Skip to main content
Jig is a framework for building software with an AI coding agent — Claude Code or Codex. You describe what you want in plain words; the agent decides how careful the work has to be, keeps the project’s knowledge up to date, and stops to ask you where a human decision matters. Jig lives inside your project. It adds a folder of project knowledge, a set of skills your agent uses, and a small command-line tool the agent runs for the mechanical parts. Nothing is hosted, there is no telemetry, and no script ever calls an AI model: the agent makes the engineering decisions, the scripts only keep records straight.

How working with Jig looks

You do not need to learn commands or skill names. You talk to your agent:
You: Add CSV export to the reports page. Agent: This touches the report pipeline and the download endpoint, so I classify it as structural (T2): analyze, plan, implement, review, verify. I have created the task csv-export on its own branch. Here is what I found in the code and the plan …
Behind that answer, the agent picked the jig-task skill, looked at the risk of the change, chose a route, created a task workspace and loaded only the project knowledge relevant to reports. The agent usually picks the right skill from what you say; when it does not, name it — /jig-task in Claude Code, $jig-task in Codex. A one-line typo fix gets a three-step route; a change to authentication gets design, your approval and an independent review.

What you get

Work sized by risk

Five classes, from a typo to a change that touches security or money. The route grows with the risk, never with habit.

Knowledge that stays true

Terms, architecture, rules and decisions live in .ai/knowledge/ next to the code. Every task ends by deciding what it taught the project.

You decide where it matters

At a human gate the agent shows you the design itself — not a summary — and waits.

Your existing docs, adopted

Rules you already keep in docs/, your own ADRs or another tool’s instruction files are linked in place, not copied.

Where to start

New project

Start from an idea: specification, architecture, rules, then the first tasks.

Existing project

Bring Jig into a codebase you already have, and adopt the documentation it keeps.
Jig runs on macOS, Linux and Windows. Install it first — one line in a terminal.