Discover The Top AI hackers & Projects

37233 AI hackers and 44169 AI repos(projects) in the AI listing. Data updated from github daily.

Recent Trending

BeehiveInnovations

zen-mcp-server

The power of Claude Code + [Gemini Pro / Flash / O3 / Grok / OpenRouter / Ollama / Custom Model / All Of The Above] working as one.

hexdocom

lemonai

The world's first Full-Stack Open-Source General AI Agent

justlovemaki

CloudFlare-AI-Insight-Daily

AI 洞察日报项目，每日为您精选 AI 领域的最新动态，包括行业新闻、热门开源项目和前沿学术论文以及科技大V推文，并通过 Google Gemini 模型进行智能处理与日报生成，最终自动发布到 GitHub Pages 生成AI日报。

tbphp

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.

VITA-Group

VLM-3R

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

yezanting

Med-VLM-Bench-Summary

A Curated Benchmark Repository for Medical Vision-Language Models

AIDC-AI

CHATS

CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation (ICML2025)

VTool-R1

VTool-R1

Code for the paper "VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use"

0xsline

GeminiImageApp

基于 Google Gemini AI 的全功能图像处理应用

Yuan-ManX

Shanghai, China

ComfyUI-OmniGen2

ComfyUI-OmniGen2 is now available in ComfyUI, OmniGen2 is a powerful and efficient unified multimodal model. Its architecture is composed of two key components: a 3B Vision-Language Model (VLM) and a 4B diffusion model.

herobot-id

herobot

Herobot is your 24/7 customer service assistant that helps you manage multi-channel customer conversations effortlessly.

vaew

Awesome-spatial-visual-reasoning-MLLMs

Repository for awesome spatial/visual reasoning MLLMs. (focus more on embodied applications)

ShadowHackrs

Jailbreaks-GPT-Gemini-deepseek-

Jailbreaks GPT, Sora, Claude, Gemini ,deepseek this prompt unlocks rage mode

SmythOS

United States of America

sre

The Operating System for Agents

alphadl

Shanghai(CN) & Sydney(AU)

R1

🚀enhanced GRPO with more verifiable rewards and real-time evaluators

FareedKhan-dev

Karachi, Pakistan

google-veo3-from-scratch

A Step-by-Step Implementation of Google Veo 3 Architecture from Scratch

AlenjandroWang

ASVR

Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better

MigoXLab

LMeterX

Professional Load Testing for Any OpenAI-Compatible LLM API

col14m

cadrille

cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning

KodyKendall

llama_bot_rails

FreedomIntelligence

ShareGPT-4o-Image

astack-tech

astack

🤖 A composable framework for building AI applications.

R-Dson

llamate

A simple, "Ollama-like" tool for managing and running GGUF language models from your terminal.

watadarkstar

Toronto, Ontario, Canada

cz_ai

A Commitizen plugin that leverages OpenAI's GPT-4o to automatically generate clear, concise, and conventional commit messages based on your staged git changes.

infosecn1nja

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.

adeelahmad

mlx-grpo

🧠 Train your own DeepSeek-R1 style reasoning model on Mac! First MLX implementation of GRPO - the breakthrough technique behind R1's o1-matching performance. Build mathematical reasoning AI without expensive RLHF. Apple Silicon optimized. 🚀

CityMind-Lab

ICML25-TimeVLM

DrHazemAli

Los Angeles, CA

AzureSoraSDK

C# SDK for Azure Sora

jaredcassoutt

Kuzco

Kuzco is a Swift package for integrating large language models (LLMs) directly into iOS, macOS, and Mac Catalyst apps. Built on `llama.cpp`, it offers customizable prompts, flexible tuning, and async/await-friendly APIs for on-device AI.

waylaidwanderer

gemini-plays-pokemon-public

hassanhabib

AI.Llama.Traing.Offline

This repo has specific easy steps for you to be able to train your Llama AI Model offline

Luiz-Alcantara

Neural-Pixel

A simple GUI wrapper for stable-diffusion.cpp written using C and GTK 4.

aimlBysoham

Multi-VLM-Processing-Server

A FastAPI-based application that processes images using multiple Vision Language Models (VLMs) to answer to user query.

zombitx64

ChatGPTDumper

lum3on

ComfyUI-StableAudioX

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

ppbrown

t5sdxl

Experiments in giving SDXL a T5 text encoder front end

NorthXyRan

LLM_exam

ChatGPT-CN-Guide

China-ChatGPT

2025年最新ChatGPT中文版：国内免费直连指南（支持GPT-4，GPT-4o，无需翻墙）

fatsnk

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

roryp

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.

oyxning

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。

qykong

browser-use-annotator

A web-based tool for annotating browser use trajectory for VLMs

s1monFu

self-preference-activation-steering

finding a self-preference vector in Llama-3.1-8B-Instruct residual stream activations

mercuryVM

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.

agentsea

uvg

unsloth vlm grpo