General-purpose enterprise orchestrator on Google ADK + Vertex AI Agent Engine. Multi-agent system with risk tiers (R0-R4), policy gates, evidence bundles, and Mission Spec v1 workflows.

A governed world-model evidence layer for AI agents: simulate bounded scenarios, track assumptions, score prediction-vs-reality error, and produce human-reviewable execution evidence.

Governed cognition substrate for AI engineering agents: mission envelopes, evidence-bound belief/plan graphs, quarantined memory, model-role review, sentinel checks, and BlackFox handoffs under human authority.

SZL Holdings monorepo — substrate runtime, agentic loops, MCP server (11 tools), reusable workflows, CI gates. Doctrine v7

The agent loop, embodied. Tool-using runtime + fail-closed safety pipeline + sim-first execution + statistically-rigorous bench harness + post-hoc analysis (counterfactual replay, causal attribution, LLM judge, property mining) for embodied AI. Sister project to GhostLM.

🛡️ Enterprise DevSecOps pipeline with Nexus Repository, security scanning, and policy gates

Governed agent runtime reference with policy gates, tool schemas, failure modes, and OpenTelemetry-shaped traces.

AO Operator profile for guarded coding-agent workflows, policy decisions, isolated workspaces, and evidence packs.

Local autonomous agent CLI for turning Codex and Claude Code subscriptions into repeatable agent teams. Start here.

Policy + receipt substrate — every action signed, every decision gated, every receipt verifiable. 46 policy gate modules · 11 MCP tools · Doctrine v7 · DOI 10.5281/zenodo.20434276

🔧 Build a secure DevSecOps pipeline with automated vulnerability scanning and policy gates for CI/CD, ensuring robust software delivery and compliance.