Local Quickstart

Run one small Task from request to acceptance.

Try a dependency-free task-list example, then bring the same workflow to your own repository.

1.2.0 manual

Read the workflow quickstart, Agent Teams contacts/session reference and init/config guide. Release Status records channel availability and the exact qualification scope; archived manuals keep their original version.

GitHub, npm and Server/Runner OCI latest defaults are verified for 1.2.0. These instructions use exact versions; WinGet review remains pending. See Release Status.

Use npm, native package channels, or an exact release archive

npm · JavaScript CLI and direct API

npm install --global @wa120/ait-native@1.2.0

The JavaScript ait CLI parses terminal syntax and calls the Node-API addon. The JS/TS API remains available; no separate native CLI or server executable is bundled.

Homebrew · macOS and Linux

brew tap weita2026/ait-native
brew install ait-native

The published formula targets 1.2.0 native archives and installs ait, ait-server and ait-runner, inactive by default. Follow the tap instructions and confirm the formula version.

Open the published formula

apt · Debian and Ubuntu

sudo apt install ait-native

The signed repository publishes exact 1.2.0 ait-native packages for amd64 and arm64. Follow its signed-repository and version-selection instructions.

Open apt instructions

Checksum-bound native archives

Use the exact v1.2.0 release files for your target and compare SHA256SUMS. Native archives provide the standalone CLI, Server and Runner; installation starts no background process.

Open 1.2.0 Release

Windows downloads

WinGet 1.2.0 pre-review passed and PR 468379 is submitted and awaiting review. No merge, discovery or public-source install result is reported. Use the exact 1.2.0 native ZIP files below; their publication is separate from WinGet availability.

AIT · 1.2.0

Your first Task, with a result you can check.

Install AIT above, then use a new folder for this example. You need Node.js 22 or newer and your own coding agent. Node.js is only a requirement of this example; the agent may use your model-provider account.

  1. 1. Extract and check the starting point

    Extract the ZIP with your file manager. Open a terminal in the extracted ait-first-task directory. These three baseline tests should pass. No npm install is needed.

    node --version
    node --test tests/baseline.test.mjs
  2. 2. Initialize the example

    Complete initialization here, then start a fresh coding-agent session in this directory. AIT generates managed workflow blocks in AGENTS.md and CLAUDE.md; tools that support the corresponding repository instruction file can load it at session startup.

    Replace your-name with the name you want recorded for local Task review. Task start records the initial baseline as part of initialization. Create later checkpoints only in the returned Task worktree, using its Task ID; use this preparation only in the fresh example directory.

    ait init
    ait config set --user-name "your-name"
    See exactly what initialization changes →
  3. 3. Give your agent this request

    Add openTasks(tasks) to src/tasks.mjs: return a new array of tasks whose done property is not true, in the original order, preserving the task objects and input data. Keep taskTitles working. Add focused tests. Do not edit checks/, remove existing tests, or add dependencies. Run the existing tests and node checks/first-task.mjs before finishing the Task.
  4. 4. Verify the result in the original folder

    After the agent reports Task finish, return to the original extracted directory and run both checks. The feature check is expected to fail before implementation.

    node --test tests/*.test.mjs
    node checks/first-task.mjs

    The feature check prints FIRST_TASK_ACCEPTED when its cases pass. Also review the actual Task finish result: the Task is complete, its worktree is cleaned, and the bound sprint item is closed where applicable. Feature acceptance and workflow completion are separate checks.

If you get stuck

If node or ait is unavailable, complete the corresponding installation first. If your tool does not automatically load repository instructions, configure its instruction-file integration or ask it to read the generated AGENTS.md (CLAUDE.md for Claude Code) before retrying in a fresh session. If a check fails, give the failure to the same Task; preserve the check and repair the feature. A conflict remains unfinished until resolved and checked.

Next: try three compatible Tasks in parallel

Use a fresh extraction and initialize it. Open three separate agent sessions in that repository. Give each its own request and require it to follow AGENTS.md, bind a sprint item, work only in its returned edit_root, and preserve checks/ and existing tests. Use separate test files. Request A is the first request above.

Repeat the complete initialization step above before opening the three fresh sessions.

Request B: In src/labels.mjs, add taskCountLabel(count) for non-negative integers. Return "1 task" for 1, otherwise "N tasks". Preserve boardTitle. Add tests in a separate file, run the existing tests, and finish the Task.
Request C: In src/priority.mjs, add priorityRank(value). high, normal, and low return 0, 1, and 2; unknown or absent input returns 3. Preserve priorityOrder. Add tests in a separate file, run the existing tests, and finish the Task.

After all three Tasks finish, run these commands in the original directory. Expect PARALLEL_TASKS_ACCEPTED. This exercise covers compatible changes; it does not force a conflict or measure throughput. Keep a record of any real conflicts, failed checks, and intervention.

node --test tests/*.test.mjs
node checks/parallel-tasks.mjs

The repository trust boundary

See exactly what ait init changes.

Run it from the repository your coding agent will modify.

cd <your-repository>
ait init
  • Creates repository-local .ait/ state and docs/sprints/.
  • Creates or refreshes clearly marked workflow blocks in AGENTS.md and CLAUDE.md.
  • Preserves user-authored content outside the managed blocks in both files; rerunning init does not duplicate the blocks.
  • CLAUDE.md has its own workflow block with Claude-specific instructions to select an absolute --edit-root and enter it with cd. Recognized legacy AIT pointer text is migrated to this block.
  • Starts no server and sends no repository data anywhere.
If you later remove the repository integration

AIT 1.2.0 deliberately has no one-command repository uninstall. Preserve .ait/ first if its history matters, remove only the marked AIT blocks from AGENTS.md and CLAUDE.md, and preserve user-authored content in both files. Delete a generated file only after confirming it contains no content you want to keep. Sprint Markdown may be user-authored, so never delete docs/sprints/ blindly.

For an existing project, use the current init/config reference. An already governed AIT repository should keep following its current AGENTS.md.

Choose a small, reviewable change in your own project once the example works.

Ask your coding agent the way you normally would

Add an accessible password-visibility control.
Leave the login API alone, and add the tests.

The generated repository instructions tell the agent to record the request, start an isolated Task, run the checks, and finish the verified result. You do not need to translate the request into AIT commands.

Check the local state

ait --version
ait status --json
{
  "ok": true,
  "line_name": "main",
  "workspace": { "status": "clean" },
  "next_action": null
}

Now give the agent one real task.

Review the finished change, then choose another small task in your own project.