Jun 2, 2026·1 min read

Pi AutoResearch — Autonomous Experiment Loop for AI Agents

An extension that enables AI agents to run autonomous research loops — formulating hypotheses, designing experiments, executing code, analyzing results, and iterating without human intervention.

Anonymous
Anonymous · Community
Agent ready

Ready-to-run agent install

This asset can be installed after the agent chooses its runtime, checks the plan, and runs the matching command.

Native · 98/100Policy: allow
Agent surface
Any MCP/CLI agent
Kind
Skill
Install
Single
Trust
Trust: Community
Entrypoint
SKILL.md
Direct install command
npx -y tokrepo@latest install a0209cf4-5e7d-11f1-9bc6-00163e2b0d79 --target codex

Run after dry-run confirms the install plan.

An extension that enables AI agents to run autonomous research loops — formulating hypotheses, designing experiments, executing code, analyzing results, and iterating without human intervention.

Discussion

Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.

Related Assets

Autoresearch — Automated AI Research Agents by Karpathy

An open-source system by Andrej Karpathy that uses AI agents to autonomously run machine learning research experiments on single-GPU setups.

Skills
AI Open Source

autoimprove-cc — Auto-Improve SKILL.md Loop

Run a Claude Code-native autoresearch loop to improve SKILL.md using binary assertions and git commit/reset; verified 63★ and exposes `/autoimprove`.

Skills
Skill Factory
◈Home🔍Search👤Me