Bande-a-Bonnot/Boucle-framework

Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.

25
/ 100
Experimental

This project helps developers and engineers enhance the safety of their Claude Code environments. It provides 'hooks' that enforce rules and prevent unintended or dangerous actions, like accidental file deletions or destructive Git commands, which Claude Code's native permissions may miss. You provide a list of files or command types to protect, and the hooks automatically block unauthorized actions, informing Claude Code of the failure.

Use this if you are a developer using Claude Code and want robust, automated safeguards to prevent AI from executing dangerous commands, modifying critical files, or performing destructive Git operations.

Not ideal if you are not a developer working with Claude Code or if you prefer a system where Claude Code prompts for confirmation rather than automatically blocking actions.

AI-safety developer-tools code-security AI-assisted-development devops
No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 11 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Rust

License

MIT

Last pushed

Mar 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/Bande-a-Bonnot/Boucle-framework"

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