Struvo
Voice-to-field-report platform for construction teams: talk through a site visit, get back a structured, photo-linked report.
Everything the studio's operator has shipped: products in production, open-source tools you can clone tonight, and the lab experiments behind them. “You can just build things” is a claim. This page is the evidence.
Voice-to-field-report platform for construction teams: talk through a site visit, get back a structured, photo-linked report.
Campaign and financial CRM built for a working creative agency: pipelines, scheduling, lead scoring, real books.
Scenario planning and decision intelligence: decision trees with probabilistic outcomes instead of gut-feel strategy.
Forms builder for creating, managing, and scoring custom questionnaires.
Operations platform for a family-run juice business: orders, batches, markets.
The next product usually starts as a Saturday demo.
See the lab ↓These aren't 21 unrelated repos. Most are parts of one machine: councils that argue and judge, guardrails that make agents safe to leave running, corpora that give them something worth remembering, and the daily drivers that keep it all fast. Each part works on its own; together they are the harness this studio runs on, audited in the open as entry 001 on the Harness Ledger.
Published as-is, from real work. If one saves you an afternoon, come say so at a Sharathon.
Five frontier models debate blind; a sixth judges, corrects, and settles. A multi-model council with a dedicated judge seat.
Multi-agent simulation of Apollo-era Mission Control: every flight-controller seat is an AI agent, together flying a KSP Apollo 11 mission.
The permanent artifact of the studio's first Sharathon: every attendee commits one file.
More than one model on the problem: debating blind, flying a mission, or fixing production while you sleep.
What makes an agent safe to leave running: nothing leaks, nothing destructive slips through, nothing ships unreviewed.
Fresh-context adversarial code review on every git push: REJECT blocks the push, verdicts land in an append-only log.
GitHub →Eight drop-in safety hooks that make an AI coding agent safe to leave running: exfiltration guard, destructive-command blocker, write-scope guard.
GitHub →Fail-closed pre-publish gate for any repo: secret scanning (history included), license and env checks, one exit code, wired as a pre-push hook.
GitHub →Schema-agnostic data-quality validation for any SQL database: referential integrity, date sequences, business rules. CLI plus HTML reports.
GitHub →Turning what you watch, read, and browse into something an agent can query.
Privacy-first browser-tab intelligence: capture, intent, project-mapping, stale and solved detection. Local SQLite; sensitive tabs never captured.
GitHub →Turn any YouTube channel into a queryable vector corpus for free: captions, de-dup, local embeddings, hash-skip re-runs.
GitHub →The house data pattern: a typed, append-only JSON spine as the source of truth, with vector databases as disposable indexes on top.
GitHub →The kit for running Claude Code hard: parallel worktrees, spoken TLDRs, packaged skills, a leaner context window.
Git worktree pool manager: bulk-spin parallel worktrees, glance the whole fleet's status, sweep only what is clean and merged. Single-file bash.
GitHub →Curated, no-secrets Claude Code skills: reusable methodology packets for grounding, adversarial research, and review.
GitHub →Hit one key, hear the action-first TLDR of your coding agent's last reply: the decision, the approval, the result. Fully local, works offline.
GitHub →Automated MCP discovery and context optimization for Claude Code: reclaim most of your context window with a five-minute setup.
GitHub →MCP server for npm package intelligence: research packages, find alternatives, check security before you install.
GitHub →A comprehensive course for mastering Claude Code: from first install to fifteen-plus parallel coding sessions.
GitHub →The scrubbed version of the config running here: hooks, settings, and agent wiring with the secrets taken out.
GitHub →Made by the room, about the room.
A receipts-first, 12-dimension audit for personal AI systems, benchmarked live against public agent stacks, plus a paste-in prompt to audit your own.
GitHub →The studio drawn as one machine: every program, tool, and feedback loop on a single page you can read top to bottom.
GitHub →Forensic pipeline that decoded an unscannable, out-of-focus conference QR: grid fitting, calibration from the code's own structure, Reed-Solomon. Full crack story linked. See it →
2026AI-video creator community hub, 200+ members, now graduating into a weekly studio program.
2025Personal YouTube watch history, transcribed, embedded, and searchable: ask your own viewing history questions.
2025Collaborative AI filmmaking sandbox: script enhancement, scene analysis, and a ruthless asset-reuse method.
2025Voice-scored disc golf PWA: sixteen thousand courses, GPS, works offline.
2025Mobile sales-training app with timed roleplay sessions.
2025Personal finance tracker wearing a full cyberpunk UI.
2025Personalized bedtime stories where robot siblings teach if/else, loops, and variables.
2025Hand-gesture mouse control from a webcam: pinch to click, fist to drag, V-sign to scroll.
2025Bring what you're building, or the idea you haven't started. Once a month, one long table, and everyone leaves with the footage.