MCP servers and skills: search, filter by where they run, and compare.
Strictly-typed, unified registry plugin designed to model, manage, and validate software component interfaces and call/dependency trees. By defining system interfaces, side-effects, and internal contr
SkillAGPL-3.0★ 7No key
OCC (Orchestrator Chain Chimera) YAML-first LLM orchestrator. Multi-model chains with auto-parallelism, 30 pre-tools at zero token cost, React canvas, MCP, REST API. 70% faster/cheaper than naive appr
SkillMIT★ 7No key
Native AI agent manager for Android — 17+ LLM providers, on-device voice & local models, multi-agent delegation
SkillMIT★ 1Few starsNo key
MCP server for Gemini 2.5 Flash Image Preview (nano-banana) - Advanced image generation, editing, and analysis
Node.jsMIT★ 1Few starsNo key
Generate a proficiency badge for your Claude Code usage — rule-based scoring engine with 53 pattern-matching rules across 5 CCA-aligned domains, auto-updating SVG badge via GitHub Gist
Node.jsApache-2.0★ 6No key
Run parallel Claude Code agents with real-time terminal UI
SkillMIT★ 5No key
AgentDesktop - a local Windows AI agent workbench built with PySide6. 61+ tools (web search, RAG, automation, voice ASR/TTS, video generation), agent loop with sub-agent parallel execution, model rout
MCPLink only★ 2Few stars
Transform mathematical images to LaTeX, chemistry structures to SMILES, and documents to markdown with security-first design. The geodesic path to mathematical OCR in Ruby.
SkillMIT★ 2Few starsNo key
Update an existing implementation plan file with new or update requirements to provide new features, refactoring existing code or upgrading packages, design, architecture or infrastructure.
OfficialSkillMIT★ 40k in collectionNo key
Create a new implementation plan file for new features, refactoring existing code or upgrading packages, design, architecture or infrastructure.
OfficialSkillMIT★ 40k in collectionNo key
A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.
GoApache-2.0★ 1.9kNo key
Multi-agent AI platform with voice and text control. Visual workflows, web interface, and chat integrations (Telegram, Discord, Slack). Long-term memory, any LLM backend, extensible via MCP tools.
SkillApache-2.0★ 110No key
Multi-perspective plan review skill for Claude Code — parallel VP Product, Engineering, and Design agents to identify blockers, anti-patterns, conflicts, and regressions.
SkillMIT★ 15No key
Self-contained multi-agent AI orchestration runtime for .NET. CLI + web UI, native tools, sandboxing, MCP, layered memory.
SkillGPL-3.0★ 9No key
CLI to output design system tokens for different stacks
Node.jsMIT★ 3Few starsNo key
Curated Pi package bundling useful extensions, skills, and recovery docs: memory, session notebooks, Magic Docs, Codex UI gallery, and frontend UI workflows.
SkillMIT★ 2Few starsNo key
Agent orchestration dashboard — Kanban UI for any work tracker × any agent runtime.
GoMIT★ 8No key
Production-grade AI agent runtime for Go — Claude Code-style capabilities out of the box: permissions & approvals, context compaction, sandboxing, subagent governance, DAG pipelines, benchmarks. MCP c
GoMIT★ 1Few starsNo key
Experimental UI and integration testing hub.
SkillApache-2.0★ 3Few starsNo key
Claude skill for OpenSCAD: parametric parts and multi-part assemblies built around off-the-shelf hardware (real screw lengths, nuts, bearings, gears, NEMA motors, BOM), verified with numbers instead o
SkillMIT-0★ 1Few starsNo key
Scale-adaptive story framework for features and bugfixes: structured requirements (EARS), design, task breakdown, and execution with specialized sub-agents for analysis, architecture, implementation,
SkillMIT★ 1Few starsNo key
AI for Blender 4.2+. Describe what you want and an agent builds it in your live scene: models, PBR textures, rigs and animation. Works with any OpenAI-compatible API (OpenAI, OpenRouter, Gemini, Ollam
SkillGPL-3.0★ 1Few starsNo key
Agent Skill for large-scale brand strategy and identity engagements: 10 evidence-backed research workstreams, iterative cross-team debate, and 7 implementation-ready deliverables for Codex, Claude Cod
SkillMITFew starsNo key
Local LLM text/speech workflow with external tool calls.
SkillMIT★ 2Few starsNo key
Who stands behind it
