AgentPulse, drift investigation for multi vs Rafter

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

Rafter captures how your team actually solves tasks and turns it into skills and agents anyone can run, inside the tools you already use.

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 Rafter

Rafter captures how your team actually solves tasks and turns it into skills and agents anyone can run, inside the tools you already use. Then lets every team member use this knowledge to accelerate their work. The summary is drafted and waiting for your approval. Interfaces shown belong to their respective owners; Rafter is independent and unaffiliated. Rafter connects over MCP, so it shows up inside the tool you already use. Developer mode is what lets ChatGPT add custom connectors; it flags them as elevated risk.