GitHub trending

MoonshotAI/FlashKDA

FlashKDA: high-performance Kimi Delta Attention kernels

tonyqinatcmu/SlideBot-AI

🎨 SlideBot AI - AI-Powered Presentation Generator

localgpt-app/localgpt

digitalknk/openclaw-runbook

OpenMOSS/MOVA

MOVA: Towards Scalable and Synchronized Video–Audio Generation

brenpoly/be-more-agent

Local AI Agent running on Raspberry Pi

Light-Heart-Labs/DreamServer

Local AI anywhere, for everyone — LLM inference, chat UI, voice, agents, workflows, RAG, and image generation. No cloud, no subscriptions.

aiming-lab/SkillRL

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

Soul-AILab/SoulX-Singer

Official inference code for SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis

alibaba-damo-academy/RynnBrain

RynnBrain: Open Embodied Foundation Models

NVIDIA-NeMo/Automodel

Star NVIDIA-NeMo / Automodel Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

TheAgentContextLab/OneContext

OneContext is an Agent Self-Managed Context layer, it gives your team a unified context for AII AI Agents.

sseanliu/VisionClaw

Real-time AI assistant for Meta Ray-Ban smart glasses -- voice + vision + agentic actions via Gemini Live and OpenClaw

TrevorS/voxtral-mini-realtime-rs

Streaming speech recognition running natively and in the browser. A pure Rust implementation of Mistral's Voxtral Mini 4B Realtime model using the Burn ML framework.

zts212653/cat-cafe-tutorials

从零搭建 AI 猫猫协作系统 — 一个真实项目的完整复盘

CelestoAI/SmolVM

Secure runtime for AI agents, and tools -- free and open-source from Celesto AI 🧡

uqogihujomuwhiff/sora2-watermark-cleaner-pro

sora2 watermark cleaner pro

togatoga/karukan

Japanese Input Method System for Linux, macOS, Neural Kana-Kanji Conversion Engine

FireRedTeam/FireRedASR2S

FireRedASR2S is a SOTA Industrial-Grade All-in-One ASR system with ASR, VAD, LID, and Punc modules. FireRedASR2 supports Chinese (Mandarin, 20+ dialects/accents), English, code-switching, and singing lyrics recognition. FireRedVAD supports speech/singing/music in 100+ langs. FireRedLID supports 100+ langs and 20+ zh dialects.

qhkm/zeptoclaw

Final form of claw family (Wannabe)

XiaomiRobotics/Xiaomi-Robotics-0

liangdabiao/make-prompt-seedance2

seedance2结构化提示语，整合了 Seedance 2.0（字节跳动 AI 视频生成模型）的结构化提示词使用方法，帮助用户快速上手并创作出高质量的视频内容。包含 16+ 个模板和 8+ 个示例 |

autogame-17/evolver

The Self-Evolving Agent Protocol (PCEC). It writes its own code.

aeromomo/claw-compactor

🦞 Claw Compactor — The 98% Crusher. Cut your AI agent token spend in half with 5 layered compression techniques.

smallnest/goclaw

An open-source AI assistant framework like openclaw

lijigang/ljg-skill-xray-paper

论文X光机 — Claude Code Skill，解构学术论文，提炼餐巾纸公式

antirez/qwen-asr

C inference for Qwen3-ASR 0.6b and 1.7b transcriptions models

MiniMax-AI/MiniMax-M2.5

deepgenteam/deepgen

blader/napkin

A Claude Code skill that gives the agent persistent memory of its mistakes via a per-repo markdown scratchpad.

oneclaw/oneclaw

OneClaw

ysharma3501/LavaSR

🌋LavaSR: Fast Speech restoration and enhancement

nepfaff/scenesmith

Code for "SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes"

MooseGoose0701/skill-compose

Skill Compose is an open-source agent builder and runtime platform for skill-powered agents. No workflow graphs. No CLI.

rookiestar28/ComfyUI-OpenClaw

Your own personal AIGC Factory. Any picture. Any reel. The Comfy way. ©️

ZackAkil/immersive-language-learning-with-live-api

Star ZackAkil / immersive-language-learning-with-live-api Immergo is an immersive language learning application powered by the Google Gemini Live SDK. It simulates real-world roleplay scenarios (e.g., buying a bus ticket, ordering coffee) to help users practice speaking in various languages with an AI that acts as a native speaker.

shallowdream204/BitDance

BitDance: Open-source autoregressive model with binary visual tokens. A research project for building powerful multimodal autoregressive model.

openhome-dev/abilities

Open-source abilities for OpenHome agents.

lijigang/ljg-skill-xray-book

深度拆书机 — Claude Code Skill，三轮认知压缩提取书籍可学习结构

Snowflake-Labs/agent-world-model

Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning

InternScience/MLEvolve

OpenDriveLab/kai0

Code for kai0, including training, inference and data collection.

andyhuo520/openclaw-assistant-mvp

OpenClaw Desktop Assistant MVP - Electron-based AI voice assistant with Live2D character animations, real-time speech recognition, and text-to-speech

Mathews-Tom/no-magic

Because `model.fit()` isn't an explanation

1va7/openclaw-pm

OpenClaw 项目经理配置升级工具 - 让你的 AI Agent 成为优秀的项目经理

milanm/AutoGrad-Engine

A complete GPT language model (training and inference) in ~600 lines of pure C#, zero dependencies

zscole/model-hierarchy-skill

OpenClaw skill for cost-optimized model routing based on task complexity

TsingmaoAI/xw-cli

实现国产算力大模型零门槛部署，一键跑通 Qwen、GLM-4.7、Minimax-2.1、DeepSeek-OCR 等模型

brendanhogan/hermitclaw

mosaxiv/clawlet

Ultra-Lightweight&Efficient Personal AI Assistant

symbolica-ai/arcgentica

An ARC-AGI solution using Agentica from Symbolica

gazingstars123/Anima-Standalone-Trainer

Standalone Anima Lora trainer with GUI

sharbelxyz/x-bookmarks

OpenClaw skill: turn your X bookmarks into agent actions. Stop hoarding. Start applying.

kyutai-labs/hibiki-zero

A real-time and multilingual speech translation model

stellarlinkco/myclaw

Your own personal AI assistant. Any OS. Any Platform. mini clawbot.

SawyerHood/gitclaw

OpenClaw but it runs entirely on github actions

AnkitNayak-eth/EpsteinFiles-RAG

A RAG pipeline implementation built on the 'Epstein Files 20K' dataset from Hugging Face (Teyler).

tyfeld/drifting-model

Personal PyTorch implementation of "Generative Modeling via Drifting" with Claude

imjszhang/Deepseek-Cowork

Open-source alternative to Claude Cowork - Browser automation & AI assistant powered by DeepSeek

datavorous/sameshi

a ~1200 Elo chess engine that fits within 2KB