litellm-agent-control-plane

LiteLLM Agent Control Plane

1 place to call all your agents - OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, Deep Agents.

LiteLLM Agent Control Plane sits on top of any runtime. Pick a runtime, create an agent, give your team one UI.

It manages:

• Unified API across runtimes - one API to create and run agents, regardless of the runtime underneath
• Access - developers create and run agents here, no Bedrock or Anthropic console access required
• Session management - persistent agent sessions across runs
• CRON schedules - run agents on a schedule
• Memory - agents remember context across sessions

Quick Start

Prerequisite: Docker Desktop.

docker compose --profile opencode up

Open http://localhost:4000 and sign in with the master key (sk-local by default). Compose starts the LiteLLM Agent Platform web/API service, a Postgres database, the OpenCode template runtime, and registers local-opencode in the UI automatically.

To start only the base LAP stack:

docker compose up

To start other template runtime profiles and add them to the UI automatically:

docker compose --profile deepagents up
docker compose --profile hermes up
docker compose --profile openclaw up
docker compose --profile opencode --profile deepagents up

Profiles register local-opencode, local-deepagents, local-hermes, and local-openclaw through the LAP API after the services are healthy. Add provider credentials in Settings before running agents against a hosted model provider.

Usage: Create an Agent

1. Make an agent in the UI

2. Select tools and skills to connect to your agent

3. Use your agent

Select your agent and the runtime you want to run it on.

Supported Agent Runtimes

• Claude Managed Agents
• Cursor Agents API
• OpenCode Agents
• OpenClaw Agents
• Deep Agents
• Hermes Agent

Contributing

PRs welcome. See docs/engineering/contributing.mdx.