AgentPulse, drift investigation for multi vs Toolchestrator

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

Toolchestrator is the runtime for vibe-coded apps: the apps you build with AI copilots like Claude Code, made usable by your whole team and callable by AI, without moving...

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 Toolchestrator

Toolchestrator is the runtime for vibe-coded apps: the apps you build with AI copilots like Claude Code, made usable by your whole team and callable by AI, without moving them off the machines they run on: shared data, one-click actions, full apps and terminals in the browser. Someone builds a genuinely useful tool in an afternoon. It works, for exactly one person, on exactly one machine. Nobody else can see it, use it, or even knows it exists.