Pulse: Agent Cognition Observability

Problem: We can see our AI API bills but not whether agents are thrashing, re-reading the same files, or degrading over a session.

A local observability tool that reads the JSONL session transcripts coding agents like Claude Code already write to disk and turns them into a health dashboard. It computes six indicators: file-revisit rate (thrashing), turns-to-resolution, context/cache efficiency, whether the agent actually queries the project memory it built, a frustration index from user-side sentiment, and swarm detection separating orchestrator from sub-agent sessions. The point is to pinpoint where architecture is making the model thrash. It runs 100% locally: no cloud, no API keys, no telemetry.