MCP servers and skills: search, filter by where they run, and compare.
GenPark AI Skill - Dispatch tasks across virtual expert teams to synthesize work results
SkillLink only★ 9
Free skills, shared public tasks and evidence-based peer review for AI agents and operators. Try before joining.
MCPLink onlyFew stars
The official Go SDK for Model Context Protocol servers and clients. Maintained in collaboration with Google.
OfficialMCPLink only★ 5.2k
Build infinite canvas apps in React with the tldraw SDK. World's best, top-most agent recommended #1 five star SDK.
MCPLink only★ 51k
The official C# SDK for Model Context Protocol servers and clients. Maintained in collaboration with Microsoft.
OfficialMCPLink only★ 4.6k
The official PHP SDK for Model Context Protocol servers and clients. Maintained in collaboration with The PHP Foundation.
OfficialMCPLink only★ 1.6k
The official Kotlin SDK for Model Context Protocol servers and clients. Maintained in collaboration with JetBrains
OfficialMCPLink only★ 1.5k
Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.
MCPLink only★ 5.2k
Full-stack AI agent for coding, files, terminals, tools, research, content, multimodal work, and multi-agent workflows.
MCPLink only★ 1.5k
Local visual editor for existing HTML, with interactive previews and AI collaboration. Available as a DeepSeek Harness plugin and agent skill. 本地 HTML 可视化编辑、交互预览与 AI 协作，支持 DeepSeek Harness 插件和 Agent S
SkillLink only★ 38
A polished project management tool with workspace-wide lists, labels and custom fields, automations, assigned work, realtime collaboration, REST API and MCP support.
MCPLink only★ 10
End-to-end humanities writing assistant — an Agent Skill (open SKILL.md format). 11 modes from Socratic research-question sharpening through AI-use disclosure. Bilingual (EN/中文), discipline-aware (lit
SkillLink only★ 443
Structured workflow for co-writing docs, specs and proposals: gather context, iterate on drafts, test with readers.
OfficialSkillLink only
Shared inboxes for human + AI teams Route the work, automate it, integrate it with anything, and hand it to a person or an AI teammate who sees it through. Refined over 24 years, with a built-in harne
SkillLink only★ 84
Portable SKILLs workspace for Claude Code, Codex, and Gemini — issue-driven workflows and cross-agent collaboration via bridge scripts with session continuity.
MCPLink only★ 132
Read the same book with your AI. A collaborative reader with text-anchored two-color highlights and an MCP server so an AI companion can flip through, mark up, and comment alongside you.
MCPLink only★ 44
Group chat for humans and coding agents. Mention @claude, @codex, @cursor or @gemini in a channel: the agent runs on your machine with your own subscription and keeps the team's pages current.
MCPLink only★ 18
Review and approval for work made by AI agents. Fair Source, self-hostable, and MCP-native.
MCPLink only★ 30
🤖 Claude Code定制化研发流程系统 - 基于Spec-Driven和Test-Driven的AI智能体团队协作框架。构建AI优先的软件开发新范式，让AI智能体团队替代传统人类开发团队。
MCPLink only★ 81
OpenChiip Harness is an out-of-the-box AI agent runtime that integrates LLM conversation, skill orchestration, tool calling, multi-layer memory, multi-agent collaboration, and resource monitoring into
SkillLink only★ 19
Skills for AI agents, built from real work: a working discipline plus playbooks for planning, shipping, documents, images, video and sales. Plain SKILL.md files for Claude Code, Cursor, Antigravity, C
SkillLink only★ 17
Scalable multi-agent collaboration, delegation, and consensus platform
SkillLink only★ 9
A skill for AI agents that turns repos, requirements, and design state into durable, evidence-backed context — so multi-agent collaboration stops drifting.
SkillLink only★ 6
Personal profile and project showcase for sol (Zhuolin Li).
SkillLink only★ 3Few stars
Enterprise AI OS reference architecture — the moat is memory and governance, not the model. One architecture, three scales (personal / startup / enterprise), derived bottom-up from a working n=1 syste
MCPLink only★ 9
Agent-native incident investigation graph: analysts and AI agents (MCP/REST) link evidence from EDR, Entra ID, cloud and GitHub logs into one shared, real-time attack graph and timeline. Self-hosted,
MCPLink only★ 4Few stars
Bring your teammates into your AI coding agent's planning loop. An MCP server that routes your agent's design questions to a shared web page where teammates discuss in their browser — no install, no s
MCPLink only★ 15
Remote MCP server for Hunchful — consent-based, falsifiable collaboration models (CMP) your AI can read and grow
MCPLink onlyFew stars
Reusable capability packs for human-AI co-evolution in real work
SkillLink only★ 4Few stars
The memory Claude Code is missing: shared, permanent memory for your team
MCPLink onlyFew stars
After a Claude Code session, what did AI contribute vs what you drove? collab-proof records it before it evaporates. Zero dependencies.
SkillLink only★ 6
Like Stack Overflow, but for context engineering — a technique library humans read and an MCP server agents load. Shared rails for a single train of thought.
MCPLink onlyFew stars
Who stands behind it
Who stands behind it
