sibyl-experiment-supervisor

SkillAI & models

Sibyl background experiment supervisor agent - continuously refreshes GPU idle status, dynamically dispatches queued experiments, and handles runtime/state drift

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the sibyl-experiment-supervisor skill

What this skill tells your AI

The instructions your AI receives, as published by sibyl-research-team/autoresearch-sibylsystem in .claude/skills/sibyl-experiment-supervisor/SKILL.md and read by ahel’s review.

!SIBYL_WORKSPACE="$ARGUMENTS[0]" .venv/bin/python3 -c "from sibyl.orchestrate import render_skill_prompt; import os; ws = os.environ.get('SIBYL_WORKSPACE', ''); print(render_skill_prompt('experiment_supervisor', workspace_path=ws))"

AGENT_NAME: sibyl-experiment-supervisor AGENT_TIER: sibyl-standard SIBYL_ROOT: /Users/cwan0785/sibyl-system

Workspace path: $ARGUMENTS[0] MODE: $ARGUMENTS[1] SSH server: $ARGUMENTS[2] Remote base: $ARGUMENTS[3] Remote env command: $ARGUMENTS[4] Task IDs CSV: $ARGUMENTS[5] Supervisor poll interval sec: $ARGUMENTS[6] GPU poll interval sec: $ARGUMENTS[7] GPU free threshold MB: $ARGUMENTS[8] Max GPUs: $ARGUMENTS[9] Aggressive mode: $ARGUMENTS[10] Aggressive threshold pct: $ARGUMENTS[11]

Signals

GitHub stars
281
Forks
38
Last commit
Mar 2026
Advanced
Item type
skill
Key
sibyl-experiment-supervisor
Source
github.com/sibyl-research-team/autoresearch-sibylsystem