How Ramp built a full context background coding agent on Modal | Modal Blog

This post details how Ramp built a full-context background coding agent ('Inspect') on Modal Sandboxes. Key technical contributions include: leveraging Modal Sandboxes to spin up full development environments (Postgres, Redis, Temporal, RabbitMQ, etc.) in seconds for AI agents; integrating agents with Ramp's stack (GitHub, Slack, Buildkite, Sentry, Datadog) for end-to-end verification; using Modal Functions on a cron job to clone repos, install dependencies, and build filesystem snapshots for near-instant sandbox startup; utilizing Modal Dicts for session locks and image metadata coordination; and employing Modal Queues to route prompts and decouple input from execution for multiplayer collaboration. The focus on matching local agent speed via filesystem snapshots and providing unlimited scale through sandboxes is highlighted.
More from the Sandboxed Code Execution trail
- Runtime Roundup: VM Sandboxes, Multi-node clusters, and more | Modal Blog
- VM Sandboxes: Full computers for agents | Modal Blog
- Sidecars: A low-latency trust boundary for Sandboxes | Modal Blog
- Product updates: Sandbox Sidecars, new models, a refreshed dashboard, and more | Modal Blog
- Devin Outposts on Modal | Modal Blog