Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
以 @helloianneo 老师的 ian-xiaohei-illustrations skill 为灵感,根据其底层项目逻辑(构图纪律+IP承担核心动作+留白+QA清单)复用改造,做出以自己原创 Q版女孩为固定主人公的中文文章正文配图 skill。
SkillLink only★ 4Few stars
Agent skill: the rules for building offline-first PWAs that launch instantly from the home screen
SkillLink only★ 30
Agent-first CLI for OddSockets real-time messaging. As simple as git.
MCPLink only★ 1Few stars
The agent-first secret vault. Coding agents store, rotate, and share secrets — AES-256-GCM encrypted, audited, autonomous.
MCPLink onlyFew stars
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
OfficialSkillLink only★ 28k in collection
**MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `use_figma` tool call. NEVER call `use_figma` directly without loading this skill first. Skipping it causes common, hard-to-debug f
OfficialSkillLink only★ 28k in collection
Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and parity enforcement. For Claude Code, Cursor, Gemini CLI, Codex and more.
MCPLink only★ 1.4k
End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.
MCPLink only★ 22k
💻 vibe coding 101|The first course for AI-native product builders.
MCPLink only★ 20k
本地优先的跨平台 Claude Code / AI Agent 桌面工作台:多 Agent 协作、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、桌面宠物;支持微信、飞书、钉钉及 H5 等远程访问。 | Local-first Claude Code / AI Agent desktop workspace: multi-agent teams, Git wo
MCPLink only★ 15k
Resolver-posture checks for MCP hosts, agents, CLI and CI. Local-first, read-only and privacy-first.
MCPLink onlyFew stars
Enterprise-grade, local-first Agent Workbench for people and agent teams. A unified multi-engine workspace for Codex Harness, DeepSeek Harness, and OpenCode, with unified plugins and Skills, multi-age
SkillLink only★ 7.0k
Open-source Claude Cowork / Codex alternative — a local-first AI office agent that turns one request into real PPTX, DOCX, XLSX and HTML files. Runs DeepSeek, Qwen, Doubao, Claude or Ollama (BYOK), MC
MCPLink only★ 325
The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex & more. Build Clawdbot 🦞· APIs for Lovable · Bots for Slack & Lark/Feishu · Skills are in
SkillLink only★ 7.5k
Magicrew. The first open-source all-in-one AI productivity platform (Generalist AI Agent + Workflow Engine + IM + Online collaborative office system)
MCPLink only★ 5.0k
Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform
MCPLink only★ 1.3k
Local-first compile step for knowledge bases. Save 350x cost, 1000x speed vs. frontier models
MCPLink only★ 89
Run a team of AI coding agents. On your machine. Local-first orchestration for Claude Code, Codex, OpenCode, Antigravity, and Copilot.
MCPLink only★ 103
macOS-first local MCP and Actions runtime that gives ChatGPT real coding hands over trusted projects
MCPLink only★ 164
A local-first, open-source coding agent for your desktop. Bring your own LLM key; your code stays on your machine and only ever leaves to the model provider. The AI Agent builds its own Harnes.
MCPLink only★ 181
A persistent, Git-versioned map of your whole codebase and database schema that coding agents read before they touch anything. Local-first MCP server + CLI in Go: a governed repository index of code k
MCPLink only★ 1.6k
PumpFun GitHub social fee claim monitor — real-time Telegram feed for first-time creator fee claims on Solana
MCPLink only★ 22
Give any AI model a real working environment on your Windows desktop. Aetox is a local-first agent harness that lets AI work across your files, shell, browser, documents, and codebase—not just chat ab
MCPLink only★ 54
Consort keeps AI-written code clean and correct: a coordinated ensemble of role agents, spec-first and test-driven, driven by a deterministic state machine against live branches of a real Lakebase dat
OfficialMCPLink only★ 33
Who stands behind it