Top Open Source AI Dev Influencers in June 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

BeehiveInnovations

24 followers
-
zen-mcp-server
The power of Claude Code + [Gemini Pro / Flash / O3 / Grok / OpenRouter / Ollama / Custom Model / All Of The Above] working as one.
2.1K
2

tbphp

8 followers
China
gpt-load
一个高性能的OpenAI格式API多密钥轮询代理服务器,支持负载均衡,使用 Go 语言开发。A high-performance OpenAI-compatible API proxy server with multi-key rotation and load balancing, built with Go.
177
3

yezanting

7 followers
-
Med-VLM-Bench-Summary
A Curated Benchmark Repository for Medical Vision-Language Models
105
4

herobot-id

4 followers
Indonesia
herobot
Herobot is your 24/7 customer service assistant that helps you manage multi-channel customer conversations effortlessly.
55
5

ShadowHackrs

190 followers
jordan
Jailbreaks-GPT-Gemini-deepseek-
Jailbreaks GPT, Sora, Claude, Gemini ,deepseek this prompt unlocks rage mode
47
6

SmythOS

12 followers
United States of America
sre
The Operating System for Agents
41
7

alphadl

213 followers
Shanghai(CN) & Sydney(AU)
R1
🚀enhanced GRPO with more verifiable rewards and real-time evaluators
35
8

AlenjandroWang

5 followers
Shanghai
ASVR
Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better
29
9

MigoXLab

1 followers
-
LMeterX
Professional Load Testing for Any OpenAI-Compatible LLM API
24
10

FareedKhan-dev

557 followers
Karachi, Pakistan
google-veo3-from-scratch
A Step-by-Step Implementation of Google Veo 3 Architecture from Scratch
21
11

KodyKendall

26 followers
San Francisco
llama_bot_rails
19
12

astack-tech

2 followers
China
astack
🤖 A composable framework for building AI applications.
13
13

R-Dson

6 followers
-
llamate
A simple, "Ollama-like" tool for managing and running GGUF language models from your terminal.
12
14

infosecn1nja

2.5K followers
Jakarta, Indonesia
TTPMapper
TTPMapper is an AI-driven threat intelligence parser that converts unstructured reports whether from web URLs or PDF files into structured intelligence. Using the DeepSeek LLM, it extracts MITRE ATT&CK techniques, IOCs, threat actors, and generates contextual summaries.
11
15

DrHazemAli

405 followers
Los Angeles, CA
AzureSoraSDK
C# SDK for Azure Sora
8
16

waylaidwanderer

357 followers
-
gemini-plays-pokemon-public
6
17

aimlBysoham

0 followers
Mumbai, India
Multi-VLM-Processing-Server
A FastAPI-based application that processes images using multiple Vision Language Models (VLMs) to answer to user query.
5
18

lum3on

31 followers
-
ComfyUI-StableAudioX
A powerful audio generation extension for ComfyUI that integrates AudioX models for high-quality audio synthesis from text and video inputs.
5
19

roryp

141 followers
Johannesburg
sora
A Java Spring Boot web application that generates Sora videos using Azure OpenAI API. This application provides a user-friendly web interface for creating AI-generated videos with configurable video specifications including resolution and duration.
4
20

Luiz-Alcantara

0 followers
-
Neural-Pixel
A simple GUI wrapper for stable-diffusion.cpp written using C and GTK 4.
4
21

fatsnk

0 followers
-
forksilly.doc
ForkSilly的文档。ForkSilly:兼容sillytavern V2角色卡(png)、世界书、正则、预设的安卓应用
4
22

oyxning

2 followers
Shanghai
astrbot_plugin_antipromptinjector
AstrBot 插件,用于检测和管理大型语言模型 (LLM) 的输出。它能帮助你识别和响应 LLM 生成的特定内容,确保其输出符合你的预期和安全标准。通过此插件,你可以更好地控制 LLM 的行为,避免不希望出现的信息。
4
23

agentsea

140 followers
-
uvg
unsloth vlm grpo
3
24

s1monFu

6 followers
-
self-preference-activation-steering
finding a self-preference vector in Llama-3.1-8B-Instruct residual stream activations
3
25

Zengwula

0 followers
-
Light-R1-ZERO
DeepSeek R1-zero轻量级复现
3
26

ugo-emekauwa

9 followers
NC
private-ai-setup-dream-guide
The Private AI Setup Dream Guide for Demos automates the installation of the software needed for a local private AI setup, utilizing AI models (LLMs and diffusion models) for use cases such as general assistance, business ideas, coding, image generation, systems administration, marketing, planning, and more.
3
27

davidkimai

15 followers
-
langtons-emergence
Recently I have been researching emergent complexities through first principles reductionism of Langton's Ant in the hopes that they could potentially offer insights into the emergent intricacies of frontier large language models.
3
28

mercuryVM

16 followers
Brazil
econosim
🎓 Simulador interativo desenvolvido como trabalho final da disciplina ACH2063 — Introdução à Administração e Economia para Computação (USP). O EconoSim permite que alunos tomem decisões fiscais e monetárias em tempo real e visualizem os impactos sobre o modelo IS-LM de forma dinâmica e colaborativa.
3
29

statikfintechllc

43 followers
Junction City, Kansas
GodCore
All-in-one local AI stack for Mistral-13B and Llama.cpp, with one-step CUDA wheel install, OpenAI-compatible API, and modern web dashboard. Switch between local and cloud chat, run on your own GPU, and deploy instantly—no API keys or paywalls. Designed for easy install, custom builds, and fast remote access. Enjoy!
3
30

Daniel-Sogbey

51 followers
Accra, Ghana
llm_log_pipeline
Containerized Go service that uses LLMs (e.g., LLaMA 3.1 Instruct) to analyze backend logs via RabbitMQ and store structured insights in PostgreSQL
3
31

koshiroquoc

0 followers
-
DaNangtourguide
This is a Rag-LLM chatbot demo for tour guide in Da Nang
3
32

technion-cs-nlp

18 followers
-
vlm-circuits-analysis
Code for the experiments and websites of the paper "Same Task, Different Circuits"
2
33

chinese-chatgpt

1 followers
-
chatgpt-sites
ChatGPT 中文版:国内ChatGPT镜像网站整理合集(支持 GPT-4、GPT-4o、o1、o3及Claude 4 Sonnet、Gemini 2.5 Pro、Grok3,无需翻墙)【6月持续更新】ChatGPT 中文版是基于 OpenAI 的 ChatGPT 模型开发的中文使用版本,专为中文用户,提供更流畅、更精准的智能AI对话。全面体验 ChatGPT 中文版,无需翻墙,支持 GPT-4、GPT-4o、o1、o3 和本地化功能。本项目提供一站式的 ChatGPT中文版使用指南,包括国内可用的 ChatGPT镜像网站,帮助快速上手,无论是个人使用还是专业需求,均可无限使用 GPT-4、GPT-4o、o1、o3及Claude 4 Sonnet、Gemini 2.5 Pro、Grok3~
2
34

IzzulGod

0 followers
-
Sorachio-Chat
Sorachio - AI Assistant
2
35

JMcrafter26

44 followers
<- This is a pin
sora-modules
My collection of Sora Modules
2
36

MethodCa

1 followers
-
HFH_LMS
Habitad for humanity LMS from from zero.
2
37

arthurcolle

14 followers
-
lmstudio.ex
2
38

shivamsingh96

19 followers
-
-AI-Powered-Mental-Health-Chatbot-using-LangChain-Groq-Gradio
A compassionate, context-aware mental health chatbot built using PDF-based knowledge, vector search (ChromaDB), HuggingFace embeddings, and LLaMA 3-70B via Groq API. The interface is designed with Gradio for a friendly, chat-like user experience.
2
39

TianmuTNT

13 followers
Location().get()
awesome-digital-lifestyle
🎉收录精选数字服务资源:虚拟信用卡、AI 工具、云服务器、开发者神器与数字生活必备服务等等... 数字生活,虚拟信用卡,海外充值,chatgpt,ai工具推荐,云服务器,vps推荐,minecraft开服,服务器推荐,免费资源,自托管,免费vps,免费ai,数字工具,雨云,海外手机号,数字游民,推荐合集,优惠推荐,开发者资源
2
40

moxin-org

67 followers
-
Moxin-VLM
Moxin-VLM: Designed for advanced Vision-Language understanding and interaction, built upon the Moxin-LLM backbone
2
41

cardinal123456

0 followers
-
3DGS-for-Chinese-Heritage-Structures
Stable Diffusion-Enhanced 3D Gaussian Splatting for Efficient Neural Reconstruction of Chinese Heritage Structures
2
42

dshinek

6 followers
-
SynMirror
A dataset for studying the semantic differences between synthetic and natural images, generated from shared captions using Stable Diffusion, SDXL, and Infinity models.
2
43

GitRectify

3 followers
Cary , NC
open-compass
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
2
44

kirainy

0 followers
Wuhan, China
GLMDeepSeaAgents
Data-driven multi-agent ecosystem for autonomous decision-making in GLM深远海船舶应用赛
2
45

Patates4

0 followers
-
sd-webui-frequency-separation
# 🌊 Frequency Separation Extension for WebUIEnhance your Stable Diffusion outputs by processing images in three layers: low, mid, and high frequencies. This method produces sharper and more detailed renders, making your images stand out. 🛠️
2
46

Maxfynn

1 followers
-
Foundation-Models-Playgrounds
Explore the Foundation Models Playgrounds repository to see how to engage with Apple's Foundation Models through Swift. Each playground offers clear examples, from simple chats to dynamic storytelling. 🛠️📚
2
47

samrylanjamesharris

3 followers
New Zealand
NexusLLM
An LLM focused on running locally.
2
48

Masoudabdul

0 followers
-
webintel
WebIntel is an advanced web intelligence system that delivers real-time insights and analysis. 🚀 It leverages cutting-edge AI technology to enhance your web research experience. 💻
2
49

mediaexplorer74

170 followers
Moscow, Russia
TraeToDo
Experimental project... simplest "Deepseek-like" UWP app created with (in) Trae Ai service for my old sweet Windows Family devices! ;)
2
50

Kunlunxin-AD

5 followers
-
Awesome-XPU-Autonomous-Driving
A comprehensive list of state-of-the-art papers in autonomous driving and robotics, covering end-to-end (e2e) learning, vision-language models (VLM), vision-language-action models (VLA), world models, and reinforcement learning (RL), with links to papers, code repositories, and relevant websites.
2
51

lightfastai

1 followers
-
chat
An open-source, production-ready AI chat application featuring Claude Sonnet 4, GPT-4o, real-time messaging, and modern UI. Built with Next.js 15, Convex, and TypeScript.
2
52

asimov-platform

50 followers
Switzerland
llama-index-asimov
LlamaIndex integration with the ASIMOV Platform.
2
53

caixiaoshun

3 followers
-
DaiyuLM
2
54

Natxo09

3 followers
Spain
Eris.
Eris is a private AI chat application that runs entirely on your device using Apple's MLX framework. Named after the dwarf planet that challenged our understanding of the solar system, Eris challenges the notion that AI must live in the cloud.
2
55

RahulSChand

39 followers
-
chess_vlm
1
56

eformat

86 followers
Australia
agentic-llamastack
1
57

ictnlp

232 followers
Beijing, China
Stream-Omni
Stream-Omni is an end-to-end language-vision-speech chatbot that simultaneously supports interaction across various modality combinations.
1
58

ljleb

54 followers
Unknown Space-Time Coordinates
time_embed_fix
Fix for SDXL merges that generate grey images.
1
59

PRITHIVSAKTHIUR

54 followers
India
Qwen2.5-VL-Video-Understanding
The Qwen2.5-VL-7B-Instruct model is a multimodal AI model developed by Alibaba Cloud that excels at understanding both text and images. It's a Vision-Language Model (VLM) designed to handle various visual understanding tasks, including image understanding, video analysis, and even multilingual support.
1
60

Kazuhito00

714 followers
Aichi, Japan
Kimi-VL-Colaboratory-Sample
Colaboratory上でKimi-VLをお試しするサンプル
1
61

aka-Harsh

8 followers
Bangalore
AI-Image-Generator
Multi-model AI art generator utilizing Stable Diffusion with GPU acceleration, AWS cloud storage, and Polygon NFT minting. Designed with Gradio & Web3.
1
62

Debapriya-source

13 followers
-
tax-buddy
Agentic RAG chatbot for Indian TAX related QnAs
1
63

thisisiron

30 followers
Seoul, South Korea
vision-token-calculator
🧮 A calculator for vision tokens in VLMs.
1
64

chatgpt-chinese

3 followers
-
chatgpt_site
ChatGPT 中文版:免费 ChatGPT镜像网站推荐(支持 GPT-4.1、GPT-4o及o1、o3、o4,无需翻墙)【6月最新】
1
65

kuc-arc-f

22 followers
-
rolldown_2ex
rolldown-vite , fullstack example
1
66

china-chatgpt-gpt

0 followers
-
ChatGPT-site
ChatGPT 中文版【国内免费直连】(支持 GPT-4、GPT-4o,无需翻墙)【2025年6月最新更新】
1
67

SeriousRasCode

6 followers
-
examnote
A deepseek based note summeriser for exam preparation, currently allows only pasting the text to be summerised. Openrouter is used for free deepseek r1 api key.
1
68

syedbilalalam1

625 followers
Karachi
StableDiffusion-WebUI
The fixed version of the StableDiffusion WebUI. 6/20/2025.
1
69

chatgpt-china-cn

0 followers
-
ChatGPT-CN
ChatGPT 中文版:免费直连指南(支持 GPT-4o、GPT-4、o1、o3 和 Claude4、Gemini 2.5 Pro,国内无需翻墙)【2025年6月最新】
1
70
chatgpt_site
ChatGPT 中文版:国内ChatGPT镜像网站汇总合集(支持GPT-4、GPT-4o、o1、o3及Claude 4 Sonnet、Gemini 2.5 Pro、Grok3,无需翻墙)【6月持续更新】ChatGPT 中文版是基于 OpenAI 的 ChatGPT 模型开发的中文使用版本,专为中文用户,提供更流畅、更精准的智能AI对话。全面体验 ChatGPT 中文版,无需翻墙,支持 GPT-4、GPT-4o、o1、o3 和本地化功能。本项目提供一站式的 ChatGPT中文版使用指南,包括国内可用的 ChatGPT镜像网站,帮助快速上手,无论是个人使用还是专业需求,均可无限使用 GPT-4、GPT-4o、o1、o3及Claude 4 Sonnet、Gemini 2.5 Pro、Grok3~
1
71

MedAI-UAIX

4 followers
-
SonoVLM
A multimodal AI system for ultrasound analysis with capabilities in cross-organ understanding, abnormality detection, diagnostic reasoning, structured reporting, and patient-centric dialogue.
1
72

Xiang196

0 followers
-
XiangSora_Note
一个高中各科笔记汇总~
1
73
chatgpt-site
ChatGPT 中文版 :国内最简单的ChatGPT教程指南(支持GPT-4/4o,无需翻墙)【2025年最新更新】
1
74

DavidBatkay

7 followers
-
Chat-DVB_AI
Vibe Coding an AI Chat app running ollama deepseek-r1 locally
1
75

nibzard

51 followers
Split, Croatia
lmdb-tui
1
76

xtremislv

2 followers
Kuchaman City
LMM-ConceptExplainer-VQA
A concept-based explainability framework applied to large multimodal models (LMMs) using the VQAv2-small dataset.
1
77

SurabhiSupriya

0 followers
-
Smart_QA_RAG
SmartQA is a hybrid Q&A system that uses BERT for fast similarity matching and LLaMA 3 for generating intelligent answers. It stores Q&A pairs locally, learns from user feedback, and offers both CLI and Streamlit-based UI.
1
78

arjun2004

7 followers
Kerala,India
edu-llama
1
79

yunxiao11xie

2 followers
-
chengyu_finetuneing
this is a test for fine_tuening deepseek r1 7b t
1
80

marisdarmawan

1 followers
DKI Jakarta
genai
I create a website using Streamlit to deploy gen AI model based on Deepseek R1
1
81

titanefe

0 followers
-
Local-RAG-Projects
I am a 16 year old working on some Local Ollama RAG Project mostly with deepseek-r1. I would really appreciate if you could check out my work, improve it and also help me on localhost web designs for my projects! Thank You!
1
82

march-7th-mini

0 followers
-
march-7th-mini.github.io
0代码基础的小三月,完全使用deepseek-R1对话搭建的音乐可视化播放器。有不少跟随音乐节奏律动的元素(●'◡'●)
1
83

dragonpilee

5 followers
-
ScholarMate
ScholarMate is an intelligent tutoring platform that leverages advanced AI technology . Powered by the DeepSeek-R1
1
84

Dolwer

0 followers
-
https-github.com-Dolwer-Post_Telegram_RAG_LM_Studio_World_1
1
85

Mzs786

7 followers
-
Learning-Management-System-LMS
1
86

mrhunsaker

10 followers
Farmington, UT
Granite_NotebookLM
NotebookLM Clone in java 17, Apache tools, and Granite LLM Models
1
87

AbdulRehman-18

1 followers
-
LMS-mini-project
1
88

Dodge100

4 followers
-
llama-engineer
Free Deep Research models with Ollama
1
89

Omkar998

3 followers
California
AI-Powered-Mock-Interviewer
An interactive AI-powered mock interview tool that simulates real interviews using LLaMA 3, Mistral, T5, and DeepSeek. Supports voice-based Q&A, gives instant feedback, and adapts to your skill level. Built with Django, Next.js, and AWS your smart prep buddy for job interviews.
1
90

lukeslp

10 followers
Santa Barbara
llamaherder
CLI AI use with ollama
1
91

jainer

0 followers
-
llamas
1
92

siminzheng

0 followers
-
train_llama
手动训练一个Llama3模型的简单示例
1
93

zephisti

0 followers
North Carolina, USA
rag-memory-llama
1
94

MituuZ

0 followers
Finland
silent-llama
1
95

FakeDefender

0 followers
-
a-simple-ai-trading-system
AI驱动的量化交易策略系统 - 基于多智能体协作的智能交易平台(基于deepseek-R1)
1
96

Jay-Gemining

0 followers
-
New_KnowmeLM
1
97

black-roland

30 followers
Bir Tawil
homeassistant-cloud-ru-ai
Cloud.ru Foundation Models — cloud-based AI assistants for Home Assistant
1
98

Ayush-ds-phy

0 followers
-
InsightGenie
A smart tool that reads various file formats (CSV, Excel, PDF, DOCX, images), visualizes data using charts and heatmaps, and generates insights and summaries using the LLaMA-4 model via the Together API. It automates data analysis and document understanding with AI-driven recommendations.
1
99

nikhilitz

0 followers
-
data_analyst_agent
Data Analyst Agent is an AI-powered Streamlit application that automates exploratory data analysis (EDA) using large language models. Simply upload your dataset (CSV, Excel, PDF, DOCX, or TXT), ask questions in natural language, and receive detailed answers, visualizations, and suggestions—all generated intelligently by LLaMA-4 through the Together
1
100

realblehhguh

0 followers
Earth
modal-vllm-server
🚀 Run LLMs on Modal with vLLM!
1