flytohub/flyto-core

AI가 끝났다고 했어. Flyto2가 증거를 보여줘.

AI 에이전트를 위한 Python 실행 엔진입니다. 브라우저와 API 작업을 다음과 같이 실행합니다. 명시적 단계, 각 단계가 무엇을 했는지 기록하고, 그 단계에서 재생하는 것들 실패했다 — 전체 작업을 다시 실행하는 대신에.

현재 공개 인벤토리는 482개의 레지스트리 지원 모듈을 89 전역에 걸쳐 보유하고 있습니다. 카탈로그 카테고리, 트리거, 큐 모듈, 워크플로우 버전 관리, 미터링 훅, 브라우저 자동화, API 호출, 데이터 변환, 검증, 파일, 그리고 암호화폐.

flyto2.com · 클라우드 자동화 · 문서 · MCP 문서 · 유튜브

---

30초 후에 해봐

스크린샷 캡처. 성과 지표 추출. JSON 보고서 저장. 모든 단계를 추적.

---

8단계가 실패하면 어떻게 될까요?

셸 스크립트를 사용하면 전체를 다시 실행합니다. flyto-core를 사용할 때:

1단계부터 7단계까지는 즉각적입니다. 8단계만 재실행됩니다. 전체 맥락은 보존됩니다.

---

이건 어떻게 다른가요?

Flyto2

Yep, it talks to a real robot. It also opens websites, calls APIs, works with files, and runs the steps in between.

English · 日本語 · 한국어 · 简体中文 · Español · Português (BR)

Try something.

Say you want to check a website, grab screenshots, collect some data, and save a report.

Run this:

pip install "flyto-core[browser]"
playwright install chromium
flyto recipe competitor-intel --url https://github.com/pricing

That’s a real workflow. No agent prompt needed. It opens a browser, runs the steps, and saves the results.

Want to poke around?

flyto recipes                 # see the built-in workflows
flyto modules                 # browse the tools
flyto run your-workflow.yaml  # run your own

There are 482 registered modules and 41 built-in recipes in the current Core inventory. Browser stuff, APIs, files, data, tests, and plenty more. Use what you need.

And about that robot…

We’re already connecting Flyto2 to a real TurtleBot3 using ROS 2.

The robot runs its normal ROS 2 / Nav2 stack. A separate adapter talks to it. Flyto2 handles the software steps and their execution records.

No custom Flyto2 firmware on the robot. No motor drivers crammed into this repo.

This isn’t a claim that every robot is plug-and-play. The current combined setup still needs its full end-to-end hardware sign-off. But the ROS 2 adapter and real-robot development are already here.

So what’s in this repo?

This is flyto-core, the Python execution engine behind Flyto2.

You can call it from Python, run YAML workflows, use its local HTTP API, or hook it into an AI client through MCP.

pip install flyto-core
python -m core.mcp_server

Your agent gets access to Core’s tools. Moving a physical device still requires a trusted host to approve the action.

Different device software stack? Different pack. That’s how ROS 2 and other integrations stay separate without turning Core into a giant pile of device drivers.

How do I know what actually happened?

This part matters.

When a workflow runs, Flyto2 keeps a record of each step. If something fails, you can inspect the run and use checkpoints or replay where it’s safe to do so.