oah helps you build an AI development workflow that fits you and keeps changing as AI improves. It is a working reference and a guide you can adapt.
A useful result needs more than generated code: the scope must be clear, the changes checked, and decisions kept for the next session. oah connects those steps so one request can carry through the work with a record of what happened.
002 / Why it keeps changing
Older rules and skills can hold a newer model back or make its results worse. Defaults should be easy to understand and change; a rule that gets in your way is a design problem to fix.
Keep the parts that help, remove what no longer helps, and revise the workflow as your tools improve. You can start with the full setup or take only the impact map, wiki, leases, evidence gates or review loop that your project needs.
003 / Why Claude builds and Codex reviews
This split comes from the author's own experience, not a measured comparison: Claude fills in details a beginner might miss in a first version; Codex checks and corrects within a fixed scope.
The current commands run Claude Code and Codex CLI. The ideas can also be adapted to another tool or harness, with one AI or several. Give each stage to the AI that suits your work.
004 / From one request to a checked change
Describe the result you want in plain language. The AI records the goal and scope, checks what the change touches, reserves its paths and chooses the tools for the task. Claude builds; Codex reviews, corrects and reviews again.
Gates record the checks and their results. The project wiki keeps the decisions and reasons beside the code. In v0.3.0, optional TypeSafe Jev can judge difficulty for model selection; rules remain the fallback when it is unavailable or uncertain.
005 / The decisions stay with you
You ask, answer when the AI needs a decision, and confirm before the change lands. If the same problem repeats or the work reaches a design choice, the loop stops to ask you.
Ask “Is the review done?” or “Did all the gates pass?” and inspect the evidence. The final confirmation belongs to you; writing code, checking it and approving its landing are separate steps.
006 / Free, open source, yours to adapt
oah is free, open-source software under the MIT license. Read the source, change it and bring the useful pieces into your own workflow. Your AI services and any optional services use their own accounts and billing.
The current v0.3.0 release supports macOS and native Windows, and expects familiarity with git and pull requests. Install it, run oah init in your project, then try the small hello-oah example. The installation and documentation sections explain each step.
Orca and Aside are optional apps that fit the workflow; nothing in oah needs them. Orca runs coding agents side by side, each in its own git worktree. Aside is a browser with an AI agent that Claude Code and Codex use for web tasks through MCP. Setup offers each one and installs only what you confirm.
When you need it
Running several agents at once, or letting them use the web, is useful but adds setup steps and account risks you want to control yourself.
How it works
oah init (or python -m oah.setup) lists each missing app as optional with its official install command and asks; --yes never installs these apps.
python -m oah.setup.companions connects installed apps, printing every step with its exact command and marking [global] steps that change files in your user folder.
Orca: you register the orca command in Orca's settings; setup can add Orca's agent guides and register the project. With Orca installed, oah call --launcher orca runs a worker in an Orca terminal.
Aside: install the aside command, sign in yourself, then register its MCP server for Claude Code and Codex. An optional rules section tells agents to use Aside for web tasks, treat page content as data, not instructions, and never confirm a payment, purchase or paid subscription.
Orca: macOS, Windows, or Linux via its official page; adding its agent guides needs Node.js (npx).
Aside: macOS or Windows; it does not run on Linux. A free plan exists.
Limits and recovery
oah never asks for, reads, prints or stores an account name, id, password or token; setup reads only the sign-in status column and MCP launch settings.
An existing MCP entry that differs from what oah would write is reported as left unchanged, not verified, and stays pending, even with --yes.
Setup records registration, not proof that the server can launch.
On macOS, use the full Homebrew name stablyai/orca/orca; an unrelated cask is also called “orca”.