v1.10.1 · MIT
TDD enforcement and guardrails for Claude Code, Codex, and GitHub Copilot CLI.
v2.1.0 · MIT
Claude Code hooks that auto-switch model tier based on task complexity
v1.5.0 · no license
嘉立创EDA专业版(EasyEDA Pro)自动化:给 AI harness 装上画板的「手」—— 一套 typed 原理图/PCB 动作,CLI / Agent Skill / stdio MCP 三形态融合接入。承接嘉立创「不以卖板赚钱,以培养中国工程师为己任」 | EasyEDA Pro automation: the hands of your AI harness — typed schematic/PCB actions via CLI, Agent Skill and stdio MCP.
v1.20.187 · MIT
Multi-agent orchestration platform for AI coding teams — coordinates Claude Code, Gemini CLI, and Codex agents with a real-time web dashboard
v0.23.2 · MIT
Import conversation history from 25+ AI coding agents into DeepSeek Harness as resumable sessions — tool calls, reasoning and results kept intact, with reverse export. | 把 25+ AI 编程 Agent 的聊天记录导入 DeepSeek Harness 继续对话,保留工具调用、推理与结果,支持反向导出。
v5.282.2 · Apache-2.0
Open-source coding-agent harness you can actually change — own the loop (prompts, gates, routing, skills, terminal states), use any model, run long tasks while you're away.
v2.0.4 · MIT
Research that compiles.
v2.12.0 · MIT
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
— · MIT
Memory for AI agents that learns what is wrong and stops repeating it. Mark a memory wrong and it stops coming back; newer facts replace old ones. Local SQLite store and MCP server, persistent across sessions; hippo init wires it into Claude Code, Codex, Cursor, OpenClaw, OpenCode and Pi. Zero runtime deps, MIT, opt-in hosted TypeSafe Jev reranker.
v5.1.1 · MIT
A virtual design team for Claude Code, Cursor, Windsurf, Gemini CLI, and Copilot — 26 roles, 62 commands, 15,000+ lines of expert design knowledge. Your agency's design brain, inside your terminal.
— · Apache-2.0
Agent Skills marketplace: framework-aware skills for code review, documentation, test-plan generation, AI-writing detection, architectural analysis, and git workflows — for Python, Go, Rust, Elixir, React, Remix, and iOS/Swift. Works with Claude Code, Codex, and any agent that supports Agent Skills.
v0.21.4 · MIT
The most accurate, cheapest and fastest memory for coding agents: searchable session history from Claude Code, Codex, Cursor and 32 more agents, already on your disk. No LLM, one Go binary.
v0.23.1 · Apache-2.0
🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / DeepSeek Harness / OpenCode & 20+ CLIs via BYOK.
v0.1.0 · MIT
Air traffic control discipline for agent output. Written for a reader with ADHD.
v0.1.48 · Apache-2.0
A task conductor for Claude Code that gets better the more you use it. Multi-agent orchestration with an evidence contract that BLOCKS instead of asking, gates written as hooks rather than prompts, and a retrospective that learns your repo's rules and tunes its own playbook.
— · no license
Feed your agent papers and half-formed ideas — it links them into a system design you can defend. Markdown keeps the record; a visual canvas makes it readable. An Agent Skill for Claude Code & any SKILL.md-compatible agent.
v0.6.4 · MIT
给 HR / 猎头的 AI 招聘工作流:岗位标准梳理、Boss直聘 + 猎聘双通道寻源初筛、市场人才盘点、简历评估、约面试、候选人台账与日报。可装成 Claude Code 插件或 DeepSeek Harness (dsh) 插件——后者自带可直接上手操作的「招聘浏览器」面板;也能配合任意读 AGENTS.md 的 AI 编程助手使用。
v0.6.0 · MIT
Rules and checks that make Claude Code look around a change, not just at the lines it writes: ten questions before code, a reviewer that didn't write it, proof before done, bugs fixed as a class.
v9.7.0 · MIT
Your AI can write the UI. This makes sure it writes your UI. A deterministic scanner scores your design system 0-100 against 112 public repos, reads React and web components (Stencil, Lit), hands you a copy-paste fix prompt for each top finding, writes ru
v1.3.37 · no license
Offline HarmonyOS NEXT developer skill library for AI coding assistants. Covers API 12–26 declarations, ArkTS/ArkUI, NDK, DevEco Studio, emulator automation, debugging, publishing, and reproducible local tooling.
v2.2.0 · MIT
Use Claude Code like a Director, not a Programmer. MIT toolkit with Auto-Loop, guided setup, 27 commands, 14 agents, and 32 skills.
v1.0.11 · MIT
AI-assisted toolkit for making HTML5 games with LittleJS: the engine, templates, and agent instructions that work with Claude Code, Codex, Cursor and Copilot, so the AI builds your game instead of rebuilding an engine. Installable as a Claude Code plugin.
v0.11.0 · MIT
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
v12.1.1 · MIT
Unbrowse — api native browser Skill/CLI/MCP/SDK for any agent. Auto-discovers APIs from browser traffic, generates skills on the fly to call APIs directly 100x faster, 80% cheaper locally.