Agents fly the legs.
You land the change.
Atlas ADE sets up Claude Code and Codex in any repository, keeps a generated chart of your code, and drives every change through one short loop. It stops only when it needs you, with the next command already on screen.
$ ade card add "greet takes a name" \ --path src/greet.py --done "greet(\"Ada\") says hello"c1 next: ade loop c1$ ade loop c1lane advance lane ~/.ade-work/61eadb80/c1build advance built with claudereview advance light review approvedtest advance passed: tests/test_greet.pyland done landed c8b7669b5c$
Five legs. One control plane.
The loop is the autopilot. It flies the routine legs without waking anyone and hands control back the moment something needs judgement.
- 01 · laneIts own worktreeEach card gets an isolated git worktree, so builders never collide on your checkout.
- 02 · buildEither engineClaude Code or Codex makes the smallest change that meets the card's done line.
- 03 · reviewA patch, not a listReview by policy: none for prose, light for code. The reviewer hands back a fix.
- 04 · testWhat the change reachesTests are picked from the graph. An unknown path runs a small critical set, never everything.
- 05 · landOne verdictMerge, one outcome record, and any reds carried to a single residuals card.
Think of a small aircraft.
Every part of Atlas ADE has one job, the way every instrument on a panel does. Nothing flies the aircraft except the loop.
Agents start with context, not a blank slate.
The first time an agent touches a file, it is told who calls it, which tests cover it, which decisions govern it and the helper it should reuse. About 250 tokens, straight from the graph.
## Open cards - c2 log every greeting [src/greet.py] done: greet writes one line per call state: not started; next: ade loop c2 ## Graph (4 files; each edit is briefed from it) - src/greet.py: the starter's one function (1 callers) ## Budgets core lines 15 / 20000 ok hooks 4 / 5 ok refusal codes 26 / 50 ok ~233 tokens (budget 20000)
Small on purpose.
Budgets are the only standing gates, and every merge prints where the kit stands against them. Your telemetry stays on your machine.
PLACARDLIMIT
Core code~20,000 lines
Warm-up per role~20,000 tokens
Hooks≤ 5
Refusal codes, each with a cure≤ ~50
Whole test suite< 5 min
Get Atlas ADE
Start a new project on it in an empty folder, or install it into a repository you already have. One command either way, with a dry-run diff first and a clean uninstall.
$ ade init --dry-run $ ade init $ ade loop c1
- The
adeCLI for macOS, Windows and Linux - Claude Code and Codex from one roster
- Python and TypeScript starters, Orca or CLI-only cockpit
- The kit as it is when you buy it
- Everything in the kit
- Every kit release for 12 months
- One-off payment, no subscription
Bought the £14.99 kit? Add 12 months of updates for £12.99 from your account, whenever you like. VAT and sales tax are worked out at checkout.
Questions
Does anything leave my machine?
No. Usage and telemetry are recorded locally in OpenTelemetry shape and never sent anywhere.
Which engines does it drive?
Claude Code and Codex, from one roster. Agent definitions are generated for each from the same source, and ADE starts the real claude and codex binaries on your PATH.
Can I try it without spending usage?
Yes. Set ADE_PROVIDER=fake and every loop runs end to end with a fake engine. ade rehearse does one full loop per config option on throwaway repositories.
Do I need Orca?
No. Orca is an optional display that also carries alerts to your phone. The CLI-only mode has every instrument.
Will it change my global settings?
No. The committed settings hold permissions only. Machine-specific hooks go in a gitignored local file, and ade uninstall removes everything init generated.
What does it need?
Python 3.11 or newer and git. The TypeScript starter also needs Node 22.6 or newer.