Library · AI toolkits · OpenAI Agents SDK

Guarded Agent Worker Starter

Python starter for the OpenAI Agents SDK: one worker, no side-effect tools, explicit UNVERIFIED output.

OpenAI Agents SDKGuarded agent orchestrationCodeNot runtime testedORIGINAL · MIT

Open the template

Summaries are public. Viewing, copying and downloading BSV-provided source requires free email verification. If you are sent to registration, verify your email and then press this button again.

About OpenAI Agents SDK

A guarded worker with no side-effect tools, ready to grow into agents-as-tools, guardrails, sessions or sandbox agents. The team runner runs each Library AI Team task on a local model with tracing disabled.

Test status

Not runtime tested. BSV has not run this on a user account or runtime; file presence and CI syntax checks are not runtime verification.

Files

guarded-worker.py · 924 bytes
README.md · 811 bytes

Official references

Library AI Teams for this job · Guarded agent orchestration

Ready-made Library Teams that do the work this toolkit supports.

Support Triage — Classify an inbound message, propose a first reply hold, and flag escalation — human sends.
Coding Review — Review a diff or file for bugs, risky paths, and missing tests — without auto-committing or running destructive commands.

Soft links by job — a toolkit and a Team are separate items; nothing here was runtime-tested together.