Strategy: the trust and preparation contract for coding agents on microVMs
Provide a reusable guest daemon, client libraries, and dated AWS observations for teams building on Lambda MicroVMs. Scheduling, pooling, and task routing belong to consumer applications.
Diagnosis
Section titled “Diagnosis”A workload and its control daemon share the guest. Bootstrap, credential handling, filesystem operations, and lifecycle recovery therefore need explicit contracts. Image preparation is also a recurring cost: dependencies can be built once and reused across launches.
The platform changes independently of this package. SDK models describe request shapes; only runtime measurements establish service behavior. Platform records those observations, each with its date and one current answer.
Guiding policy
Section titled “Guiding policy”Keep shared behavior in core and use thin CLI/Python/Node adapters. Validate requests before billable operations, preserve specific errors, and test failure paths. State limits directly: guest root is not isolated from the daemon, metadata exposes the execution role, and internet isolation requires a correctly configured VPC connector.
Coherent actions
Section titled “Coherent actions”- Maintain the wire protocol and trust contract, with model, unit, property, and live conformance coverage appropriate to each claim.
- Reuse images by build inputs and dependency lockfiles. Keep per-run code and credentials out of shared snapshots.
- Maintain published CLI and language packages from one implementation. Refresh API references with boto3 and check serializer/SDK parity.
- Keep documentation short: tutorials explain tasks, generated references describe contracts, and platform notes keep one dated answer per question.
The agent helpers are a deliberate convenience layer over core primitives; Agent VMs defines their bounded scope.
What we are deliberately not doing
Section titled “What we are deliberately not doing”- A scheduler, pool manager, or general orchestrator.
- Guest-side process-tree cloning as a substitute for provider snapshots.
- A new turn-boundary suspend protocol: consumers can use existing lifecycle calls and endpoint health polling.
The AWS ask, and the honest bet
Section titled “The AWS ask, and the honest bet”Reusable snapshots of running VM state require provider support. Existing suspend/resume preserves a single VM, but does not establish a reusable clone API. Prefer measured capabilities over predictions about future AWS features.
How we would know this worked
Section titled “How we would know this worked”Consumers can integrate the daemon without rediscovering bootstrap or network assumptions, reuse environments across launches, and upgrade packages without surprises between the CLI and language bindings. Live coverage remains scoped to the regions and paths actually exercised.
Check existing capabilities before adding an abstraction
Section titled “Check existing capabilities before adding an abstraction”Existing hooks and lifecycle APIs already cover a turn-boundary suspend, so the project adds no convention for it. Human interactive idle time and headless batch workloads have different idle patterns, so plan for each separately. Measure the target workload and check existing platform capabilities before adding an abstraction. Research notes are in git history.