oh-my-evor

Mission interview workflow that elicits all mission settings and launches a validated run via evor_init_run

Start the live FastAPI + SSE dashboard for the active Evor mission on port 8756

Scan an existing ML workspace to produce a starting-point report; pre-fills the evor-setup interview

Check environment health and .evor integrity; auto-repair obvious issues

Inspect accumulated Gotchas (failures + hardware limits) and the hardware capability profile

Evor MCP tool catalog, run lifecycle, artifact schemas, and native-tool guide. Auto-loads when operating an evor run — setting up/running/resuming/inspecting a mission, recording nodes/evals, launching or watching training, reading/writing tick artifacts, citing papers, emitting/querying signals, or changing any evor state.

Generate a final Evor mission report with tree visualization, frontier table, and static HTML export

Load and validate the mission contract, set active run state, and invoke the Evor tick loop

Set up unattended, multi-day EVOR operation. Auto-suggest when the user asks to run a mission overnight, unattended, for days, on a schedule, or while away. Establishes a poll-and-advance cadence so the session sleeps between ticks and wakes to advance the search, then notifies on milestones and completion.

Main 9-step Evor tick loop with meta-evolution, doom-loop detection, and parallel candidate scheduling

Run the Phase-2 contract/state validator against an active evor run directory and present the report