Use Astra as orchestrator and Luna for subagents in Codex

Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.

A farm of real iPhones, run from your Mac. Open-source iOS device automation with live control, a Postgres-backed scheduler, and TikTok workflows. Self-hosted, Apache-2.0.

The language app you eventually delete. A native iPhone companion for learning through conversation.

Spotify, native and fast. One lightweight Rust app for your whole library, local playback, and Spotify Connect on Linux, macOS, and Windows.

《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验

Continual learning infra for self-improving agents

Droidloom - weaving Android into Linux. Run Android Apps inside your Wayland session! Supports arm64 and x86_64 platforms, running arm64-only apps on x86_64 without closed source libraries.

302 open exercise illustrations and a framework-neutral npm package by Bryl Lim

Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.

Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state), ~114 tok/s single-user at default sampling / ~124 greedy (MTP drafts, own-output draft vocab, calibrated int4 lm_head, split-KV verify attention), 150k-262k context; patches, requant scripts, benchmarks

Minimal graphics API. Built on top of latest Vulkan extensions. As close as possibly to my "No Graphics API" blog post and the SIGGRAPH talk.

An agent organization for Claude Code, structured as a company — 15+ departments, 125+ skills, each independently installable.

DeepSeek v4.1 flash 网络安全红队工具（无限四代） — jailbreak prompts and test suite for DeepSeek 求 Star 收藏 ⭐欢迎大家提交项目的改进

SoL-Pi: Scaling Auto-Research Loops for Efficient Agent Harnesses

SVG recreation of the x.ai bot avatar. One shape morphing through 14 states, measured off the reference video frame by frame.

cn is a new engine for Tailwind class merging and conflict resolution. It replaces tailwind-merge and clsx. Same APIs. Full parity. And it is 30× faster.

Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.

Turn the user's description or uploaded reference into a finished, editable Blender card and an interactive Three.js page. Preserve the requested subject, style, typography and destination. This skill contains code and text only; generated artwork belongs in the user's output project.

A studio for image and video generation — one prompt bar, each model’s own settings, and every finished run in one gallery.

WeMM-Embedding is a family of universal multimodal embedding models by the WeChat Vision Team at Tencent, supporting multimodal understanding and retrieval.

A macOS app that pins usage limits from Claude Code, Cursor, Codex, and Antigravity to a screen edge.

手绘风格编号画廊与双语提示词 Skill

For detecting anti-detect browsers and spoofed profiles through runtime coherence analysis.