SutroYaro

cybertronai

SutroYaro — Sutro Group research workspace for energy-efficient AI training.

Open cybertronai/SutroYaro → Manually confirmed as a workspace.

ai-researchclaude-codecodex-clicoding-agentsdata-movement-complexityenergy-efficiencyenergy-efficient-traininggemini-cligymnasiummachine-learningopencodepure-python

Works with any agent

ships AGENTS.md, the cross-tool instruction file.

In its own words

Aboutcybertronai/SutroYaro

Point any coding agent at the repo and it becomes a research agent. 34 experiments, eval environment, weekly catch-ups, multi-researcher workflow.

README.md

Research workspace for the Sutro Group -- energy-efficient AI training, meeting weekly at South Park Commons (SF).

Docs site: License: Unlicense (Public Domain)

What this repo is for

SutroYaro is the lab's memory and dispatcher: where you go to find out what's been tried, who's working on what right now, and the agent-team patterns + sync infra that let you spin up new builds against the org's other repos.

Concretely it does five things:

Lab memory across sessions. DISCOVERIES.md is the curated "what's proven" record. New agents and contributors read it before they spend tokens re-running settled experiments. Same for docs/tasks/ (queue) and docs/catchups/ (weekly snapshots).
Agent-teams dispatcher. The hinton-problems and schmidhuber-problems builds (53+58 stubs, ~71 wall hours, ~1.8B tokens combined) were both dispatched from SutroYaro sessions. The reusable machinery — .claude/skills/, hooks, the agent-teams patterns, the JSONL token-counting methodology — lives here.
Cross-repo index. The 8-repo cybertronai org map (docs/related-repos.md, docs/research/active-threads-*) only really makes sense from SutroYaro's vantage point.
Public face for the Sutro Group. The mkdocs site at is what gets shown at meetings.
Telegram + Google Docs + GitHub integration. bin/tg-sync, src/sync_google_docs.py, the daily catchups. No per-experiment-repo would naturally own this.

What this repo is not (anymore):

The repository's own description, then 27% of its README. Read the rest on GitHub ↗

Read from the repository's git tree on 2026-08-17.