A living architecture document for AI-built projects. Your AI agent maintains it; you understand what was built.
Goal mode extension for pi: persistent long-running objectives, /goal-set drafting, Sisyphus prompt style, autoContinue, and an above-editor status overlay. Fork of @capyup/pi-goal.
Bearer Node Agent
A local chat UI for testing agents built with @economic/agents.
Compozy CLI
Traseq MCP server, CLI, and SDK for AI-assisted trading strategy research, SignalGraph authoring, validation, backtesting workflows, and system template composition.
건설현장의 법정 안전문서 작성을 더 빠르고 정확하게. 산안법·기준규칙·중처법·KOSHA Guide를 기반으로 안전관리자와 현장소장의 문서 작성과 검토를 돕는 오픈소스 도구입니다.
openHermit: team-oriented agent management workbench atop cc-connect.
Discovery + readiness manifest emitter so agents can introspect aihu apps.
Agent-first CLI for SiYuan Note — workspace management, kernel API proxy, workflow tools, and agent skill install
A library of MUI-based design system components.
Workspace types for the Amazon Connect SDK
Futuristic AI Developer Terminal & Autonomous Coding Agent
Pipeline-driven task management for AI coding agents — stages, dependencies, artifacts, and multi-agent claiming
Parses browser user-agent strings for Astro
Security observability + real-time policy enforcement for AI agents. Local-first NDJSON capture with a continuous Watch daemon that auto-uploads anonymized signals, Shield CLI that blocks policy violations live (with policies pulled from Fortress cloud),
Embeddable AI coding agent built on @cuylabs/agent-core
Harness-agnostic agentic infrastructure for Salesforce developer experience tooling
MCP server for agent-browser - complete browser automation with token-efficient @ref system
Microsoft OpenTelemetry distro adapter for @cuylabs/agent-core
Goal mode extension for pi: persistent long-running objectives, /goal-set drafting, Sisyphus prompt style, autoContinue, and an above-editor status overlay.
Register agent wallets with World ID-verified humans via AgentBook.
Filesystem-first framework for durable backend AI agents that run anywhere.
VibeCheck MCP — the code intelligence layer for AI-built software, wired into your agent. Truth-grounded, runtime-aware, multi-agent. 16+ verification engines, runtime probes, and live truthpack context for Cursor, Claude, Windsurf, and any MCP-compatible