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.
New in v0.3.0: benchmark-based choice never overrides what you configured. Your pinned models, tier pools, effort caps and task floors stay in force throughout. oah does not edit your config: a pin always wins, effort_caps clamp to a supported level, and the old default quality_order simply counts as unset.
When you need it
An automatic chooser that ignores the models you have checked, or your budget limits, would make every update a risk.
How it works
Pin a model for a tier with [engines.<engine>.tiers] <tier> = { model = "<model>" } in .oah/config.toml; a pin always wins.
tier_pools, your own quality_order, allowed_models and effort_caps keep their meaning.
effort_caps clamp to a supported level and record OAH_EFFORT_CAPPED; a cap below a model's floor skips that model.
The old default quality_order = ["opus", "sonnet", "haiku"] counts as unset (OAH_MODEL_ORDER_IGNORED); remove the line, or list other models to rank them yourself.
Codex's default flag and the model in your Codex configuration no longer choose; to keep one model, pin it.
Example
Pin a model for a tier in `.oah/config.toml` (from Concepts and Upgrade).
[engines.<engine>.tiers] <tier> = { model = "<model>" }
Requirements
Available in the v0.3.0 model chooser.
Limits and recovery
An unrunnable pin stops with OAH_CONFIG_INVALID.
A narrow allowed_models no longer lowers a floor; when no allowed model reaches it, a review stops with OAH_MODEL_BELOW_FLOOR and any other call with OAH_MODEL_UNRESOLVED.
Claude Code accepts names it does not print, so Claude pins are not checked against a list.