Today
aid-server
AID 是一套全开源、可私有化部署、可直接运营的一站式 AI 漫剧、AI 漫画、AI 动态漫、AI 短剧与 AI 视频创作平台。支持 AI 剧本创作、角色/道具/场景管理、AI 智能分镜、AI 文生图、AI 图生视频、AI 配音及项目管理,并提供多模型多厂商接入、任务调度、用户权限、积分计费、充值支付和运营后台。
sonicloud_opensdk
声云录音卡 Recorder 是一套面向开发者和行业客户的智能录音硬件接入方案。 项目以录音卡片硬件为核心,开放 BLE 协议 SDK 及 Android、iOS、鸿蒙、Flutter 接入示例,同时提供 Windows/macOS 桌面端 Demo,支持设备连接、录音控制、实时音频、文件传输、OTA 升级和语音转写等能力,帮助开发者快速将录音硬件接入自己的 App、桌面软件或行业系统。 如需获取硬件规格、样机、完整协议、SDK 资料或定制服务,请联系安徽声云
codex-astra-luna-orchestrator
Use Astra as orchestrator and Luna for subagents in Codex
anything2explainer
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.
prod-FARM-IOS-Core
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.
Yesterday
mural
The language app you eventually delete. A native iPhone companion for learning through conversation.
spotifast
Spotify, native and fast. One lightweight Rust app for your whole library, local playback, and Spotify Connect on Linux, macOS, and Windows.
ai-infra-book
《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
reef
Continual learning infra for self-improving agents
droidloom
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.
workout-guide
302 open exercise illustrations and a framework-neutral npm package by Bryl Lim
agent-memory
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.
qwen38-27b-rtx3090
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
NoGraphicsAPI
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.
headcount
An agent organization for Claude Code, structured as a company — 15+ departments, 125+ skills, each independently installable.
dsh-infinite-gen-4
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
2026-9-13
SoL-Pi
SoL-Pi: Scaling Auto-Research Loops for Efficient Agent Harnesses
bloub
SVG recreation of the x.ai bot avatar. One shape morphing through 14 states, measured off the reference video frame by frame.
cn
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.
VoiceMem
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.
holo-card-studio
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.
open-higgsfield
A studio for image and video generation — one prompt bar, each model’s own settings, and every finished run in one gallery.
Click to load more
