Lawful AI Daily Brief — 2026-05-05

⚙️ Tool Updates

• Claude Code v2.1.128 rolled in with cleaner /mcp visibility (including zero-tool server detection), better reconnect signal/noise, and .zip plugin-dir support.
• Workflow sanity boost: EnterWorktree now branches from local HEAD, and parallel read-only shell calls don’t all die when one sibling fails.
• Codex CLI is still sprinting through alpha drops (0.129.0-alpha.4 → .6) with heavy packaging modularization momentum.

💡 Tip of the Day

Treat compliance evidence like build artifacts, not afterthoughts.

# Quick daily evidence capture pattern
codex --version
claude /mcp
printf "%s | model=%s | tool_snapshot=ok\n" "$(date -Iseconds)" "$(codex --version)" >> .ai-audit/evidence.log

⚖️ Legal x AI Watch

• Legal/compliance-flavored repos with fresh activity:
  • CSOAI-ORG/care-membrane-mcp
  • CSOAI-ORG/healthcare-fhir-mcp
  • StrangeDaysTech/devtrail
  • airblackbox/air-trust
  • airblackbox/airblackbox
• Signal: teams keep pushing EU AI Act + auditability + MCP patterns into practical tooling.

📚 Fresh Papers

• Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudication — http://arxiv.org/abs/2605.02472v1
• SCPRM: A Schema-aware Cumulative Process Reward Model for Knowledge Graph Question Answering — http://arxiv.org/abs/2605.02819v1
• InfoLaw: Information Scaling Laws for Large Language Models with Quality-Weighted Mixture Data and Repetition — http://arxiv.org/abs/2605.02364v1

🔥 Trending Repos

• Significant-Gravitas/AutoGPT
• langgenius/dify
• NousResearch/hermes-agent
• bytedance/deer-flow
• openai/openai-agents-python

🎤 Standup One-Liner

“Yesterday we tightened agent workflows and doubled down on audit-grade evidence trails, so velocity went up while compliance risk went down — rare win-win unlocked 😎.”

---

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