1.2KGitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Results · “modal”
1–16 / 22
More filters · 1
Candidates in this shortlist, not the full registry. GitHub stars belong to repositories, not individual skills.
Results: 22
Vllm Omni
vllm-project
A framework for efficient model inference with omni-modality models
Media AutomationSkill source unconfirmed
5.2KGitHub
Parlor
fikrikarim
On-device, real-time multimodal AI. Have natural voice and vision conversations with an AI that runs entirely on your machine. Powered by Gemma 4 E2B and Kokoro.
Media AutomationSkill source unconfirmed
1.9KGitHub
HunyuanImage 3.0
Tencent-Hunyuan
HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation
Media AutomationSkill source unconfirmed
3.1KGitHub
Lance
bytedance
A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.
Media AutomationSkill source unconfirmed
1.2KGitHub
Lmms Engine
EvolvingLMMs-Lab
A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.
Media AutomationSkill source unconfirmed
791GitHub
KG MM Survey
zjukg
Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey
Media AutomationSkill source unconfirmed
497GitHub
Mmagic
open-mmlab
OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion mod…
Media AutomationSkill source unconfirmed
7.4KGitHub
SALMONN
bytedance
SALMONN family: A suite of advanced multi-modal LLMs
Media AutomationSkill source unconfirmed
1.5KGitHub
DreamOmni2
JIA-Lab-research
This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation (CVPR2026 Highlight)''
Media AutomationSkill source unconfirmed
2KGitHub
Lhotse
lhotse-speech
Tools for handling multimodal data in machine learning projects.
Media AutomationSkill source unconfirmed
1.1KGitHub
InternGPT
OpenGVLab
InternGPT (iGPT) is an open source demo platform where you can easily showcase your AI models. Now it supports DragGAN, ChatGPT, ImageBind, multimodal chat like GPT-4, S…
3.2KGitHub
Phantom
Phantom-video
Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment
Media AutomationSkill source unconfirmed
1.5KGitHub
HunyuanCustom
Tencent-Hunyuan
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
Media AutomationSkill source unconfirmed
1.2KGitHub
SpeechT5
microsoft
Unified-Modal Speech-Text Pre-Training for Spoken Language Processing
Media AutomationSkill source unconfirmed
1.4KGitHub
Echomimic V3
antgroup
[AAAI 2026] EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation
Media AutomationSkill source unconfirmed
1KGitHub