A 250-line self-hosted background coding agent. Label a GitHub issue with `agent`, wake up to a draft PR. ~$0.30/task. The snapshot, the agent loop, the webhook server, and the dead ends I'd save you from.
Utpal Nadiger · June 1, 2026
Lessons from shipping Clawputer, a managed openclaw that lives in your iMessage. Patterns for VM lifecycle, versioning, OAuth integrations, and browser offloading when building AI coworkers on long-lived compute.
Mohamed Habib · May 22, 2026
A direct response to 'The agent harness belongs outside the sandbox.' Why credentials, hibernation, elasticity, and checkpoints make a persistent in-sandbox harness the better default.
Utpal Nadiger · May 4, 2026
Agent harnesses are to this era what WordPress was to the early 2000s internet. The race to build the next one is already on.
Igor Zalutski · April 19, 2026
From EC2 to agent sandboxes — how agents broke the compute paradigms we've relied on for 20 years, and what elasticity looks like now.
Igor Zalutski · April 7, 2026
Isolation models, agent placement tradeoffs, credential design, and sandbox lifecycle patterns for agentic systems.
Utpal Nadiger, Mohamed Habib, Igor Zalutski · March 20, 2026
From CGI scripts to serverless, web infrastructure evolved over 30 years. Now agents are taking us full circle - back to files and scripts.
Igor Zalutski · March 17, 2026
We fingerprinted 6 sandbox providers to understand their isolation models - from containers to microVMs to full hypervisors. Here's what we found.
Mohamed Habib · March 17, 2026
Agent code doesn't fit neatly into existing categories. It's not a traditional app, and it's not a CI job. It's something new.
Igor Zalutski · March 15, 2026
A series to build a lovable clone to learn how lovable works under the hood using Claude Agent SDK and OpenComputer.
Mohamed Habib · March 11, 2026