f5devcentral/codex-integration

View on GitHub

Runtime security controls for OpenAI Codex. This integration scans user prompts, tool inputs, and tool outputs through F5 AI Guardrails, powered by CalypsoAI, and inspects final assistant responses on a best-effort basis. It helps detect prompt injection, PII leakage, toxic content, and off-topic material at Codex lifecycle boundaries.

Stars: 1
Forks: 1
Open beginner issues: 0
Indexed issues: 3

Dominant language: Python
License: Apache-2.0
Last GitHub push: Jun 22, 2026
Latest indexed: Sep 15, 2026
Contributing guide: Contributing guide
Code of conduct: Code of conduct
Beginner labels: No beginner labels indexed
PR merge metrics: No merged PRs in 30d

Beginner friendly Everything

Open All

Spike: server-side inference proxying behind Calypso (WAF-style deterrence) Open

discussion enhancement

Difficulty 5/5 Over a week Newbie friendliness 35/100

f5devcentral/codex-integration#3 · Opened Jun 22, 2026
Client-side hook model is bypassable and exposes data at the endpoint Open

discussion security

Difficulty 5/5 Over a week Newbie friendliness 25/100

f5devcentral/codex-integration#2 · Opened Jun 22, 2026
Stop hook can't suppress responses in the Codex GUI (scan runs after display) Open

bug upstream

Difficulty 4/5 3-5 days Newbie friendliness 35/100

f5devcentral/codex-integration#1 · Opened Jun 22, 2026

f5devcentral/codex-integration

Get new issues in your inbox