Skip to main content
Start
Now
Principles
Building
Projects
Writing
About
Resume
Contact Me

Start Here

If you only spend 5 minutes here.

Curated front door. 9 things worth your time, ordered by leverage. From the home page if you want the full sprawl, or /principles if you came for the takes.

01

Subscribe to The Production Agent

Weekly Substack on shipping agentic AI to production: orchestration patterns, eval harnesses, governance, and the failure modes that don't make it into the launch posts.

Subscribe (free)
02

The pyAGI acquisition story

Open-sourced an early autonomous-agent Python framework in 2022, acquired by Kyle Morris (co-founder of banana.dev serving 1,000+ startups) and Jeffrey. The artifact behind everything else on this site.

View on PyPI
03

agent-audit-kit - OWASP Agentic + MCP Top-10 SAST

Open-source security scanner for agentic AI systems. 148 rules across OWASP Agentic Top-10 (10/10) and OWASP MCP Top-10 (10/10). GitHub Marketplace-listed. Drop it into any CI pipeline.

Open microsite
04

Provael - red-team & assurance for physical AI

Open-source (Apache-2.0) harness that red-teams vision-language-action robot policies in simulation and reports an attack-success rate with a 95% CI + benign control. Authored the Embodied AI Security Top 10. Measured result: one roleplay instruction drove a real SmolVLA policy 100% off-task (10/10, CI 72-100%) vs a 0% baseline. Action-layer red-teaming: the embodied twin of my agent-security work.

Visit provael.com
05

Disclosure #001 - MCP STDIO Config Injection (CVE-2026-30623)

Inaugural entry in the agent-audit-kit Public Disclosures stream. Why MCP STDIO is RCE-by-design across 150M+ downloads, how AAK-MCP-001 detects it, and what the remediation actually looks like.

Read disclosure
06

OWASP Agentic Top-10 - Commercial Platform Benchmark

10 commercial AI-agent platforms (Claude Managed Agents, Cursor, Devin, Amp, Continue, Bolt, Codeium, Replit, Cline, Augment) scored against OWASP Agentic Top-10. Public methodology, repro repo, quarterly refresh.

See scorecard
07

Principles - how I build production AI agents

12 opinionated rules from 4 years shipping agentic systems. Audit-trail first · capability leases over keys · deny by default on tool calls · MCP STDIO is untrusted · vendor-multi by default · the patterns that survive the acquisitions.

Read the rules
08

VAJRA - physical AI build-in-public

Autonomous find-and-fetch robot on Jetson Orin Nano Super + ROS 2 Humble + NanoOWL (TensorRT-optimized OWL-ViT). Same governance instincts as Agentify (deny-by-default, budget routers, eval harnesses) re-applied to physical actions. Tabletop v0.1 milestone in motion.

Open VAJRA
09

Production work at Attri.ai

GenAI Architect & Tech Lead. 15+ specialized agents in production, 99.9% uptime, 70% cost reduction via cascading routers. Case studies for MannSetu (voice-first AI mental wellness) and Agentify (the platform).

Open case studies