my-agent / rules
Cursor rule0 starsChanged 6 months agoMITView on GitHub
AI Agent System — my-agent правила и архитектура
- Reads credentials
In this repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- api_integrationSkill
- audio_transcriptionSkill
- auto_agentsSkill
- browserSkill
- code_analysisSkill
- code_executionSkill
- data_analystSkill
- deep_researchSkill
- docsSkill
- emailSkill
- git_integrationSkill
- gmailSkill
- google_sheetsSkill
- image_generationSkill
- messagingSkill
- notionSkill
- ocrSkill
- parsingSkill
- ragSkill
- researchSkill
- rss_newsSkill
- schedulerSkill
- self_devSkill
- slidesSkill
- social_mediaSkill
- sql_dbSkill
- templateSkill
- translationSkill
- video_processingSkill
- visionSkill
- voice_ioSkill
- web3Skill
- web_automationSkill
The file
Files
--- description: AI Agent System — my-agent правила и архитектура globs: ["**/*.py", "**/ARCHITECTURE.md", "**/CONTEXT.md"] --- # my-agent — Modular AI Agent System ## Стек - Python 3.12, FastAPI, asyncio - Standalone Docker Compose в `/opt/projects/my-agent/` - Порт: `localhost:8020` (через `tunnel-myagent`) ## Архитектура - Модульная система: каждый агент — отдельный модуль - Коммуникация через HTTP или очередь - Конфиги через `.env` + `pydantic-settings` ## Разработка ```bash # Запуск туннеля к VDS ssh -N -L 8020:localhost:8020 vds-root & # Деплой ssh vds-root "cd /opt/projects/my-agent && git pull && docker compose up -d --build" # Логи ssh vds-root "cd /opt/projects/my-agent && docker compose logs -f --tail=50" ``` ## Правила агента - Новые агенты — отдельные модули, не трогай core - Все внешние API-вызовы — с retry и timeout - Логи через structlog или stdlib logging (не print)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

