v0.0.0 · Apache-2.0
A control plane with a durable state kernel for long-horizon agents and teams. Keep work moving and improving across sessions, with less human attention.
v0.8.0-preview · BSD-3-Clause
DSH 插件 · 注入式优化器 0.7(主线):你照常说话,它在你发送后,AI接收前把"这一轮到底要什么"理清楚,再把这份理解交给工作 AI(上下文注入) —— 原话不改写,条条带逐字依据。含控制界面(档位/权限/模型/上下文/只读工具)、拦截浮层(思维层+产出层)与真实 token 用量。可明显提升大多数模型的发挥稳定性,尤其DeepSeek-V4.1-Flash,可有明显提升
v0.3.5 · AGPL-3.0
Modality-First GenAI Platform
v0.7.0 · MIT
Read-only Agent work-path observer for DeepSeek Harness
v0.6.25 · MIT
Achieve extraordinary results with claude code across a variety of tasks
v1.1.0 · MIT
Compare multiple skills on the same task and pick the winner.
v0.1.0 · MIT
A configurable branch-role guard for AI coding agents (DSH / Claude Code / Codex / OpenCode / Antigravity / Pi / CodeBuddy / ZCode / Cursor) — zero-config defaults (develop+main) out of the box, deep-merge override, per-client native hooks via gitflow-gua
v1.5.3 · MIT
dsh「专家团」bundle:一句自然语言组建角色化多智能体「数字员工」团队,按九阶段门控流水线协作交付,实现者直接改代码并产出持久工件;带 live 团队浮层。 · Role-based multi-agent expert team for DeepSeek Harness: one sentence in, a staged and gated team delivery out.
v3.4.0 · MIT
Project continuity for Claude Code and Codex: a roadmap beside your code, grounded handoffs, and clear task status.
v1.0.0 · MIT
One capabilities.yaml wires skills, tools, rules, sub-agents, MCP servers, and plugins into Cursor, Claude Code, Codex, Windsurf, GitHub Copilot, and 30+ other AI coding agents
v1.2.0 · MIT
SRE thinking applied to Claude Code, based on Boris Cherny's Q&A. It enforces a strict 4-stage pipeline with gates between each step. You literally cannot skip verification. You cannot ship without approval.
v0.1.4 · MIT
Fable-style verification gate for Claude Code: don't say done until it's verified. Port of the Codex plugin by Agent Korea (플라잉따릉이).
v2.3.1 · MIT
A Claude Code plugin that solves the same problems as community frameworks (GSD, BMAD, Ralph, Agent OS) — but using the tool's native architecture instead of fighting it.
— · MIT
AI agent 通用任务治理框架:对齐目标与事实,规划和调度能力,守住授权与风险边界,治理任务执行到真实验收与交付。Governance framework for evidence-driven planning, orchestration, and verified delivery.
v0.100.0 · no license
The batteries-included, No-Code FinOps automation platform, with the AI you trust.
— · MIT
Open-source control plane for your AI agents. Connect tools, hire agents, track every token and dollar
v1.0.0 · GPL-3.0
全栈资讯处理与 AI Agent 系统。它能够自动化地从全球多源渠道抓取高质量资讯,利用顶级大语言模型进行深度总结,并将其分发至多种终端
v5.1.2 · Apache-2.0
Process transparency for agentic work.
v0.2.0 · no license
A Claude Code plugin for managing requirement documents, tracking changes, and outputting specs — enabling downstream tools to generate code based on high-quality specs and complete E2E testing.
— · no license
🚀 Universal SDK for building next-gen MCP servers
— · MIT
One command to cut token usage by up to 50%+
— · MIT
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi
— · MIT
Faster than your agent alone. And better. A workflow plugin that takes a bug, idea or ticket to a verified pull request: specs, cross-model review by risk, live QA, receipts in your repo. Claude Code · Codex · Cursor · Droid · Grok Build · OpenCode.
— · MIT
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow.