projects from around the world.
656
18

lanesky

16 followers
Tokyo
thinking-gemini
451
19

harishsg993010

94 followers
-
LLM-Reasoner
Make any LLM to think like OpenAI o1 and deepseek R1
413
20

qunash

380 followers
Circassia
r1-overthinker
Force DeepSeek r1 models to think for as long as you wish
343
21

deepseek-php

59 followers
-
deepseek-laravel
Laravel wrapper for Deepseek PHP client, to seamless deepseek API integration with laravel applications.
337
22

andrewkchan

191 followers
San Francisco
deepseek.cpp
CPU inference for the DeepSeek family of large language models in C++
292
23

OpenMOSS

175 followers
China
SpeechGPT-2.0-preview
GPT-4o-level, real-time spoken dialogue system.
275
24

CNTRLAI

4 followers
-
Notate
Notate is a desktop chat application that takes AI conversations to the next level. It combines the simplicity of chat with advanced features like document analysis, vector search, and multi-model AI support - all while keeping your data private.
245
25

Rizwankaka

28 followers
-
deepseek-r1-chat
chatbot made with gradio using opensource deepseek-r1 running locally
230
26

MontrealAI

160 followers
Montreal
AGI-Alpha-Agent-v0
META‑AGENTIC α‑AGI 👁️✨ — Mission 🎯 End‑to‑end: Identify 🔍 → Out‑Learn 📚 → Out‑Think 🧠 → Out‑Design 🎨 → Out‑Strategise ♟️ → Out‑Execute ⚡
189
27

milanglacier

26 followers
-
minuet-ai.el
💃 Dance with LLM in Your Code. Minuet offers code completion as-you-type from popular LLMs including OpenAI, Gemini, Claude, Ollama, Llama.cpp, Codestral, and more.
177
28

hao-ai-lab

264 followers
United States of America
Dynasor
Simple extension on vLLM to help you speed up reasoning model without training.
153
29

DMontgomery40

9 followers
Denver, CO
deepseek-mcp-server
Model Context Protocol server for DeepSeek's advanced language models
153
30

xororz

9 followers
秋葉原
local-dream
Run Stable Diffusion on Android Devices with Snapdragon NPU acceleration. Also supports CPU inference.
145
31

ruvnet

1.4K followers
0x
SynthLang
SynthLang is a hyper-efficient prompt language designed to optimize interactions with Large Language Models (LLMs) like GPT-4o by leveraging logographical scripts and symbolic constructs.
144
32

liangyuwang

15 followers
-
zo2
ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory
121
33

xtekky

4.9K followers
Europe
deepseek4free
Deepseek V3 and R1 private API, deep thinking, search, full requests. pow challenge reversed. deepseek api.
115
34

go-deepseek

0 followers
-
deepseek
Go (Golang) client for Deepseek API. Deepseek Go supports DeepSeek-V3, DeepSeek-R1 and more
97
35

Kashif-E

355 followers
Islamabad
KOllama
A UI client for Ollama written in Compose Multiplatform focused on running Deepseek r1 locally
94
36

ai-decentralized

7 followers
United States of America
BloomBee
Decentralized LLMs fine-tuning and inference with offloading
88
37

OpenAgentPlatform

5 followers
Taiwan
Dive
Dive is an open-source AI Agent desktop application that seamlessly integrates any Tools Call-supported LLM with frontend MCP Server—part of the Open Agent Platform initiative.
83
38

justinlietz93

25 followers
Wisconsin, USA
agent_tools
Deepseek-R1 Tools and guide
83
39

Ingvarstep

41 followers
Kyiv, Ukraine
open-r1-text2graph
Open replication of DeepSeek R1 for text-to-graph extraction.
77
40

vllm-project

1.5K followers
-
vllm-ascend
Community maintained hardware plugin for vLLM on Ascend
74
41

hasan-py

165 followers
Dhaka, Bangladesh
chat-with-pdf-RAG
Chat with PDF using LangChain, Streamlit, Ollama (for LLM inference) and PDFPlumber. Overall which is an example of a Retrieval-Augmented Generation (RAG) system with Deepseek r1 model.
61
42

Azure-Samples

7.1K followers
Redmond, WA
azure-ai-agent-service-enterprise-demo
Demonstrates how to build a streaming enterprise agent using Azure AI Agent Service. This sample integrates local HR and company policy documents, Bing for external context, and GPT-4o (though the service is model-agnostic) to deliver real-time Q&A and automated workflows.
58
43

longevity-genie

33 followers
-
just-chat
Make your LLM agent and chat with it simple and fast!
57
44

dolmens

3 followers
-
gptel-aibo
An AI Writing Assistant for Emacs
56
45

Mohammadjafari80

17 followers
Tehran
GSM8K-RLVR
A simplified implementation for experimenting with Reinforcement Learning (RL) on GSM8K, inspired by RLVR and Deepseek R1. This repository provides a starting point for exploring RL-based reasoning.
51
46

lechmazur

63 followers
-
step_game
Multi-Agent Step Race Benchmark: Assessing LLM Collaboration and Deception Under Pressure. A multi-player “step-race” that challenges LLMs to engage in public conversation before secretly picking a move (1, 3, or 5 steps). Whenever two or more players choose the same number, all colliding players fail to advance.
49
47

Liao-Ke

0 followers
-
everyday
✨ 让经典名言焕发新生!基于LLM模型动态生成创意故事,用AI重新诠释金山每日一句的智慧结晶
49
48

paquino11

25 followers
Gothenburg, Sweden
chatpdf-rag-deepseek-r1
47
49

Ajmal0197

25 followers
New Delhi
DeepseekOllamaRag
Build a powerful AI-driven retrieval-augmented generation (RAG) system using Ollama and DeepSeek R1.
47
50

RManLuo

344 followers
Melbourne
gfm-rag
Graph Foundation Model for Retrieval Augmented Generation
46
51

jackfsuia

7 followers
-
nanoRLHF
RLHF experiments on a single A100 40G GPU. Support PPO, GRPO, REINFORCE, RAFT, RLOO, ReMax, DeepSeek R1-Zero reproducing.
46
52

harsh-vardhhan

55 followers
-
ai-agent-flight-scanner
AI agent to search Google Flights data
44
53

MaxiDonkey

87 followers
France
DelphiGenAI
The GenAI API wrapper for Delphi is designed to seamlessly integrate OpenAI's latest models (GPT-4o, o3, o4, and GPT-4.1), providing robust functionality for chat or response interactions for agents, text generation, vision processing, audio analysis, JSON configuration, web search, and asynchronous operations. Image generation with gpt-image-1
43
54

drive-bench

3 followers
-
toolkit
Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives
43
55

martinbowling

54 followers
Charleston, WV
thoughtful-claude
MCP server that enhances Claude's reasoning capabilities by integrating DeepSeek R1's advanced reasoning engine 🤔
42
56

aylar-ghezelbash

1.3K followers
-
awesome-deepseek
A curated list of projects related to deepseek
38
57

webhiveos

47 followers
-
WebHive
Meet WebHive, the AI-powered browser that takes care of tasks for you. No more endless clicks, tell it what you need, and it gets it done.
34
58

WavesMan

2 followers
-
DeepSeek-R1-Local-WebUI
DeepSeek-R1本地化WebUI运行
34
59

tensorwavecloud

7 followers
-
ScalarLM
ScalarLM - a unified training and inference stack
33
60

Recodify

3 followers
Bristol
deepseek-r1-local-docker
Run DeepSeek R1 models locally using Docker. Interact with the model through a browser-based UI or CLI using Ollama.
32
61

mbzuai-oryx

281 followers
-
AIN
AIN - The First Arabic Inclusive Large Multimodal Model. It is a versatile bilingual LMM excelling in visual and contextual understanding across diverse domains.
31
62

935963004

42 followers
-
NeuroLM
[ICLR 2025] NeuroLM: A Universal Multi-task Foundation Model for Bridging the Gap between Language and EEG Signals
31
63

thedevops-gpt

0 followers
-
devops-gpt
30
64

jondoescoding

28 followers
Jamaica
awesome-ai-agents
A collection of awesome web2 and web3 AI agents and workflows using OpenAI compatible LLMs.
30
65

Justmalhar

45 followers
San Fransisco, California
rsearch
AI-powered reasoning engine powered by DeepSeek R1 reasoning model to refine queries, synthesize data, and provide insightful research responses.
29
66

amrrs

1.0K followers
-
deepseek-r1-agent
Deepseek R1 Agent powered by LMStudio and Smolagents
28
67

WangQrkkk

0 followers
-
ThinkingCursor
A powerful tool for cursor through DeepSeek R1.(DeepSeek R1,o1,etc.)
26
68

fabiomatricardi

73 followers
Novara, Italy
Deepseek-R1-qwen1.5B
how to run DeepSeek-R1-Distill-Qwen-1.5B GGUF locally on your PC
25
69

Liu8Can

7 followers
-
CiscoPacketTracerChinese
高质量的思科模拟器汉化 CiscoPacketTracerChinese 通过使用智谱清言的 glm-4-plus 大模型 进行翻译,并结合后期人工矫正,达到了前所未有的汉化质量。
25
70

tripolskypetr

68 followers
The Internet
agent-swarm-kit
A TypeScript library for building orchestrated framework-agnostic multi-agent AI systems
24
71

fzn0x

527 followers
Indonesia
discord-deepseek-r1-bot
First-ever Discord Bot with Deepseek R1 (Runs locally or with API)
24
72

strangeloopcanon

40 followers
-
LLMRank
PageRank for LLMs
23
73

AstraZeneca

397 followers
Global
vlm
Official implementation for "Diffusion Instruction Tuning"
23
74

linq-rag

12 followers
United States of America
linqalpha-deepseek-r1-agent
Linq's Function Calling Agent utilizing DeepSeek-R1
23
75

AllAboutAI-YT

1.4K followers
-
local_deepseekr1
Running Deepseek R1 Local on Ollama
22
76

HarshJ23

7 followers
India
deepseek-claude-MCP-server
a MCP server which integrates reasoning capabilities of DeepSeek R1 model into claude desktop app.
22
77

The-Swarm-Corporation

163 followers
United States of America
AgentGym
A framework making it effortless to convert any llm model into a reasoning agent like o1 or DeepSeek's r1
20
78

XiaomingX

9.8K followers
japan
awesome-deepseek
deepseek可以用来做什么?这个项目给出的答案
19
79

oztrkoguz

78 followers
Turkey
SubtitleAI
An AI-powered tool for summarizing YouTube videos by generating scene descriptions, translating them, and creating subtitled videos with text-to-speech narration
17
80

john-carroll-sw

8 followers
-
coffee-chat-voice-assistant
Coffee Chat Voice Assistant is a voice-driven ordering system powered by Azure OpenAI GPT-4o Realtime API, simulating the experience of ordering coffee with a café barista. It supports natural conversations, live order updates, and real-time transcription, showcasing the power of AI for seamless customer interactions.
17
81

ZhengaoLi

3 followers
Florida State University
DISP-LLM-Dimension-Independent-Structural-Pruning
An implementation of the DISP-LLM method from the NeurIPS 2024 paper: Dimension-Independent Structural Pruning for Large Language Models.
17
82

HarbhagwanDhaliwal

12 followers
Punjab
Allora_HyperLiquid_AutoTradeBot
This repository provides an AI-powered trading bot leveraging AlloraNetwork for automatic trading on HyperLiquid decentralized exchange. The bot integrates predictive insights and customizable strategies for seamless trading. 🌟
17
83

khaidq97

2 followers
-
SimpleChatbot
Models: Deepseek R1 models, Llama3.2, Qwen2.5. Integrations: Ollama, Gradio. Supports Local LLM. Test and deploy the latest LLM models in the fastest and most efficient way
16
84

edoardoavenia

7 followers
-
deepseek-r1-gradio-env
Interactive environment to explore DeepSeek-R1 on Google Colab, featuring Gradio UI and LangChain pipelines, with Ollama as the model runtime.
16
85

Badim41

11 followers
-
network_tools
API | o1, gpt-4o, Claude 3.5 sonnet, command r+, Recraft v3, Dalle-3, Stable Diffusion, Flux, Kandinsky, Suno V4, Suno V3.5, Riffusion, Hailuo, TTS
15
86

siddharth-Kharche

278 followers
pune
Multi-Agent-AI-Researcher-Powered-by-DeepSeek-R1
14
87

HudsonGri

3 followers
Gainesville, FL
llm-os-agent
LM Agent for Operating Systems Course Assistance
14
88

java-ai-tech

1 followers
-
spring-ai-summary
SpringAI,LLM,MCP,Embedding
14
89

cyanheads

12 followers
Seattle, WA
mentor-mcp-server
A Model Context Protocol server providing LLM Agents a second opinion via AI-powered Deepseek-Reasoning R1 mentorship capabilities, including code review, design critique, writing feedback, and idea brainstorming through the Deepseek API.
13
90

JeongHun0716

9 followers
-
MMS-LLaMA
Official PyTorch implementation for "MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens"
13
91

aws-samples

15.1K followers
-
nki-llama
12
92

lmstudio-ai

9.0K followers
United States of America
docs
LM Studio App and Developer Docs
12
93

meta-llama

8.8K followers
-
llama-stack-ops
Ops files for https//github.com/meta-llama/llama-stack
12
94

Gager-Git-life

10 followers
china
llm_sts
一个基于WebSocket和LLM的实时语音对话系统,集成了语音识别(ASR)、大语言模型(LLM)和语音合成(TTS)功能。
12
95

Emericen

7 followers
Mountain View
deepseek-r1-distilled
DeepSeek R1 distilled into smaller OSS models
12
96

manu-mishra

5 followers
-
DeepSeekR1onAmazonBedrock
Deploy Amazon DeepSeek R1 Models on Amazon Bedrock
12
97

shareAI-lab

17 followers
China
Super2Brain-Extension
强大的浏览器插件,支持deepseek r1直接以侧边栏的形式和页面进行交互。
12
98

miccunifi

41 followers
Firenze - Viale Morgagni 65 - Italia
Cross-the-Gap
[ICLR 2025] - Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion
11
99

soralabs

79 followers
-
hana
Hana is an AI agent built with the Zen package.
11
100

fedify-dev

16 followers
-
fedichatbot
An LLM-powered chatbot for fediverse. A tech demo for BotKit.
11