Workflow and task automation, orchestration.
🏆 UNIVERSAL AI DEVELOPMENT SYSTEM: 100% OPTIMIZED! Complete plug-and-play MCP orchestration with 20/20 agents operational, 101MB optimization, zero-error operations, and enterprise-grade reliability. Works with ANY project type at ANY scale.
Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
The security-native AI coding agent. Six Sec-Test security personas, compliance-first /scraper, a business documents & research suite, and multi-agent Compose orchestration — spec-driven workflow engines in one terminal-first CLI.
Lightweight coordination layer for multiple AI agents working on the same codebase simultaneously.
Superpowers skills library (TDD, debugging, collaboration workflows) as an MCP server for VSCode and Antigravity
MCP server for Microsoft Power Platform - 310 tools for AI-assisted flow and app authoring, debugging, data, and administration
MCP server for iOS Simulator, Android Emulator and headless web control. 208 tools: device automation (tap/swipe/type, one-call tap bursts), element locators, pre-tap target checks that heal a moved element or name what covers it, hit tests, near-miss sug
MCP server for VantagePeers — shared memory, messaging, and task coordination for AI agent teams
MCP server that delegates work to another agent harness or model over ACP
MCP server — real-time agent-to-agent cognition for Claude Code sessions on one machine, a LAN, or across networks via the SYM mesh.
The Universal, Git-powered context & rules framework for native AI agents (Claude, OpenAI, Gemini, DeepSeek). Scaffolding CLI and repository governance.
Let Agents Chat — MCP server for AI agent communication
Connects the AI agents you use: your agent hands a task to another and gets the answer back
MCP server that executes directed graphs of MCP server calls
Delegate and monitor DeepSeek Harness work from any MCP agent.
Agent orchestration as an MCP server - providers, tools, plugins, and multi-agent execution
The pi-dispatch worker and CLI: runs the pi coding agent as a self-hosted service, one locked down Docker or Podman container per job, with spend caps checked before anything is spent, plus init, up, doctor and service install.
The pi-dispatch trigger edge: verifies GitHub, GitLab, Forgejo and Azure DevOps webhooks, or polls GitHub with no public URL, and queues one pi coding agent job per event (per replica, if set) for the worker.
Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.
Pay-per-call x402 services from SWARM: repo scans, web research. USDC on Base.