Platforms and session credits
A platform is the runtime used by the agent. Agent Types in Background agent settings controls the choices available to your organization. Only enabled platforms appear in the creation form.
Platforms
| Platform | platform | Setup | Description |
|---|---|---|---|
| Willow Agents | willow-agents | None | Run the agent on Willow's fully managed infrastructure. Each new agent session consumes one of your organization's monthly session credits. |
| Custom | custom | None | Bring your own runtime. Download the agent as a ZIP bundle or connect any host with the agent's MCP configuration. See Custom Agents & Self-Hosted Harnesses for runtime integration. |
| Claude Managed Agents | claude-managed-agents | Set key | Run the agent on Anthropic's managed infrastructure. Syncs the agent definition, tools, and gateway credentials to Claude. Needs an ANTHROPIC_API_KEY. |
| Claude Tag | claude-tag | None | Expose the agent's tools to @Claude as a connected app, either as an MCP connector or as REST endpoints. Skills and webhooks are not supported yet. See Connect Claude Tag. |
| AWS AgentCore | aws-agentcore | Set credentials | Run the agent as an Amazon Bedrock AgentCore harness. Syncs the agent definition, gateway tools, and credentials to your AWS account. See Connect AWS AgentCore. |
| Cursor Cloud Agents | cursor-agents | Set key | Run a coding agent on Cursor's cloud infrastructure, with Willow tools connected through MCP. |
| kagent | kagent | Connect | Run the agent through a kagent controller in your cluster, referencing a SandboxAgent. See Connect kagent for setup. |
| Snowflake Cortex Agents | snowflake-cortex-agents | Connect | Run the agent as a Cortex agent object in your own Snowflake account, answering over Cortex Analyst and Cortex Search tools. Needs an account identifier and a programmatic access token. See Connect Snowflake Cortex Agents. |
| Your own type | custom-managed | Add custom type | A runtime you register with push or pull delivery. See Add a custom agent type. |
| — | codex | API only | Accepted by the API with no card in Agent Types. |
| — | langgraph | API only | Accepted by the API with no card in Agent Types. |
The first eight ship as cards in Agent Types. custom-managed is what Add custom type creates. The API also accepts codex and langgraph; neither has an Agent Types card.
custom-managed does not have to mean building a harness yourself. Willow ships one as a Helm chart: install it, register it as a custom type, and every agent you create gets a dedicated pod in your Kubernetes cluster. See Run Agents in Your Own Cluster.
A custom runtime can call Willow to access its assigned tools. Willow can also deliver conversation turns to configured harness endpoints. The endpoints and authentication differ between Custom and a registered Custom Managed type. See runtime integration and the harness delivery contract.
Platforms that need credentials stay switched off until you supply them, and appear in the create dialog only once enabled. The Agent Types card in settings is the source of truth for what your organization can currently select, and Add custom type defines a platform of your own beyond this list.
Managed platforms keep an external copy of the agent, which you push with Deploy.
Session credits
Agents on the Willow Agents platform draw on a monthly pool of session credits. Each new agent session uses one credit.
The balance and next reset date appear on the Background Agents inventory. Deployment & Sync also displays Willow Agents credit information. Use the date shown in your organization.
Credits apply only to Willow-hosted agents. Other platforms use their own infrastructure and billing arrangements.
API platform values
Create/update schemas also accept codex and langgraph, which have no Agent Types card. An accepted API value does not imply that a runtime can be configured through the dashboard. See the Create Background Agent schema.