GitHub Featured Open Source

jnmetacode--agency-agents-zh

Shell 0 0

jnMetaCode/agency-agents-zh｜GitHub 镜像 ⭐ 18.1k · 🍴 3k

mirror

最后更新于 2026-07-21 18:48:37 +00:00

voltagent--awesome-claude-code-subagents

Shell 0 0

收录 100+ 专为 Claude Code 打造的子智能体，覆盖各类开发场景。｜GitHub 镜像 ⭐ 23.6k · 🍴 2.8k

mirror

最后更新于 2026-07-20 08:48:16 +00:00

light-heart-labs--ods

Shell 0 0

一键将 PC、Mac 或 Linux 设备变成本地 AI 服务器，支持 LLM 推理、聊天界面、语音、Agent、工作流、RAG 和图像生成。｜GitHub 镜像 ⭐ 3.4k · 🍴 498

mirror

最后更新于 2026-07-20 08:44:08 +00:00

light-heart-labs--dreamserver

Shell 0 0

把 PC、Mac 或 Linux 变成 AI 服务器，支持 LLM 推理、聊天界面、语音、智能体、工作流、RAG 和图片生成。｜GitHub 镜像 ⭐ 3.4k · 🍴 498

mirror

最后更新于 2026-07-20 08:42:43 +00:00

spiritlhls--ecs

Shell 0 0

VPS 融合怪服务器测评项目更推荐使用无环境依赖的Go版本 VPS Fusion Monster Server Test Script – More recommended to use the Go version with no environment dependencies: https://github.com/oneclickvirt/ecs｜GitHub 镜像 ⭐ 7.1k · 🍴 556

mirror

最后更新于 2026-07-20 08:40:03 +00:00

orbstack--orbstack

Shell 0 0

快速、轻量的 Docker 容器和 Linux 运行环境｜GitHub 镜像 ⭐ 9.1k · 🍴 94

mirror

最后更新于 2026-07-20 08:39:21 +00:00

donchitos--claude-code-game-studios

Shell 0 0

将 Claude Code 变成完整游戏开发工作室：49 个 AI Agent、72 项工作流技能。｜GitHub 镜像 ⭐ 23.3k · 🍴 3.3k

mirror

最后更新于 2026-07-20 08:36:53 +00:00

msitarzewski--agency-agents

Shell 0 0

一站式 AI 代理机构：从前端专家到社区运营，每个智能体各有专长与工作流。｜GitHub 镜像 ⭐ 136k · 🍴 22.1k

mirror

最后更新于 2026-07-20 08:32:30 +00:00

mattpocock--skills

Shell 0 0

来自真实工程师 .claude 目录的技能集。｜GitHub 镜像 ⭐ 181k · 🍴 15.5k

mirror

最后更新于 2026-07-20 08:32:26 +00:00

obra--superpowers

Shell 0 0

一套行之有效的智能体技能框架与软件开发方法论。｜GitHub 镜像 ⭐ 259k · 🍴 23.1k

mirror

最后更新于 2026-07-20 08:30:02 +00:00

skillhub-118-tmux

Shell 0 0

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

最后更新于 2026-07-13 13:36:35 +00:00

skillhub-079-council-review

Shell 0 0

Run any question, plan, PR, or code through a Diverse Multi-Agent Debate (DMAD) council of 5 AI advisors with distinct reasoning methods. Advisors collaborate, peer-review each other anonymously, and a chairman synthesizes a verdict. Empirically outperforms adversarial debate (M3MADBench 2026, DMAD ICLR 2025). Use when: 'council this', 'run the council', 'council review', 'pressure-test this', 'stress-test this', 'war room this', or when facing a genuine decision with stakes and tradeoffs.

最后更新于 2026-07-13 13:36:13 +00:00

skillhub-074-planning-with-files

Shell 0 0

Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring 5+ tool calls. Supports automatic session recovery after /clear.

最后更新于 2026-07-13 13:36:11 +00:00