A standard SDK for building agent-facing apps across MCP, CLI, React, and AI tool stacks.

🚀 Run Codex Mobile Anywhere: Linux, Windows, or Termux on Android 🚀

Orchestrate coding agents remotely from your phone, desktop and CLI

Go Agent：Windows、Linux、macOS (go原生支持多端) 客户端支持平台：Windows、Linux、macOS、iOS、Android、Web

A curated list of papers, tools, and benchmarks on LLM-based computer-use agents, covering both terminal/CLI and GUI approaches.

Remote Control for Codex.

[NeurIPS 2025 D&B] 🚀 SWE-bench Goes Live!

RepoLaunch is an agentic SWE tool aimed at automating the build, execution and test of GitHub repositories across programming languages and operating systems.

Create and manage Fujifilm camera profiles, with ease and speed. Connect your camera and you are good to go!

CRS-自建Claude Code镜像，一站式开源中转服务，让 Claude、OpenAI、Gemini、Droid 订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。

Mobile and Web client for Codex and Claude Code, with realtime voice, encryption and fully featured

Machine Learning Containers for NVIDIA Jetson and JetPack-L4T

A debugging and profiling tool that can trace and visualize python code execution

A ready to go nvidia jetson linux for tegra cuda enabled image & container generator.

Configure Jetson Nano with Ubuntu 22.04 headless

[NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

NVR with realtime local object detection for IP cameras

Scrypted is a high performance video integration and automation platform

[ICLR 2026] ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation

Unofficial extension implementation of CausVid

(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis

A unified inference and post-training framework for accelerated video generation.

(CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

Unofficial extension implementation of Self-Forcing to support I2V && 14B training.

Wan: Open and Advanced Large-Scale Video Generative Models

Wan: Open and Advanced Large-Scale Video Generative Models