Lawful AI Daily Brief — 2026-05-04

🛠️ Tool Updates

Codex CLI 0.128.0 keeps getting better: persistent /goal, codex update, stronger permission profiles, and cleaner plugin lifecycle.
Claude Code v2.1.126 remains the practical winner for regulated workflows: project purge controls, better model discovery, and improved skill telemetry.
Community pulse: awesome-claude-code looked mostly like docs/structure maintenance, not a fresh wave of new skills.

💡 Tip of the Day

Treat your agent permission profile like legal policy, not just dev config:

profiles:
  strict:
    fs: read-only
    net: allowlist
    net_hosts: [api.openai.com, github.com]
    approvals: on-request

⚖️ Legal x AI Watch

Compliance-focused repos still moving fast:
- arqajalvarez/aibom-scanner
- Jozithe3019/ai-act-guardian
- Kabbalistgenusmasdevallia941/EUfirst
Pattern worth noting: more teams are baking EU AI Act mapping into scanner/tooling layers instead of handling it in docs after the fact.

📈 Trending Repos

f/prompts.chat — giant prompt hub that still dominates stars.
MemPalace/mempalace — open-source AI memory system with strong momentum.
langchain-ai/langgraph — agent graph workflows keep pulling attention.
onyx-dot-app/onyx — open AI chat platform climbing steadily.
mastra-ai/mastra and yamadashy/repomix — builder tools with strong practical adoption.

🎤 Standup One-Liner

“We tightened agent permissions and compliance traceability while keeping delivery speed high—so we’re shipping faster and making auditors less scary.”

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