Install Agent Layer once per machine, then initialize each repo you want to use. The CLI is named al.
Requirements
- A supported client installed separately (Antigravity
agy, Claude, Codex, Copilot CLI, Grok, or VS Code with thecodecommand onPATH)
Agent Layer does not install clients for you.
If you manage multiple repos, you still install al only once. Each repo gets its own .agent-layer/ config.
Homebrew (macOS/Linux)
brew install conn-castle/tap/agent-layer
Script (macOS/Linux)
curl -fsSL https://github.com/conn-castle/agent-layer/releases/latest/download/al-install.sh | bash
The script installs to ~/.local/bin by default and verifies checksums. If ~/.local/bin is not on your PATH, it prints an exact line to add.
If you prefer not to pipe a script into your shell, download it first and inspect it:
curl -fsSL -o al-install.sh https://github.com/conn-castle/agent-layer/releases/latest/download/al-install.sh
less al-install.sh
bash al-install.sh
By default, the script also installs shell completions for your current interactive shell. You can manage completions manually with al completion <bash|zsh|fish> --install.
Verify
al --version
First run
cd /path/to/repo
al init
al <client> # e.g., al claude
al init seeds:
.agent-layer/for configuration- a managed
.gitignoreblock
By default, al init prompts to run the setup wizard. The wizard can seed instruction files and docs/agent-layer/ project memory, and can install catalog skills. Skip it with --no-wizard if you prefer to configure manually.
You can also run al wizard later to revisit approvals, enabled clients, MCP servers, and warnings.
For a safe evaluation, run al init in a disposable repository first.
Recommended next steps
- Read the docs: /docs/getting-started
- Run
al doctorto validate config and MCP connectivity - Edit
.agent-layer/instructions/to set team rules - Review
.agent-layer/commands.allowto keep approvals tight - Enable only MCP servers you trust (see /docs/concepts#mcp-servers)
- Skim /security for network behavior and secret handling
Update
Update the global CLI:
al update
al update detects whether the running release binary is owned by Homebrew. It upgrades the formula when it is, and otherwise downloads and reruns the official installer while preserving the current install prefix.
If the installed CLI predates the al update command, update it once with brew upgrade conn-castle/tap/agent-layer for Homebrew or by rerunning the original script install command (including the same --prefix, if any).
Run al upgrade plan and then al upgrade inside the repo. This updates the repo pin (.agent-layer/al.version) and refreshes template-managed files.
For a concise runbook (interactive + CI), use /docs/upgrade-checklist.
For the full upgrade policy (event model, compatibility guarantees, migration rules, and platform matrix), see /docs/upgrades.
To upgrade a repo safely, use al upgrade plan (dry-run) and then al upgrade (apply).
For CI-safe non-interactive apply, use al upgrade --yes --apply-managed-updates. Include --apply-memory-updates and/or --apply-deletions only when explicitly intended.