Real-time dashboard for spawning and controlling AI coding agents across multiple hosts. Streams live terminals via PTY, tracks token usage with OpenTelemetry, supports git worktrees, and deploys with rootless Podman containers. Built with FastAPI + React/TypeScript.
Agent
PROACTIVE — Delegate without user @mention when the repo is unfamiliar, the question spans modules/services, or you need path:line evidence before any edit. Read-only codebase cartographer (files, symbols, call paths). Set thoroughness in the task prompt: quick, medium, or very thorough. NOT for external docs (scout)…
Agent
PROACTIVE — General-purpose agent for researching complex questions and executing multi-step tasks. Use for parallel units of work (parent may launch multiple task calls). May edit when needed. NOT for in-repo-only mapping (explore) or docs-only external research (scout).
Agent
PROACTIVE — Delegate without user @mention after non-trivial parent or general-agent edits, before telling the user the work is done or ready to commit. Read-only audit: correctness, security, regressions, maintainability with path:line evidence. NOT before code exists to review.
Agent
PROACTIVE — Delegate without user @mention when the answer requires official docs, API/library behavior, or web evidence not in the repo. External research with citations; use memory when prior decisions may apply. NOT for in-repo mapping (explore) or implementation (general).