Skip to content
@hullwork

Hullwork

Open, self-hosted infrastructure for dependable AI agents — secure execution and verified delivery on Kubernetes.
Hullwork — open infrastructure for dependable AI agents

Infrastructure for agents that do real work

Hullwork builds open, self-hosted infrastructure for AI agents that need to execute code and ship software—not just generate an answer.

An agent is dependable only when its execution boundary and delivery evidence are explicit.

Our public projects cover the path from an agent request to a result you can trust:

agent requestsecure executionverified deploymentobservable result

Hullwork system path from agent intent through secure execution and verified deployment to evidence

Two systems. One dependable path.

Sandbox — Secure execution for AI agents

Run an agent's shell and file operations inside a dedicated Kubernetes gVisor Pod. The self-hosted control plane manages durable workspaces, tenant-scoped credentials, quotas, checkpoints, and runtime lifecycle—without ever falling back to host execution.

Interfaces: Python SDK · CLI · MCP   |   Proof: architecture · benchmarks · live project site

Site — Verified website delivery for AI agents

Turn an agent's deployment request into a real Kubernetes workload through HTTP, CLI, or MCP. The control plane handles tenancy, quotas, builds, ingress, observability, and scale-to-zero—then makes a real HTTP request and records the status code and body digest.

Interfaces: HTTP API · CLI · MCP   |   Proof: architecture · one-command demo · live project site

What we optimize for

Principle Engineering consequence
Boundaries over promises Untrusted code runs with explicit identity, resource, network, and runtime isolation.
Evidence over status labels A deployment is successful only when the running address has been measured.
Fail closed Missing control-plane or runtime dependencies never become permission to execute on the host.
Composable interfaces HTTP APIs, CLIs, SDKs, and MCP tools keep products useful without hidden coupling.
Operator ownership Workspaces, credentials, state, and deployment infrastructure stay in your environment.

Start with the boundary you need

  • Need to execute agent-generated code safely? Start with Sandbox.
  • Need to turn a generated site into a verified deployment? Start with Site.
  • Evaluating the architecture? Read each repository's explicit known limitations before adopting it.
Build the boundary. Measure the result.

Pinned Loading

  1. sandbox sandbox Public

    gVisor-isolated Kubernetes sandbox with an HTTP API, SDK and MCP bridge

    Python 1 1

  2. site site Public

    Website build and deployment control plane

    Python 1

Repositories

Showing 4 of 4 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…