ellmos-ai/ellmos-tests
B/O/E evaluation framework for SKILL.md-based LLM operating systems and agent hubs
B/O/E evaluation framework for SKILL.md-based LLM operating systems and agent hubs
npx add-skill ellmos-ai/ellmos-testsB/O/E evaluation framework for SKILL.md-based LLM operating systems and agent hubs
Один раз настрой AGENTS_RULES v2 для автономии. Цель: агенты (Claude, Gemini, GLM) всегда имеют контекст при смене аккаунтов и перезапуске IDE. Без моего вмешательства. Обязательно: Git-репо, авто Check-in/Check-out, watcher + compile.py (raw → wiki), shared_status.md, правило «Что получилось/НЕ получилось», сохранение Handover Protocol.
One command. Full stack. Zero compromise. — All-in-one Claude Code skill with 33 modes, 6-layer security, 23 hooks, and 75% token savings. Works on Codex, Cursor, Manus, Windsurf.
一个 golang 原生 Agent SDK，支持 multi-agents/skill/spawn 等能力以及全量的中文文档
Personal AI agent that lives on your device; viral local-first assistant reaching 210k+ stars in 2026.
Automate Pdfless tasks via Rube MCP (Composio). Always search tools first for current schemas.
Personal AI coding harness — orchestrates Claude Code + skill ecosystem across 4 phases with auto-memory, sub-agent isolation, and cross-model review