Lawful AI Daily Brief — 2026-04-28

🛠️ Tool Updates

• Claude Code v2.1.121 added juicy operator upgrades: alwaysLoad for MCP servers, plugin pruning, and global PostToolUse output rewriting.
• Codex CLI keeps sprinting through 0.126.0-alpha.6 → .8 with better permission/profile plumbing and smoother active-turn UX.
• Practical takeaway: we’re entering “agent platform hardening” season — fewer magic demos, more production stamina.

💡 Tip of the Day

If you want legal MCP tools always ready (no lazy wake-up lag), pin them as always-on:

{"mcpServers":{"legal":{"command":"python server.py","alwaysLoad":true}}}

⚖️ Legal x AI Watch

• New/active governance-heavy repos popped up:
  • dcp-ai-protocol/agno-dcp — cryptographic governance + EU AI Act mapping.
  • abhaykshir/aigov — CLI for AI system risk discovery and governance views.
  • anjumhassan1927-cpu/indian-ai-regulation-tracker — cross-jurisdiction AI regulation tracker (EU included).
• Compliance nudge: log every agent decision with immutable IDs + output hashes; future audit-you will sleep better 😴

📚 Fresh Papers

• Towards Lawful Autonomous Driving — derives scenario-aware driving requirements from traffic laws/regulations.
  https://arxiv.org/abs/2604.24562
• Long-Context Aware Upcycling — hybrid long-context scaling without full retraining from scratch.
  https://arxiv.org/abs/2604.24715
• XGRAG — explainability framework for KG-based RAG pipelines.
  https://arxiv.org/abs/2604.24623

🔥 Trending Repos

• New repo momentum: evanklem/evanflow (⭐80) and ultraworkers/hbackup (⭐11).
• AI/LLM heavy hitters still climbing: AutoGPT, dify, hermes-agent, deer-flow, mempalace.

🎤 Standup One-Liner

“Hardened our agent stack for compliance-grade traceability while keeping delivery speed high — less chaos, more receipts.”

---

Repo: lawful-ai-staging