Operations
10 engineering articles on operations from building and running Swarm 357 in production.
Status26 July 2026
Swarm 357 mid-year status: what is Stable, Beta, and not built
The July 2026 maturity picture in plain language. What hardened this year, what is still Beta and why, and the four things that are explicitly not implemented.
Scenarios29 June 2026
Scenario: a sales layer that stops at the CRM handoff
A worked scenario for research, drafting, and handoff notes, with the send left to a human. What the sales layer refuses to do, and why that line matters.
Operations22 June 2026
Durable checkpoints: resume, cancel, replay, and fork
A run that dies at step nine should not restart at step one. How SQLite-backed state turns a crash into a resume, and why cancel must be a persisted flag.
Definitions26 May 2026
What an agent swarm actually means in production
The word swarm gets used for three different systems. A definition that survives a security review, plus the four vendor claims that do not hold up.
Deployment12 May 2026
Deploying a Claude agent runtime on Railway
Split the API from the landing site, keep write keys server-only, force simulate on the public demo, and let the container make Bash fail closed.
Evals28 April 2026
How to actually evaluate an agent swarm
Single-agent and swarm metrics measure different systems. An eval methodology with budget caps, baselines in version control, and the numbers that lie.
Security24 March 2026
Human-in-the-loop approvals for autonomous agents
A durable ApprovalRecord, a control plane on both CLI and HTTP, and timeouts that reject. Putting a person in front of side effects without stalling runs.
Security10 March 2026
Why your agent needs a bash policy gate
Thirteen patterns, argv-level validation, and a deny-by-default posture in production. What a bash policy gate stops, and the three things it will never stop.
Memory24 February 2026
Portable agent memory with Memvid
Flat-file topics for memory you read, a single-file .mv2 archive for memory you search. How the Memvid bridge gives agents recall you can copy and diff.
Cost control10 February 2026
Cost control for LLM agent fleets
Layer budgets, an atomic ledger, and a logged downgrade at 80 percent. The FinOps primitives that keep a multi-agent run from becoming a surprise invoice.