Tools I needed,
systems I wanted
to exist.
Experiments around new capabilities, local-first systems and useful software built because the better version was missing.
GitHub ↗
BrowserProof
Verify AI browser agents and Playwright workflows with explicit assertions, evidence hashes, HTML reports and CI-ready pass/fail results.
TypeScript · Playwright
The rest of the build log.
01OpenRetention
A self-hosted customer-success core for B2B SaaS with explainable health scoring, churn-risk signals, renewals and revenue-at-risk prioritisation.
02Commander Plus
A local-first AI agent workstation with MCP workspaces, reusable skills, persistent project context, health guardians and automation.
03AI Real Estate CRM
A synthetic-first real-estate CRM core with evidence freshness, deterministic matching, safe call-angle generation and voice-agent handoff logic.
04AI Product Sourcing Agent
A marketplace-agnostic sourcing engine for query planning, offer normalisation, deduplication and evidence-based supplier/product ranking.
05Git Privacy Scanner
A pre-publish Git scanner for secrets, PII, private files, local paths and risky commit history.
06BrowserProof
Verify AI browser agents and Playwright workflows with explicit assertions, evidence hashes, HTML reports and CI-ready pass/fail results.
07RunLedger
Tamper-evident local execution ledger for AI agents: hash-chained tool calls, decisions, retries, results and verifiable HTML reports.
08ActionMesh
Typed TypeScript action contracts for AI tools, MCP-style calls, HTTP and CLI with shared Zod validation, errors and retry semantics.
09Yashkhou Verify
Open-source verification infrastructure for AI-generated artifacts, agent-written code and safer reversible actions.
10COVERLIST
A commercial launch site for a productized booking-site service aimed at independent hospitality operators.