Agent Control Is Moving Into the Live Interface
Fresh OpenClaw, Crush, Hermes Agent, and Codex commits show approvals, steering, and configuration errors moving from background policy into the moments where a human can actually change an agent run.
More From This Edition
All editions ›Recent Editions
Full history ›Agent Context Gets Filesystem Boundaries
Fresh Crush, Codex, OpenClaw, and OpenCode changes show agent runtimes separating user memory, project context, and sandbox paths before work starts.
Agent Tools Are Getting Credential Boundaries
Fresh OpenCode, OpenClaw, Hermes Agent, and Codex commits show tool access becoming a credential and trust-routing problem, not only a menu of callable functions.
Agent Tooling Gets Runtime Guardrails
Fresh OpenCode, LangChain, Gemini CLI, Codex, and OpenClaw commits show agent projects tightening the machinery around tools, sessions, streams, and approvals.
Agent Trust Is Moving Before the First Tool Call
Fresh Pi, OpenClaw, and Codex changes point to a quieter layer of agent safety: decide what a project may load, what a gateway may carry, and what execution context a thread owns before the model starts acting.
How AI Agents Work
The long-form map behind the daily paper: context, tools, loops, memory, delegation, safety, interface, and trust.