tsaijamey/frago

Multi-runtime automation infrastructure for AI agents. Native CDP browser control, metadata-driven Recipe system, and persistent Run context management.

49
/ 100
Emerging

Frago captures and reuses working task solutions as deterministic **Recipes** — executable code generated after AI completes a task, eliminating repeated AI calls and token costs. It provides a lightweight desktop runtime (~2MB) with automatic dependency installation across macOS, Windows, and Linux, designed for non-technical users to define automation through natural language rather than terminals. The system chains reusable Recipes as building blocks, enabling AI agents to compose complex workflows from previously solved subtasks while maintaining persistent Run context across execution cycles.

No Package No Dependents
Maintenance 13 / 25
Adoption 8 / 25
Maturity 13 / 25
Community 15 / 25

How are scores calculated?

Stars

55

Forks

9

Language

Python

License

AGPL-3.0

Last pushed

Mar 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/tsaijamey/frago"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.