naolbeyene
SudoAgent runtime guardrails for AIagent toolcalls policy and approval and audit
Re:SudoAgent runtime guardrails for AIagent toolcalls policy and appro...
on Friday January 23, 2026 @10:48AM (#46733892)
I built SudoAgent, a Python library that guards “dangerous” function calls at runtime.
It’s meant for agent/tool code (refunds, deletes, API writes, prod changes) where you want a gate outside the prompt.
How it works
Evaluate a policy on the call context (action + args/kwargs)
Optionally request human approval (terminal y/n in v0.1.1)
Write audit entries (JSONL by default) and correlate with request_id
Key semantics
Decision logging is fail-closed (if decision logging fails, the function does not execute)
Outcome logging is best-effort (logging failure won’t change the function return/exception)
Redacts secret key names + value patterns (JWT-like, sk-, PEM blocks)
It’s intentionally minimal and framework-agnostic: implement your own Policy, Approver,or AuditLogger (Slack/web UI/db) and inject them.
Ask HN: How do you authorize AI agent actions in production?
I'm deploying AI agents that can call external APIs – process refunds, send emails, modify databases. The agent decides what to do based on user input and LLM reasoning.My concern: the agent sometimes attempts actions it shouldn't, and there's no clear audit trail of what it did or why.Current options I see: 1. Trust the agent fully (scary) 2. Manual review of every action (defeats...