AgentPulse, drift investigation for multi vs TaskPeace

Open-source drift investigation for multi-agent systems: which agent drifted, where it originated, and what to check next.

Mission control for AI coding agents. One ranked queue Claude Code, Cursor or any MCP agent works top to bottom, you watch live. Free while in beta, every feature, no...

About AgentPulse, drift investigation for multi

Open-source drift investigation for multi-agent systems: which agent drifted, where it originated, and what to check next. What did change is the payload it receives from writer, starting at the same run. So critic is probably downstream damage, not the source. After the change, writer responses run ~180% longer and drop the section structure critic expects, earlier payloads were structured summaries, newer ones read as prose. If restoring the format fixes critic, make the fix in writer.

About TaskPeace

Mission control for AI coding agents. One ranked queue Claude Code, Cursor or any MCP agent works top to bottom, you watch live. Free while in beta, every feature, no limits, no card. Your agents pull the top task, do it, report back, and move to the next, top to bottom, on autopilot. The loop your agents run: get_next_task → do the work → complete_task, top to bottom, while you do other things.