Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.litellm-agent-platform.ai/llms.txt

Use this file to discover all available pages before exploring further.

LAP architecture

Components

ComponentWhere it runsWhat it does
WebNext.js app (Render / EKS)UI, REST API, session orchestration
WorkerBackground processReconciler for session lifecycle, idle reaping
Sandbox controllerKubernetes (kind / EKS)Manages Sandbox custom resources from kubernetes-sigs/agent-sandbox
Harness podInside the sandboxRuns the agent — Claude Code, Codex, opencode, claude-agent-sdk
Vault sidecarInside the sandboxHTTPS proxy; swaps stub credentials for real keys at the wire

Request flow

  1. Client (UI / CLI / API) hits the web service.
  2. Web creates a Sandbox CR; the controller schedules a pod.
  3. Pod boots with vault sidecar + harness container. Stubs are injected into the harness env.
  4. Harness clones the repo, installs deps, listens on its protocol — JSON (/message) or PTY (/tty).
  5. Client streams messages or attaches a terminal.
  6. Outbound HTTPS from the harness flows through the vault sidecar, which swaps stubs for real credentials.

Why Kubernetes

  • Portable: kind locally, EKS / GKE / AKS / on-prem in production.
  • Pod-level isolation, RBAC, network policies — off-the-shelf.
  • gVisor / Kata runtimes available via the CRD’s runtimeClass.
  • No cloud-provider lock-in for the sandbox runtime path.