mattijsmoens/intentshield

Pre-execution intent verification for AI agents. Audits what your AI is about to do, not what it says. Zero dependencies, deterministic, hash-sealed.

50
/ 100
Established

Intercepts action payloads (shell commands, file operations, API calls) before execution using two deterministic safety layers—CoreSafety with hash-sealed immutable rules and Conscience with regex-based behavioral detection—eliminating LLM calls from the security path. Provides optional human-in-the-loop approval and SIEM-compatible structured logging, with per-action type auditing (SHELL_EXEC, FILE_WRITE, BROWSE, ANSWER) returning deterministic pass/block decisions tied to specific rule violations.

Available on PyPI.

No Dependents
Maintenance 13 / 25
Adoption 6 / 25
Maturity 18 / 25
Community 13 / 25

How are scores calculated?

Stars

17

Forks

3

Language

Python

License

Last pushed

Mar 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/mattijsmoens/intentshield"

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