Agent Lab Get in touch

In development · Developer tooling

Agent Lab

Let a coding agent run with the brakes off, inside a box where that is safe.

Engineers who want agent throughput without giving one root on their laptop.

Get in touch See it working
Animated illustration of Agent Lab agent-lab — session $ agent-lab run --scope . resolving workspace … Docker indexed 1,284 files · 96 changed analysis complete — 4 findings, 0 blocking $ agent-lab report --format=json written to ./report.json UNCHECKED UNWRAP IN RETRY PATH src/net DUPLICATE CONFIG PARSE src/cli DEAD BRANCH AFTER EARLY RETURN src/store TEST ASSERTS ON FORMATTING tests
Animated schematic of a representative session. Command names are real; timings are compressed for the page.
Built on
Docker + Shell
Fits the workflow
A step in the pipeline, not a replacement for it
History
37 commits, in the open record

What it is

Agent Lab lets Codex and Claude Code run in their fully unrestricted modes while Docker confines them to the one project folder you explicitly mount. The dangerous setting becomes the safe setting because the blast radius is the container.

Logins for the agent CLIs, GitHub and Google Cloud live in Docker-only named volumes, so credentials survive between sessions without ever sitting in the sandbox filesystem. One install script sets up a new machine.

Capabilities

What it actually does.

Engineers who want agent throughput without giving one root on their laptop.

  1. Unrestricted agent modes

    Unrestricted agent modes confined to an explicitly mounted project directory

  2. Credentials isolated in

    Credentials isolated in Docker-only named volumes, never in the sandbox tree

  3. Single install script

    Single install script; images build on first use

  4. One command surface

    One command surface across both agent CLIs for logins and MCP servers

How it works

3 moves, end to end.

This is how Agent Lab works, not a set of steps you can follow yet — it is in development and not distributed.

  1. Drop it in

    Agent Lab attaches to the repository or project you already have.

  2. Give it the job

    It takes a concrete task with a defined output, not an open-ended prompt.

  3. Review the result

    Everything it produces is a diff, a file or a report you approve before it counts.

The full technical description

Specification

Made of, and made when.

Read from the repository at build time rather than typed onto a marketing page.

State
In development
Discipline
Developer tooling
Shape
Developer tooling
Started
Aug 2026
Last change
Aug 2026
Commits
37
  • Docker
  • Shell
  • PowerShell
  • Claude Code
  • Codex
  • Shell 44%
  • JavaScript 27%
  • PowerShell 24%
  • Dockerfile 5%

Related work

Built alongside Agent Lab

rev-local Autonomous code review that never uploads your repository Andare Code A desktop daemon that closes tracker work with a coding agent ctxfs A copy-on-write filesystem for running many agents against one repository

Next

Put Agent Lab in your pipeline

Ask about integrating it with the repositories and agents you already run.

Email dmoore@dwmmholdings.com Read the source

This is a pre-production site. All content is subject to finalisation, and nothing stated here is binding until the site is live.