LiteLLM-Labs/litellm-agent-control-plane
1 place to call all your agents - OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, DeepAgents.
What it solves
LiteLLM Agent Control Plane provides a centralized management layer for AI agents, allowing teams to create, run, and monitor agents across multiple different agent runtimes from a single interface.
How it works
The platform acts as an abstraction layer that sits on top of various agent runtimes (such as Claude Managed Agents, Cursor, or OpenCode). It provides a unified API, a web-based dashboard for configuration, and infrastructure for session management, persistent memory, and scheduled execution (CRON). It uses Docker to deploy the platform alongside specific runtime profiles.
Who it’s for
This is for developers and teams who need to manage multiple AI agents across different platforms without needing individual access to various provider consoles (like Bedrock or Anthropic) and who want a centralized way to handle agent persistence and scheduling.
Highlights
- Unified API for creating and executing agents across diverse runtimes.
- Centralized dashboard for team-wide agent management.
- Persistent memory and session management for agent interactions.
- Built-in support for CRON-based agent scheduling.
- Easy deployment via Docker Compose with support for multiple agent runtime profiles.
Related
- Project
- Project
- Project
- Project