Claude Code

Open a Kubernetes-sandboxed Claude Code session from your terminal.

The lap CLI talks to a running LAP instance. If you haven’t deployed one yet, see Installation.

First time? Install the CLI:

git clone https://github.com/BerriAI/litellm-agent-platform.git
cd litellm-agent-platform/cli && npm install
ln -sf "$PWD/bin/lap.mjs" ~/.local/bin/lap

1. Log in

lap login

Paste your LAP URL and MASTER_KEY when prompted. Saved to ~/.lap/config.json.

2. Open an agent

lap

Pick your Claude Code agent from the interactive list. lap spins up a Kubernetes-sandboxed pod running Claude Code, attaches your local terminal to its TTY over a WebSocket, and drops you straight in.

The pod’s env contains only stub credentials. The vault proxy swaps them for real keys on every outbound TLS connection.

Press Ctrl-D to detach — the session stays alive for 24h. Run lap again and pick the same agent to reattach.

---

Creating an agent

If you’re setting up the platform, create a Claude Code agent first. In the UI choose claude-code from the Harness picker and pick a model, or via API:

curl -X POST $LAP_URL/api/v1/managed_agents/agents \
  -H "Authorization: Bearer $MASTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name":"my-claude","harness_id":"claude-code","model":"anthropic/claude-sonnet-4"}'