Agent Runtime
4 essays tagged with Agent Runtime.
Inside ContextOS: Shared Business Limits for AI Agents
The first public ContextOS runtime deep dive: a deterministic Rust kernel, atomic business exposure across agent runs, governed tool dispatch, conservative recovery, signed evidence and Tower.
The Production Harness Roadmap: Lessons from Claude Code, Copilot Studio, and Thea
A concrete 90-day roadmap for building a governed agent harness, derived from the latest Claude Code, Copilot Studio, Thea, Harness-IF, and A2E evidence.
OpenWorker Review: A Real Desktop Coworker With an Unfinished Trust Runtime
OpenWorker already owns the agent loop, approvals, connectors, and desktop UX. Its next leap is containment, durable effects, replay, budgets, and evals.
What Production Agent Runtimes Actually Teach ContextOS: Twelve Laws of a Governed Harness
The strongest production agent runtimes converge on twelve architectural laws: compile context, persist state, separate authority from containment, make side effects resumable, treat approvals as typed interrupts, and promote learning only through evidence and replay.