Top Open Source AI Dev Influencers in April 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

google

55.9K followers
United States of America
adk-python
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
10.1K
2

AsyncFuncAI

98 followers
United States of America
deepwiki-open
Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme
7.0K
3

jamez-bondos

109 followers
-
awesome-gpt4o-images
Awesome curated collection of images and prompts generated by GPT-4o and gpt-image-1. Explore AI generated visuals created with ChatGPT and Sora, showcasing OpenAI’s advanced image generation capabilities.
6.4K
4

VoltAgent

62 followers
United States of America
voltagent
Open Source TypeScript AI Agent Framework
2.2K
5

OmniSVG

20 followers
-
OmniSVG
OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from simple icons to intricate anime characters.
1.8K
6

River-Zhang

109 followers
Cambridge, MA
ICEdit
Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Training released! Surpasses GPT-4o in ID persistence! Official ComfyUI workflow release! Only 4GB VRAM is enough to run!
1.7K
7

stepfun-ai

885 followers
-
Step1X-Edit
A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.
1.4K
8

liweiphys

16 followers
CN
layra
LAYRA—an enterprise-ready, out-of-the-box solution—unlocks next-generation intelligent systems powered by visual RAG and limitless visual multi-step agent workflow orchestration.
728
9

ModelEngine-Group

315 followers
-
nexent
Nexent 是一个可以零代码开发智能体的平台 —— 无需编排,无需复杂拖拉拽。基于 MCP 工具生态,Nexent 还提供强大的模型集成、数据处理、知识库管理能力。
609
10

cafferychen777

93 followers
-
mLLMCelltype
An iterative multi-LLM consensus framework for accurate cell type annotation in single-cell RNA-seq data
531
11

NousResearch

881 followers
-
atropos
Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments
414
12

mengxi-ream

54 followers
Vancouver
read-frog
🐸 Read Frog - Open Source Immersive Translate | 🐸 陪读蛙 - 开源沉浸式翻译
283
13

policy-gradient

0 followers
-
GRPO-Zero
Implementing DeepSeek R1's GRPO algorithm from scratch
281
14

google-ai-edge

1.8K followers
-
LiteRT-LM
231
15

kizuna-ai-lab

0 followers
-
sokuji
Live speech translation application built with Electron 34 and React, using OpenAI's Realtime API.
219
16

Stream29

13 followers
-
ProxyAsLocalModel
Proxy remote LLM API as Ollama and LM Studio, for using them in JetBrains AI Assistant
101
17

daily-co

111 followers
-
pcc-groq-llama
Voice AI agent starter kit with Groq, Llama 4, and (optionally) Twilio
68
18

lucas-ventura

28 followers
-
chapter-llama
Official PyTorch implementation of the paper "Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs"
59
19

Nutlope

6.8K followers
New York City, NY
smartpdfs
Summarize PDFs into beautiful sections with Llama 3.3
57
20

Azure-Samples

7.1K followers
Redmond, WA
eShopLite
eShopLite is a set of reference .NET applications implementing an eCommerce site with features like Semantic Search, MCP, Reasoning models and more.
50
21

llm-d

243 followers
United States of America
llm-d-deployer
Helm charts for llm-d
42
22

tarun7r

14 followers
Hyderabad
Vocal-Agent
A cutting-edge voice assistant combining real-time speech recognition, AI reasoning, and neural text-to-speech capabilities.
38
23

tsunghan-wu

61 followers
Berkeley, CA
reverse_vlm
🔥 Official implementation of "Generate, but Verify: Reducing Visual Hallucination in Vision-Language Models with Retrospective Resampling"
34
24

mgreen27

180 followers
Sydney
mcp-velociraptor
VelociraptorMCP is a Model Context Protocol bridge for exposing LLMs to MCP clients.
31
25

TH3Psycho

0 followers
-
cursor-free-vip
[Support 0.48.x](Reset Cursor AI MachineID & Auto Sign Up / In & Bypass Higher Token Limit)自动注册 Cursor Ai ,自动重置机器ID , 免费升级使用Pro功能: You've reached your trial request limit. / Too many free trial accounts used on this machine. Please upgrade to pro. We have this limit in place to prevent abuse. Please let us know if you believe this is a mistake.
30
26

Joy-Marchattiwar

0 followers
-
AI-NoteMaker
NoteCraft is a full-stack web app built with Django, Celery, and Next.js that lets users upload academic PDFs, generate AI-powered notes, and retrieve relevant content using RAG. It's optimized for long documents, supports async processing, and runs fully containerized with Docker.
29
27

alimohammadiamirhossein

43 followers
Vancouver
cora
✨ PyTorch implementation of "Cora: Correspondence-aware Image Editing Using Few-Step Diffusion", accepted at SIGGRAPH 2025.
23
28

pinkpixel-dev

8 followers
United States of America
MCPollinations
A Model Context Protocol (MCP) server that enables AI assistants to generate images, text, and audio through the Pollinations APIs. Supports customizable parameters, image saving, and multiple model options.
23
29

BeautyyuYanli

293 followers
-
tooluser
Enable tool-use ability for any LLM model (DeepSeek V3/R1, etc.)
20
30

whitecircle-ai

6 followers
France
circle-guard-bench
First-of-its-kind benchmark for evaluating the protection capabilities of large language model (LLM) guard systems
19
31

globlord

1 followers
-
AIstudioProxyAPI
Node.js+Playwright服务器,通过模拟 OpenAI API 的方式来访问 Google AI Studio 网页版,服务器无缝交互转发gemini模型对话。这使得兼容 OpenAI API 的客户端(如 Open WebUI, NextChat 等)可以使用 AI Studio 的无限额度及能力。经测试因无法绕过自动化检测故暂不支持无头模式启动实例-自用项目随缘维护
19
32

shibing624

2.2K followers
Beijing, China
thinking-intervention
Used for thinking process intervention of reasoning models such as DeepSeek-R1, effectively controlling the reasoning thinking process. 用于DeepSeek-R1等推理模型的思维过程干预,有效控制推理思考过程
18
33

tattn

155 followers
Tokyo, Japan
LocalLLMClient
Swift local LLM client for iOS, macOS, Linux
18
34

containers

4.9K followers
Earth
ramalama-stack
An external provider for Llama Stack allowing for the use of RamaLama for inference.
16
35

techcow2

31 followers
-
LMSA
A powerful Android app that connects to LM Studio running on your computer, allowing you to chat with your favorite AI models from your mobile device.
16
36

kenantang

17 followers
Santa Barbara, CA
spice
SPICE: A Synergistic, Precise, Iterative, and Customizable Image Editing Workflow
14
37

VERMAXVR

0 followers
-
awsome_kali_MCPServers
awsome kali MCPServers is a set of MCP servers tailored for Kali Linux, designed to empower AI Agents in reverse engineering and security testing. It offers flexible network analysis, target sniffing, traffic analysis, binary understanding, and automation, enhancing AI-driven workflows.
14
38

SiyuWang0906

1 followers
-
CAD-GPT
[AAAI2025] CAD-GPT: Synthesising CAD Construction Sequence with Spatial Reasoning-Enhanced Multimodal LLMs
12
39

Ownned3389

1 followers
-
Gen-AI-Virtual-Try-On-Clothes
Gen AI-Powered Virtual Try-On Clothes Platform Upload any model and garment image to preview realistic try-on results instantly. Built with Google Gemini, FastAPI, and React. Ideal for fashion, retail, and e-commerce.
11
40

microsoft

95.1K followers
Redmond, WA
BUILD25-LAB331
This repository hosts the instructions and workshop materials for Lab 331 (Deep Research with Langchain and DeepSeek R1) for Microsoft Build
10
41

sammcj

274 followers
Melbourne, Australia
agentic-coding
Agentic Coding Rules, Templates etc...
9
42

Techiral

28 followers
India
OmniMind
OmniMind: An open-source Python library for effortless MCP (Model Context Protocol) integration, AI Agents, AI workflows, and AI Automations. Plug & Play AI Tools for MCP Servers and Clients, powered by Google Gemini.
9
43

headlinesquare

0 followers
-
headlinesquare-home
The home of HeadlineSquare and Dr. Headline. HeadlineSquare is a public square for US news headlines, fully powered by Dr. Headline, an autonomous AI agent who applies academic neutrality and rigor to news curation.
9
44

gpt4free

28 followers
-
gpt4free.github.io
9
45

LMCache

84 followers
-
LMBenchmark
8
46

R-Dson

6 followers
-
llama-server-cli.py
A simple, user-friendly CLI tool for managing, and running, llama.cpp's llama-server with multiple configuration profiles and providing OpenAI-compatible API access.
7
47

DennisDRX

0 followers
-
Faraday-Web-Researcher-Agent
Faraday: An Autonomous Web Research Agent (LangGraph/Streamlit). 🕵️♀️ Investigates queries using dynamic tools (Tavily, Google, NewsAPI, etc.), gathers multi-source info, and synthesizes structured reports in a Streamlit UI. Features agentic workflow & source tracking.
7
48

LiehSt

0 followers
-
Streaming-Avatar
🌟 Full-stack app for real-time avatar streaming with HeyGen & Gemini AI. Built with React, TypeScript, Express, and Tailwind during a hackathon by Team "Bit by Bit"
7
49

AbuFar1s

0 followers
-
SunoBot
SunoBot — a personalized, generative audio companion designed to boost user engagement through interactive storytelling and voice-based experiences.
7
50

Spac5y

0 followers
-
Vocal-Agent
A cutting-edge Cascading voice assistant combining real-time speech recognition, AI reasoning, and neural text-to-speech capabilities.
6
51

zhuolhc

10 followers
江苏苏州
recounter
在Mac上记录您在任何应用打下的字与您剪切板的内容并在本地通过ollama DeepSeek-r1分析。Reminding all the words you have typed for Macbook and analysis with ollama Deepseek-r1
5
52

hexart

13 followers
China
prompt-booster
Prompt Booster: A comprehensive tool for optimizing LLM prompts with version control, A/B testing, and template management. Supports multiple AI providers (OpenAI, Gemini, DeepSeek, Qwen, etc.) across web and desktop platforms. Increase your AI prompt effectiveness with professional engineering tools.
5
53

Creature-112

1 followers
-
gemini-live
This project enables real-time streaming of audio (and optionally video or screen captures) from your local device to Google Gemini using the Live API. It allows you to interact with Gemini through both text and voice, supporting conversational AI responses.
5
54

imrightguy

0 followers
-
CloudToLocalLLM
5
55

papersgpt

12 followers
-
chatpdflocal
A chat pdf app on MacOS, keeping your data safe, handling massive documents, and connecting you with SOTA AI models
4
56

flerk3n

2 followers
Delhi, India
Llama-360
An AI-Powered Multi-Agent Solution for Retail Banking Products.
4
57

openconstruct

4 followers
VA
llamaedit
code editor with completion powered by llamacpp
4
58

kojix2

123 followers
Japan
llama.cr
4
59

BlueCarrot1

0 followers
-
Logo-Detection
use florence model for few shot special logo detection; iou reward training with grpo for florence and VLMs
4
60

reynaldopapi

0 followers
-
SystemProbe
an AI-powered desktop application designed to help users discover and optimize system prompts for Large Language Models (LLMs) without requiring complex fine-tuning or LoRA training.
4
61

hoangtuanhehehehhe

0 followers
-
AgentVault
"Open-source toolkit (Python Library, Registry API, CLI) for secure, decentralized AI agent interoperability using A2A/MCP."
4
62

LovaRajuMCA

0 followers
-
MCP-Security-Checklist
A comprehensive security checklist for MCP-based AI tools. Built by SlowMist to safeguard LLM plugin ecosystems.
4
63

oobabooga

4.8K followers
-
llama-cpp-binaries
llama.cpp server in a Python wheel.
3
64

FawwazRaza

4 followers
Lahore,Pakistan
QueryClip
A RAG video chatbot to deliver accurate, context-aware answers. Users can upload videos, which are split into chunks and embedded into a vector database. When a question is asked, the chatbot retrieves relevant chunks using similarity search and generates response.
3
65

lilit-org

3 followers
-
awesome-decentralized-ai
⽊ ongoing list of curated resources for decentralized AI and LLMs, with a focus on agents, blockchains, and privacy 🏴‍☠️
3
66

DerisO22

4 followers
Burlington, VT
Project3-LMS
Learning Management System for CSI-300: Database Management Systems
3
67

jesus3476

0 followers
-
Fire-Detection-Siglip2
Fire-Detection-Siglip2 is an image classification vision-language encoder model fine-tuned from google/siglip2-base-patch16-224 for a single-label classification task. It is designed to detect fire, smoke, or normal conditions using the SiglipForImageClassification architecture.
3
68

seagpt

2 followers
California
LMTokenCook
Cook your files into AI-ready servings
3
69

Bouquets-ai

51 followers
Bristol, UK
StrikeGPT-R1-Zero
基于DeepSeek-R1黑盒蒸馏的网络安全渗透领域推理模型。可高效的应对断网情况下的网络安全大赛。简介写完整了,图片加载不出来看看是否梯子挂好了
3
70

ytmytm

61 followers
Polska
llama2.c64
Inference Llama 2 in several files of pure C but on a C64
3
71

annangiv

0 followers
-
LibreAIChat-Community
A privacy-first, self-hosted AI chat UI powered by Ollama and open-source models like Mistral, LLaMA 3, and Phi. Designed to be fast, lightweight, and simple to deploy (Docker-ready)—no GPU or complex setup required. Spin up your own ChatGPT alternative in minutes with a beautiful TailwindCSS UI and Go Fiber backend. Supports real-time streaming
3
72

Varun-coder1

0 followers
-
ai-access
A flexible PHP library providing access to various AI models (Gemini, OpenAI, Anthropic, DeepSeek, Grok) via a consistent interface.
3
73

E-sar456

0 followers
-
GEN-AI-CAPSTONE-PROJECT
This project demonstrates a Generative AI-powered assistant that streamlines the job application process using Google Gemini Pro. It analyzes a user’s resume against a job description, calculates a match score, suggests tailored bullet points, and generates a personalized cover letter — all formatted in structured JSON for automation.
3
74

MaouNakano

2 followers
-
youtube_timecodes_generator
YouTube AI Timecodes Generator
3
75

OUIsolutions

24 followers
-
VibeScript
a lua runtime for vibecoding
3
76

Yumben-Open-Source-AI

0 followers
China
LibRAG
​​LibRAG​​: A next-gen intelligent content retrieval engine that redefines traditional RAG architecture. Leveraging ​​full-chain LLM inference​​ to streamline document processing and paragraph recall, it eliminates embedding models/vector databases while achieving precise end-to-end semantic retrieval through deep language understanding .
3
77

dengruihan

1 followers
-
GLM-Edge-V-2B--Monitoring_Species
一个福寿螺卵自动统计系统,用户只需上传一组或更多带有福寿螺卵的图片即可统计出每张图片里的福寿螺卵数量。An automatic statistics system for Fushou snail eggs. Users only need to upload a set or more pictures with Fushou snail eggs to count the number of Golden Apple Snail eggs in each picture.
3
78

aman29100

0 followers
-
GPT-Awesome-List-Generator
This is a Python program that automatically generates an "awesome list" for a specific keyword as a markdown file. An "awesome list" is a list of resources related to a specific topic. Currently, the resources include GitHub projects, Google Scholar articles, YouTube videos, courses, slides and presentations, software and tools and podcasts. The aw
3
79

swaymm7

0 followers
-
Open-Source-Prompt-Library
Here is where I store all my useful prompts
3
80

Creadores-Program

3 followers
-
CreaProDroid
Un Asistente de IA basado en Google Gemini para Android Antiguo 4.2-8.1 / An AI Assistant based on Google Gemini for Old Android 4.2-8.1
3
81

michaelskyba

41 followers
~Toronto, Canada :(
hinata
CLI AI "agents"™ + Unix philosophy 🐙
3
82

luwhano

0 followers
-
fastapi-langgraph-agent-production-ready-template
A production-ready FastAPI template for building AI agent applications with LangGraph integration. This template provides a robust foundation for building scalable, secure, and maintainable AI agent services.
3
83

fabiogiglietto

22 followers
Italy
fabiogiglietto.github.io
AI-driven academic portfolio with automated content aggregation and intelligent web mentions discovery - like Yahoo Pipes for academics, but with GPT-4 superpowers! A modern Jekyll site that mashes up publication APIs, social feeds, and scholarly references into one sleek, auto-updating research showcase.
3
84

gpt4o-image

0 followers
-
GPT-4o
新版GPT-4o生图功能太强了(附国内使用指南)【6月最新更新】
3
85

Fredff1

3 followers
-
LLM-inference-module
3
86

AI-Maker-Space

335 followers
-
Unsloth-Llama-4
Simplified "how to run" Llama 4
2
87

deepseek-free-r1

0 followers
-
deepseek-r1-web
DeepSeek | 中文官网、DeepSeek网页版、API 调用和本地部署教程 | 最全使用指南~【2025年4月更新】
2
88

AlperenEvci

28 followers
Eskişehir
multi-chat-agent
A conversational AI agent built with Python, Streamlit, and LangChain, featuring multi-LLM support (Gemini, Llama 3), persistent chat history via PostgreSQL, agent tools (Web Search, Python REPL), and image generation using Google Cloud's Imagen model.
2
89

tubiccelavi

0 followers
-
Poker-COACH
Ai Vr Machine Learning Natural language Poker Coach
2
90

BotirBakhtiyarov

4 followers
Kunming
MindMap
An intelligent web application that transforms complex questions into interactive visual mind maps using AI (Deepseek integration).
2
91

asii-mov

1 followers
-
Llama-Guard-Output-Feedback
2
92

TianJianShen-nova

4 followers
-
DeepSeek-R1-free
DeepSeek-R1 免费的API Key可使用。https://hao666666.online 获取免费API接口。
2
93

priyanshua44

0 followers
Delhi, India
no-llm
no-llm is a lightweight library designed to simplify the integration of machine learning models without relying on large language models. It provides essential tools for developers to create efficient, scalable applications while maintaining clear and concise code.
2
94

Clay-111

1 followers
Dhaka, Bangladesh
PDF-Chatbot-with-LangChain-and-Ollama
An interactive Streamlit app that lets users upload PDFs and ask questions to receive concise, reasoning-based answers using the DeepSeek-R1 language model.
2
95

Vaishnavi639

4 followers
Pune
llama3.2-dockerfile_generator
2
96

dev-lime

1 followers
-
SHGPU-LMS
2
97

pramodkoujalagi

17 followers
Karnataka, India
SmolLM2-360M-Instruct-Text-2-JSON
A fine-tuned version of SmolLM2-360M-Instruct-bnb-4bit specialized for parsing unstructured calendar event requests into structured JSON data.
2
98

doganarif

51 followers
Berlin, Germany
promptpilot
A fast, lightweight CLI tool for versioning, testing, and optimizing your AI prompts across multiple providers. Easily track prompt evolution, run A/B tests, and measure performance without Git dependencies. Supports OpenAI, Claude, Llama, and HuggingFace.
2
99

GraHms

88 followers
Maputo
prompter
Fluent Go prompt builder for LLaMA- and Chat-style models with role-delimited blocks and built-in list formatting.
2
100

HLM1337

1 followers
-
AIDebateMaster
A Python-based application that enables debates and answer optimization between two AI language models. The platform supports OpenAI models, Anthropic Claude models, and various Chinese AI models like DeepSeek, Moonshot, ChatGLM, Qwen, and ERNIE.
2