Built models that see. Now building agents that ship.

A LangGraph + Claude Agent SDK pipeline that reviews pull requests against security, licensing, and data-handling policy before merge — cost-gated, human-in-the-loop.

• active
• ·
• LangGraph
• Claude Agent SDK
• FastAPI
• Policy compliance

A pip-installable PDPA compliance layer for Malaysian SMEs using AI/LLM tooling with customer data. One shared codebase, two packages: presidio-audit and presidio-malaysia.

• active
• ·
• PDPA
• PII redaction
• Presidio
• Python

Multi-agent supervision of a live ML model: monitoring, investigation, remediation, post-mortem.

• active
• ·
• Multi-agent
• MLOps
• Monitoring
• Post-mortem

vcrpy for MCP. Records real agent–server sessions into diffable cassettes and replays them as deterministic mock servers.

• active
• ·
• MCP
• Testing
• PyPI
• Python

The smallest tool in my Claude Code monorepo — a wrapper that auto-names every unnamed session with its folder and a timestamp, so the session history is actually browsable.

file-sync keeps my Claude config in step across two folders, newer wins either way — until a raw copy clobbered a machine-specific statusLine.command and taught me why settings.json needs a merge, not a copy.