Index of items under the local-experiments catalog directory.
A minimal cloud baseline focused on identity, networking, and cost control.
A first-time Azure run that turned identity and networking into the real curriculum.
A small experiment to see where longer context starts to degrade quality.
A first cloud baseline with focus on projects, IAM, and network rules.
A new launcher flow that hands local models into tools like Codex and OpenCode.
A baseline run to learn where M1 throttles and why it matters.
A first clean install that taught me where local stacks really fail.
How I built a policy-governed MCP runtime where models can reason freely but execution stays deterministic, verifiable, and auditable.