让 Hermes Agent 和主流 AI 工具拥有中国教育场景能力的开源 Agent Skill Pack：学前启蒙、教材同步、备考复习、错题复盘、每日练习、亲子陪学、阅读写作和教师工作流。 Open Agent Skill Pack for Hermes Agent and mainstream AI tools.
General-purpose agent with transport abstraction, state management, and attachment support
OpenJaw Agent — Autonomous desktop AI assistant for the terminal. Rich Ink TUI, 100+ tools, multi-channel bridges (Telegram, Feishu, Teams, WeChat). Standalone, no MCP server required.
Autonomous supervisor for agent-of-empires sessions using OpenCode or Claude Code
Agent authentication runtime primitives
NPX wrapper around vibe-kanban and vibe-kanban-mcp
Local runner connector for Cyrnix/Cyrboard Tracker Local Agent / MCP jobs.
OCSP Stapling implementation
Node.js agent framework for SPM by Sematext
Conclave AI core — Agent interface, council orchestration, self-evolve substrate, efficiency gate.
ESLint plugin with configurations and custom rules for Factory projects
One command for CI, pre-commit hooks, and agent feedback loops. Ships as a single binary.
Agent skill for Dobot+ plugin development
Antenna — agent-mediated nearby people discovery for OpenClaw
One CLI for all your AI coding agents - versions, config, cloud dispatch, sessions, and teams (now with first-class Grok Build CLI support)
A modular SDK for building on-chain autonomous agents using Hashgraph Online Standards, including HCS-10 for agent discovery and communication. https://hol.org
ECS microkernel
NestJS adapter for agent-safe action and workflow runner for TypeScript backends.
Scaffold a Vexel Multi-Agent Intelligence Framework project. Build AI agent squads with ETL mind-cloning and automated squad creation.
Unified CLI for Agent File Tools (AFT) — setup, doctor, and diagnostics across supported agent harnesses (OpenCode, Pi)
Device detection cloud services for the 51Degrees Pipeline API
Paperclip plugin for GitHub platform — repo sync, PR review, issue triage, CI/CD monitoring, engineering metrics, standup reports, knowledge graphs, and decision logs
External Guardian approval broker for OpenClaw exec approvals with dry-run audit, reviewer agent support, and safe enforce mode
Shared HTTP utilities for agent-safe action and workflow runner adapters.