Lmms Engine
EvolvingLMMs-Lab
A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.
Media AutomationSkill source unconfirmed
791GitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Results · “clean-code”
129–144 / 446
More filters · 1
Candidates in this shortlist, not the full registry. GitHub stars belong to repositories, not individual skills.
Results: 446
790GitHub
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
709GitHub
SCAIL
zai-org
SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations (CVPR 2026 Findings)
Media AutomationSkill source unconfirmed
993GitHub
Cosmos Transfer2.5
nvidia-cosmos
Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.
Media AutomationSkill source unconfirmed
684GitHub
Local Talking Llm
vndee
A talking LLM that runs on your own computer without needing the internet.
Media AutomationSkill source unconfirmed
869GitHub
Expo Speech Recognition
jamsch
Speech Recognition for React Native Expo projects
Media AutomationSkill source unconfirmed
637GitHub
Free AI
Free-The-Ai
FreeTheAi (Free The AI): free OpenAI-compatible AI API with 50+ models, Discord key signup, streaming, tools, images, Messages, and Responses. No credit card.
632GitHub
Artemis
momori777
破限本地AI女友后宫，openclaw/claude code+画图语音向量数据库+live2D+桌宠+酒馆角色卡导入+前端，QQ+Telegram双通道，8G显存可跑🩵uncensored Fully offline AI girlfriends harem Openclaw/Claude code+Local LLM+GPT-So…
202GitHub
Nano World Model
simchowitzlabpublic
A Minimalist, Batteries-included Repository for Advancing World Model Science.
Media AutomationSkill source unconfirmed
619GitHub
InfinityStar
FoundationVision
[NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation
Media AutomationSkill source unconfirmed
767GitHub
Libva
intel
Libva is an implementation for VA-API (Video Acceleration API)
Media AutomationSkill source unconfirmed
765GitHub
Flow Factory
X-GenGroup
A unified framework for easy reinforcement learning in Flow-Matching models
Media AutomationSkill source unconfirmed
574GitHub
FollowYourClick
mayuelala
[AAAI 2025] Follow-Your-Click: This repo is the official implementation of "Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts"
Media AutomationSkill source unconfirmed
908GitHub
CloneTTS
sipeter
A lightweight, offline Android Text-to-Speech (TTS) engine enabling seamless system-wide voice cloning and high-fidelity text reading. / 运行在安卓本地的轻量级文字转语音 (TTS) 引擎，支持离线发音…
Media AutomationSkill source unconfirmed
692GitHub