Agent Tools Are Getting Capability Switches
Fresh Codex, Hermes Agent, and Pi patches show agent projects narrowing when external skills, MCP tools, and package surfaces become visible.
More From This Edition
All editions ›Recent Editions
Full history ›The Agent Can Refile a Worktree, Not Rewrite the Filing Cabinet
Kilo Code’s new Agent Manager move gives an agent a way to reorganize parallel work—only through a live inventory, a targeted command, and a hard boundary around the recovery file.
Agent Behavior wants to make good conduct a versioned artifact
Braintrust and Basis propose a tiny BEHAVIOR.md standard as the answer key between runtime instructions and agent evals. The file is easy; writing conduct that remains observable across real trajectories is the actual work.
An Approval Cannot Outlive the Conversation That Asked for It
Cline fixed a small but revealing failure in its VS Code extension: change a message while a command approval is waiting, and the old run could keep waiting forever—then catch answers meant for the new one.
QM is trying to turn the personal agent into company infrastructure
Y Combinator's new open-source harness does not win its case by running Codex or Claude in Slack. Its more consequential bet is that every person and room needs a clearly owned memory, workspace, permission set, schedule, and durable computer.
How AI Agents Work
The long-form map behind the daily paper: context, tools, loops, memory, delegation, safety, interface, and trust.