Top AI Project by Categories

A list of Top influential AI open source project listed by different categories. ( Data sourced from GitHub, updated automatically everyday.)
RankingsOrganization Account
Related Project
Project intro
Star count
1

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
2

om-ai-lab

674 followers
-
VLM-R1
Solve Visual Understanding with Reinforced VLMs
5.2K
3

jingyaogong

852 followers
HangZhou, China
minimind-v
🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM!🌏 Train a 26M-parameter VLM from scratch in just 1 hours!
3.9K
4

manycore-research

152 followers
Hangzhou, China
SpatialLM
SpatialLM: Training Large Language Models for Structured Indoor Modeling
3.4K
5

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
6

SkyworkAI

917 followers
Singapore
Skywork-R1V
Skywork-R1V2:Multimodal Hybrid Reinforcement Learning for Reasoning
2.6K
7

QiuYannnn

52 followers
Los Angeles
Local-File-Organizer
An AI-powered file management tool that ensures privacy by organizing local texts, images. Using Llama3.2 3B and Llava v1.6 models with the Nexa SDK, it intuitively scans, restructures, and organizes files for quick, seamless access and easy retrieval.
2.4K
8

SkalskiP

5.6K followers
127.0.0.1
vlms-zero-to-hero
This series will take you on a journey from the fundamentals of NLP and Computer Vision to the cutting edge of Vision-Language Models.
1.0K
9

OpenBMB

5.1K followers
-
VisRAG
Parsing-free RAG supported by VLMs
611
10

PKU-YuanGroup

1.2K followers
China
UniWorld-V1
UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
560
11

vlm-run

43 followers
United States of America
vlmrun-hub
A hub for various industry-specific schemas to be used with VLMs.
510
12

nrl-ai

51 followers
-
llama-assistant
AI-powered assistant to help you with your daily tasks, powered by Llama 3, DeepSeek R1, and many more models on HuggingFace.
486
13

awwaiid

97 followers
Washington, DC
ghostwriter
Use the reMarkable2 as an interface to vision-LLMs (ChatGPT, Claude, Gemini). Ghost in the machine!
436
14

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
15

fpgaminer

173 followers
-
joycaption
JoyCaption is an image captioning Visual Language Model (VLM) being built from the ground up as a free, open, and uncensored model for the community to use in training Diffusion models.
349
16

Hon-Wong

20 followers
-
VoRA
[Fully open] [Encoder-free MLLM] Vision as LoRA
299
17

Aident-AI

5 followers
United States of America
open-cuak
Reliable Automation Agents at Scale
279
18

TIGER-AI-Lab

300 followers
Canada
VLM2Vec
This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks" [ICLR25]
266
19

Genta-Technology

20 followers
Indonesia
Kolosal
Kolosal AI is an OpenSource and Lightweight alternative to LM Studio to run LLMs 100% offline on your device.
227
20

MigoXLab

1 followers
-
dingo
Dingo: A Comprehensive Data Quality Evaluation Tool
182
21

2U1

89 followers
South Korea
Llama3.2-Vision-Finetune
An open-source implementaion for fine-tuning Llama3.2-Vision series by Meta.
156
22

IDEA-Research

2.5K followers
China
ChatRex
Code for ChatRex: Taming Multimodal LLM for Joint Perception and Understanding
156
23

lucasjinreal

2.3K followers
Sanfancisco
Namo-R1
A CPU Realtime VLM in 500M. Surpassed Moondream2 and SmolVLM. Training from scratch with ease.
133
24

FennelFetish

8 followers
-
qapyq
An image viewer and AI-assisted editing/captioning/masking tool that helps with curating datasets for generative AI models, finetunes and LoRA.
127
25

balrog-ai

1 followers
-
BALROG
Benchmarking Agentic LLM and VLM Reasoning On Games
117
26

RenzKa

61 followers
-
simlingo
[CVPR 2025, Spotlight] SimLingo (CarLLava): Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment
110
27

mtkresearch

94 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。
104
28

Ravi-Teja-konda

15 followers
-
Surveillance_Video_Summarizer
VLM driven tool that processes surveillance videos, extracts frames, and generates insightful annotations using a fine-tuned Florence-2 Vision-Language Model. Includes a Gradio-based interface for querying and analyzing video footage.
102
29

MDGrey33

13 followers
Riga, Latvia
pyvisionai
The PyVisionAI Official Repo
97
30

shikiw

65 followers
-
Modality-Integration-Rate
The official code of the paper "Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate".
96
31

WooQi57

41 followers
-
Helpful-Doggybot
Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models
90
32

fangyuan-ksgk

37 followers
Singapore
Mini-LLaVA
A minimal implementation of LLaVA-style VLM with interleaved image & text & video processing ability.
89
33

OpenRobotLab

531 followers
-
VLM-Grounder
[CoRL 2024] VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding
85
34

TrustGen

12 followers
United States of America
TrustEval-toolkit
TrustEval: A modular and extensible toolkit for comprehensive trust evaluation of generative foundation models (GenFMs)
79
35

Gumpest

129 followers
Beijing
SparseVLMs
Official implementation of paper "SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference".
77
36

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
74
37
3d-conditioning
Enhance and modify high-quality compositions using real-time rendering and generative AI output without affecting a hero product asset.
61
38

ai4ce

220 followers
Brooklyn, NY, U.S.
SeeDo
[IROS 2025] Human Demo Videos to Robot Action Plans
54
39

50n50

13 followers
-
sources
READ THE README
50
40

hewei2001

116 followers
Shanghai
ReachQA
Code & Dataset for Paper: "Distill Visual Chart Reasoning Ability from LLMs to MLLMs"
48
41

iris0329

57 followers
-
SeeGround
[CVPR'25] SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding
46
42

declare-lab

285 followers
Singapore University of Technology and Design
Emma-X
Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning
39
43

thubZ09

12 followers
India
All-Things-Multimodal
Hub for researchers exploring VLMs and Multimodal Learning:)
38
44

USC-GVL

25 followers
United States of America
PhysBench
[ICLR 2025] Official implementation and benchmark evaluation repository of <PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding>
36
45

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
46

wendell0218

0 followers
-
GVA-Survey
Official repository of the paper "Generalist Virtual Agents: A Survey on Autonomous Agents Across Digital Platforms"
33
47

Video-Bench

0 followers
-
Video-Bench
Video Generation Benchmark
32
48

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
49

roboflow

3.5K followers
United States of America
vision-ai-checkup
Take your LLM to the optometrist.
31
50

GAD-cell

5 followers
-
VLM_GRPO
An implementation of GRPO for Unsloth's VLMs training
31
51

kesimeg

17 followers
-
awesome-turkish-language-models
A curated list of Turkish AI models, datasets, papers
30
52

opendatalab

1.7K followers
China
UrBench
[AAAI 2025]This repo contains evaluation code for the paper “UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios”
29
53

sayedmohamedscu

46 followers
Egypt
Vision-language-models-VLM
vision language models finetuning notebooks & use cases (paligemma - florence .....)
27
54

sovit-123

140 followers
India
SAM_Molmo_Whisper
An integration of Segment Anything Model, Molmo, and, Whisper to segment objects using voice and natural language.
23
55

ArmenJeddi

8 followers
Toronto
saint
a training-free approach to accelerate ViTs and VLMs by pruning redundant tokens based on similarity
22
56

gptscript-ai

142 followers
-
gptparse
Document parser for RAG
20
57

taco-group

68 followers
United States of America
Re-Align
A novel alignment framework that leverages image retrieval to mitigate hallucinations in Vision Language Models.
19
58

kornia

205 followers
Spain
bubbaloop
🦄 Serving Platform for Spatial AI and Robotics.
19
59

col14m

15 followers
-
cadrille
cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning
19
60

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
61

NVIDIA-AI-Blueprints

262 followers
United States of America
video-search-and-summarization
Blueprint for Ingesting massive volumes of live or archived videos and extract insights for summarization and interactive Q&A
17
62

worldcuisines

1 followers
-
worldcuisines
WorldCuisines is an extensive multilingual and multicultural benchmark that spans 30 languages, covering a wide array of global cuisines.
16
63

tychenjiajun

41 followers
Guangzhou, China
exif-ai
A Node.js CLI and library that uses OpenAI, Ollama, ZhipuAI, Google Gemini or Coze to write AI-generated image descriptions and/or tags to EXIF metadata by its content.
13
64

stogiannidis

13 followers
Edinburgh
srbench
Source code for the Paper "Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models"
12
65

SiyuWang0906

1 followers
-
CAD-GPT
[AAAI2025] CAD-GPT: Synthesising CAD Construction Sequence with Spatial Reasoning-Enhanced Multimodal LLMs
12
66

FreedomIntelligence

418 followers
-
TRIM
We introduce new approach, Token Reduction using CLIP Metric (TRIM), aimed at improving the efficiency of MLLMs without sacrificing their performance.
11
67

xlang-ai

547 followers
-
computer-agent-arena-hub
Computer Agent Arena Hub: Compare & Test AI Agents on Crowdsourced Real-World Computer Use Tasks
11
68

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
69

gptbmw

0 followers
-
wildcard
最新野卡wildcard虚拟信用卡使用指南:wildcard注册教程,如何开通野卡信用卡?如何为野卡充值和提现?
11
70

OPTML-Group

76 followers
East Lansing, Michigan
VLM-Safety-MU
Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-tuning
11
71

MING-ZCH

52 followers
Wuhan, China
CII-Bench
Can MLLMs Understand the Deep Implication Behind Chinese Images?
9
72

securade

5 followers
Singapore
sentinel
Securade.ai Sentinel - A monitoring and surveillance application that enables visual Q&A and video captioning for existing CCTV cameras.
9
73

Open-Social-World

0 followers
-
EgoNormia
EgoNormia | Benchmarking Physical Social Norm Understanding in VLMs
9
74

HaoyuanYang-2023

1 followers
-
ImagineFSL
Official implementation of "ImagineFSL: Self-Supervised Pretraining Matters on Imagined Base Set for VLM-based Few-shot Learning" [CVPR 2025 Highlight]
9
75

hyun-yang

0 followers
Brisbane, Australia
MyColPali
The PyQt6 application using ColPali and OpenAI to show Efficient Document Retrieval with Vision Language Models
8
76

Kazuhito00

714 followers
Aichi, Japan
Qwen2-VL-Colaboratory-Sample
Colaboratory上でQwenLM/Qwen2-VLをお試しするサンプル
7
77

DataFog

6 followers
United States of America
vlm-api
REST API for computing cross-modal similarity between images and text using the ColPaLI vision-language model
7
78

ola-krutrim

69 followers
India
Chitrarth
Chitrarth: Bridging Vision and Language for a Billion People
7
79

loong64

14 followers
China
ollama
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.
7
80

2dameneko

0 followers
-
ide-cap-chan
ide-cap-chan is a utility for batch image captioning with natural language using various VL models
6
81

david-s-martinez

8 followers
Munich, Germany
Dex-GAN-Grasp
DexGANGrasp: Dexterous Generative Adversarial Grasping Synthesis for Task-Oriented Manipulation - IEEE-RAS International Conference on Humanoid Robots (Humanoids) 2024 | DOI: 10.1109/Humanoids58906.2024.10769950
5
82

Ashad001

62 followers
Karachi
RoomAligner
A focus on aligning room elements for better flow and space utilization.
5
83

sonstory

16 followers
Seoul, Korea
VLM-ZSAD-Paper-Review
Reviews of papers on zero-shot anomaly detection using vision-Language models
4
84

Bhavik-Ardeshna

55 followers
Montreal, Quebec
Multimodal-VideoRAG
Multimodal-VideoRAG: Using BridgeTower Embeddings and Large Vision Language Models
4
85

bastien-muraccioli

1 followers
Tsukuba, Japan
svlr
SVLR: Scalable, Training-Free Visual Language Robotics: a modular multi-model framework for consumer-grade GPUs
3
86

asaddi

10 followers
California, USA
ComfyUI-YALLM-node
Yet another set of LLM nodes for ComfyUI (for local/remote OpenAI-like APIs, multi-modal models supported)
3
87

PandragonXIII

1 followers
China
CIDER
This is the official repository for Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models.
3
88

XiaomingX

9.8K followers
japan
awesome-text-to-video-plus
The Ultimate Guide to Effortlessly Creating AI Videos for Social Media Go From Text to Eye-Catching Videos in Just a Few Steps
3
89

StabRise

3 followers
-
ScaleDP
ScaleDP is an Open-Source extension of Apache Spark for Document Processing
3
90

JoeJoe1313

21 followers
Sofia, Bulgaria
LLMs-Journey
Various LLM resources and experiments
3
91

MicDZ

45 followers
Wuhan, Hubei, China
MANBench
MANBench: Is Your Multimodal Model Smarter than Human?
3
92

wangclnlp

8 followers
-
Vision-LLM-Alignment
This repository contains the code for SFT, RLHF, and DPO, designed for vision-based LLMs, including the LLaVA models and the LLaMA-3.2-vision models.
2
93

sourceduty

52 followers
International
Sora
🎬 OpenAI's Sora, a new text-to-video AI model, is set to launch later in 2024.
2
94

sandy1990418

5 followers
-
Finetune-Qwen2.5-VL
Fine-tuning Qwen2.5-VL for vision-language tasks | Optimized for Vision understanding | LoRA & PEFT support.
2
95

MaxLSB

4 followers
Paris, France
mini-paligemma2
Minimalist implementation of PaliGemma 2 & PaliGemma VLM from scratch
2
96

fork123aniket

10 followers
Montreal, QC, Canada
Multi-Round-VLM-powered-Multimodal-Conversational-AI-Navigation-Bot
Streamlit App Combining Vision, Language, and Audio AI Models
2
97

anyofai

48 followers
-
sora
Sora是什么?如何使用Sora?Sora入口在哪?Sora订阅保姆级教程!
2
98

Shard-AI

0 followers
United States of America
Shard
Open Source Video Understanding API and Large Vision Model Observability Platform.
2
99

claw1200

3 followers
UK
llama-cord
Discord App for Interacting with local Ollama Models. Multiple Agents Supported!
2
100

elloza

59 followers
Salamanca
slides2video-pinokio-script
Pinokio script for installing the app slides2video
2