《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

OpenWiki is a CLI that writes and maintains agent documentation for your codebase.

The fastest knowledge base for growing teams. Beautiful, realtime collaborative, feature packed, and markdown compatible.

Aircraft design optimization made fast through computational graph transformations (e.g., automatic differentiation). Composable analysis tools for aerodynamics, propulsion, structures, trajectory …

BS 架构 Agent 开发平台(面向无人系统设计优化):LangGraph + agent-infra/sandbox + 人机协同工作台

Where people and agents build in tune.

Browser-native Office / PDF / CAD / archive viewer for internal web apps, with Vue, React, Svelte, jQuery, Web Components, and no server-side conversion.

这是 mattpocock/skills 的简体中文本地化版本。

Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docker or Kubernetes.

A coding agent that evolves its own source, in public — 200 lines of Rust on day one, every commit since agent-written and tests-gated.

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

三滴血大冒险：机关迷宫闯关 — 手机横屏 H5/PWA 2D 平台闯关游戏 (Next.js + TypeScript + Phaser 3)

OpenClaw Skill - 值班安排系统 API 集成

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

zcode/Claude Code skill: offline-packaging skill deps (pip/npm/playwright/exe) + skill bodies for intranet (no-internet) install

Modular SenseNova skills for building AI-powered office assistants and productivity workflows

AI coding platform for teams

Edit Banana: A framework for converting statistical formats into editable.

基于 OpenAI gpt-image-2 API 的图片生成与编辑工具

Custom UI for Deep Agents

An Open-Source Asynchronous Coding Agent

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

Topic → 4K narrated video for coding agents. v4.0: all TTS via the ttsCN engine component (11 platforms incl. MiniMax voice clone, native word-level subtitle sync), manifest-based Asset Engine, Rem…

Tool-calling quality benchmark for LLM serving stacks. 80+ deterministic scenarios testing multi-turn orchestration, safety boundaries, and structured output. Supports vLLM, SGLang, and llama.cpp.

llama-benchy - llama-bench style benchmarking tool for all backends

Spark Pulse is a web control plane for spark-vllm-docker