Lawful AI Daily Brief — 2026-05-03

🛠️ Tool Updates

• Codex CLI 0.128.0 is bringing operator energy: persisted /goal flows, codex update, stronger permission profiles, and cleaner plugin lifecycle.
• Claude Code v2.1.126 (just outside 48h, still hot) added gateway model discovery (/model), claude project purge, and better OAuth fallback in WSL/SSH/container setups.
• Trend vibe: fewer “where did my tool go?” moments, more “it just shipped.”

💡 Tip of the Day

Make compliance checks a merge blocker, not a retro meeting:

# .github/workflows/ai-compliance.yml
name: ai-compliance
on: [pull_request]
jobs:
  check:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: Varshith-07/eu-ai-act-check-action@main

⚖️ Legal x AI Watch

• Legal/compliance-flavored repos updated in the last day include:
  • aevum-labs/aevum — policy engine + audit trail + EU AI Act tags.
  • Unawakened-landlord758/ClawGuard — guardrails for agent actions, leak prevention, and audit logs.
  • ivanmoralesf2015-sudo/enterprise-governance-toolkit — governance/risk toolkit with EU AI Act and ISO 42001 themes.
• Signal: governance-by-default tooling is moving from “nice idea” to “actual repo with commits.”

📈 Trending Repos

• Significant-Gravitas/AutoGPT — still a giant in agent land.
• langgenius/dify — strong momentum for production agent workflows.
• firecrawl/firecrawl — web data layer remains a core AI stack primitive.
• NousResearch/hermes-agent — fast-moving agent framework with huge traction.

🎤 Standup One-Liner

“Yesterday we tightened agent workflows and moved compliance checks into CI, so we can ship faster and leave an audit trail legal won’t hate.”

---

Repo: github.com/laugustyniak/lawful-ai-staging