A provider vs AgentPulse, drift investigation for multi

A headless, provider-agnostic agentic loop. Every piece, memory, model, tools, stop conditions, sits behind a swappable interface. Streaming by default, one dependency,...

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

About A provider

A headless, provider-agnostic agentic loop. Every piece, memory, model, tools, stop conditions, sits behind a swappable interface. Streaming by default, one dependency, runs anywhere. The pieces to build your own agent: your Jarvis, your Cortana, your Samantha. The loop never writes to a screen, it emits one typed AgentEvent stream, so a trace is just data. Scrub the same run and watch three front ends rebuild in lockstep. One pass through the loop, seam by seam, each is just a field on runAgent() .

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.