https://github.com/LiteLLM-Labs/litellm-agent-control-plane
1 place to call all your agents - OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, DeepAgents.
https://github.com/LiteLLM-Labs/litellm-agent-control-plane
agent-builder agent-builder-tools agent-platform agent-vault ai-gateway claude-code codex codex-cli litellm litellm-ai-gateway sandbox
Last synced: about 2 hours ago
JSON representation
1 place to call all your agents - OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, DeepAgents.
- Host: GitHub
- URL: https://github.com/LiteLLM-Labs/litellm-agent-control-plane
- Owner: LiteLLM-Labs
- License: mit
- Created: 2026-05-07T21:35:39.000Z (about 2 months ago)
- Default Branch: main
- Last Pushed: 2026-06-20T20:58:35.000Z (3 days ago)
- Last Synced: 2026-06-20T22:19:24.717Z (3 days ago)
- Topics: agent-builder, agent-builder-tools, agent-platform, agent-vault, ai-gateway, claude-code, codex, codex-cli, litellm, litellm-ai-gateway, sandbox
- Language: Rust
- Homepage: https://docs.litellm-agent-platform.ai
- Size: 79.1 MB
- Stars: 967
- Watchers: 8
- Forks: 101
- Open Issues: 13
-
Metadata Files:
- Readme: readme.md
- License: LICENSE
- Agents: AGENTS.md
Awesome Lists containing this project
- awesome-agent-harness - GitHub - 970-f4b400?style=flat-square)](https://github.com/LiteLLM-Labs/litellm-agent-control-plane) | control-plane, sessions, runtime | Agent control plane that provides one API and UI across OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, DeepAgents, and OpenClaw runtimes. | (Catalog / Harness Architecture & Orchestration)
README
# LiteLLM Agent Control Plane
1 place to call all your agents - OpenCode, Hermes, Claude
Managed Agents, Cursor Agents API, Deep Agents.
[](https://discord.gg/Nkxw3rm3EE)
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.
```bash
docker compose --profile opencode up
```
Open [http://localhost:4000](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:
```bash
docker compose up
```
To start other template runtime profiles and add them to the UI automatically:
```bash
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](docs/engineering/contributing.mdx).