4 tagged edge ai, measured the same way as everything else here.
Agent
Use when the user wants to extend bubbaloop's daemon, MCP server, RBAC, agent runtime, or tool set — adding a new MCP tool, modifying tier mapping, extending the multi-agent runtime, working on the alignment-notes gaps, or refactoring core internals. Knows the crate layout, rmcp 0.15 macro syntax, the…
Agent
Use when the user wants to create, scaffold, validate, or refactor a bubbaloop node (sensor/actuator/processor/gateway). Knows the node contract (manifest queryable, command queryable, heartbeat), bubbaloop-sdk patterns for Rust and Python, registration + install flow, and how to test end-to-end via the MCP plugin or…
Agent
Use when the user asks to inspect, control, or troubleshoot a running Bubbaloop deployment — node lifecycle (start/stop/restart/build), health checks, log reads, mission management, or scheduling tasks. Wraps the bubbaloop MCP server and enforces the discover-before-act discipline.
Agent
Knows the rvCSI runtime end to end — the normalized CsiFrame/CsiWindow/CsiEvent schema, the validateframe pipeline + quality scoring, the CsiSource plugin trait + AdapterProfile, the .rvcsi JSONL format, the napi-c shim contract, the napi-rs surface, and ADR-095/096. Use for: adding a CsiSource adapter, extending the…