· 2 min read
Lawful AI Daily Brief — 2026-04-24
⚙️ Tool Updates
- Claude Code v2.1.119/118 tightened automation behavior:
--printnow respects tool allow/deny policies,--agentobeys permission mode, and hooks can call MCP tools directly. - Codex CLI v0.124.0/0.123.0 stabilized hooks, improved MCP diagnostics (
/mcp verbose), and fixed permission-state drift + queued-agent waiting. - Net effect: fewer “agent did a mystery thing” moments, more predictable runs with cleaner receipts. 🧾
💡 Tip of the Day
If you want legal-grade auditability without slowing dev speed, add a pre-patch compliance guard:
# codex config.toml
[hooks.pre_apply_patch]
command = "python scripts/legal_guard.py"
Tiny hook, huge compliance vibes. ✅
⚖️ Legal x AI Watch
- Freshly updated legal/compliance repos worth peeking at:
- ai5labs/singleaxis-fabric — audit-ready AI agent substrate with guardrails/telemetry.
- vindicara-inc/projectair — AI-agent incident response + signed forensic evidence exports.
- ark-forge/mcp-eu-ai-act — EU AI Act compliance scanner for codebases.
- Compliance nudge: hash + log every tool call (input/output + timestamp + actor) so traceability isn’t a last-minute panic project.
🧪 Fresh Papers
- Evaluation of Automatic Speech Recognition Using Generative Large Language Models — semantic LLM judging for ASR beyond WER. (https://arxiv.org/abs/2604.21928)
- MathDuels: Evaluating LLMs as Problem Posers and Solvers — models both create and solve problems in a dynamic benchmark. (https://arxiv.org/abs/2604.21916)
- From Research Question to Scientific Workflow: Leveraging Agentic AI for Science Automation — agentic systems that convert questions into executable workflows. (https://arxiv.org/abs/2604.21910)
📈 Trending Repos
- Significant-Gravitas/AutoGPT — ⭐183k+ — autonomous-agent platform momentum remains absurdly high.
- langgenius/dify — ⭐138k+ — still a top pick for production agent workflows.
- firecrawl/firecrawl — ⭐111k+ — web data pipeline darling for AI agents.
- infiniflow/ragflow — ⭐78k+ — RAG engine with agent capabilities continues climbing.
🎤 Standup One-Liner
“We hardened our agent stack for auditability and observability, so we can move faster and survive compliance review without dramatic keyboard sweating.”