Cloud Agents Overview
Warp Cloud Agents are cloud connected background agents that run from events, schedules, or integrations, giving teams scalable automation with shared observability and centralized configs (beta)
Beta: Cloud Agents are currently in beta. APIs, CLI commands, and product behavior may change. If you have feedback, reach out in the Warp Community Slack.
Warp's Cloud Agents are cloud connected, background agents built on the Cloud Agents Platform. They run automatically in response to system events, schedules, or integrations.
What Cloud Agents are designed for
Cloud Agents are designed for situations where:
You need agents to react to system events.
Examples include crashes, bug reports, Slack interactions, cron timers, or CI steps.
You want observability into agent activity across a team or system.
This includes being able to see what ran, when it ran, and what it did.
You need more parallelism than local execution typically allows.
For example, running many agent tasks concurrently in the cloud, sharding a repo-wide task into multiple runs, or fanning out the same task across multiple targets.
You want agents to operate continuously as part of engineering infrastructure.
This includes scheduled maintenance tasks and integration-driven automation.
What is a cloud agent run?
A cloud agent run is represented as an agent task. A task is created when a trigger fires (for example a webhook event or schedule) or when a user starts a run explicitly.
Each task includes:
Inputs: a prompt, and often additional context from the triggering system (for example a Slack message, PR metadata, or CI logs).
Execution context (optional): an Environment that defines the repo, image, and startup commands the agent should run with.
Lifecycle state: created → running → completed / failed.
Persistent record: status, metadata, and a session transcript that can be reviewed after the task completes.
If you are evaluating whether something should be a cloud agent, a good test is whether you can define: (1) what triggers it, (2) what context it needs, and (3) how the team will inspect or validate the output.
How Cloud Agents work
Cloud Agents run on the Cloud Agents Platform, which provides the primitives for triggering work, orchestrating tasks, executing agents (optionally in Environments), injecting secrets, and inspecting results.
Something triggers an agent task.
The orchestrator creates and tracks the task.
The agent executes on a host, optionally inside an environment, with whatever secrets and credentials it needs. The exact way tasks are triggered and executed depends on your deployment model (for example CLI-only, Warp-hosted orchestration, or self-hosted execution). Those options are covered in the Deployment Patterns pages.
What you get by default
Because Cloud Agents run on the Cloud Agents Platform, each run is tracked and produces a persistent record that can be observed, shared, and audited (even if execution happens outside the Warp app).
Observability and steerability
Cloud agent tasks are designed to be inspectable by the team:
Agent Session Sharing lets authorized teammates attach to a running task to monitor progress and, where supported, steer the agent while it runs.
Each run produces a session transcript and task metadata, which provides a record of what the agent did.
A management experience surfaces task status and history.
Centralized configuration
Cloud agent workflows often rely on shared configuration such as MCP servers, rules, saved prompts, environment variables, and secrets.
Warp supports centralized configuration so the same workflow behaves consistently across triggers (for example Slack + CI + schedules), without duplicating setup in every system.
API access to tasks
The Warp Platform exposes task visibility via the Agent API and SDKs, so teams can…
Query which tasks are running or have run.
Fetch task metadata and outcomes.
Build internal dashboards or monitoring (for example success rates, runtime, failure reasons).
Using Cloud Agents with or without Warp’s app
Cloud Agents do not require the Warp desktop app. Teams can deploy and operate them through the Cloud Agents Platform using:
Web surfaces (where available)
Admin settings and APIs If your team also uses Warp’s terminal, you get an additional workflow: tasks launched via the CLI can be handed off into an interactive session for review, edits, or continuation.
Team and billing requirements
Cloud Agents and integrations run on the Cloud Agents Platform control plane, and usage is billed using credits.
To run integrations (and most cloud agent automation), your team must meet the following requirements:
Plan requirements
Supported plans: Build, Business
Not supported: Pro, Turbo, Lightspeed, legacy Business
Your plan must support add-on credits.
Credit requirements
Your team must have at least 20 add-on credits available to run an integration.
Integration usage is billed to the team's add-on credit balance.
Cloud agents and integrations can use Cloud Agent Credits if available.
For more details, please refer to: Team Access Billing And Identity Permissions
If the team’s add-on credit balance reaches zero, integrations and cloud agent runs that require add-on credits will not be able to execute until credits are replenished.
Learn more
Cloud Agents Platform — CLI, Agent API/SDK, orchestration, tasks, environments, hosts, integrations, and more.
Warp CLI — shows how to run Warp's agent in non-interactive mode from CI, scripts, or remote machines, including auth and common commands.
Environments — explains how environments provide the runtime context (repo, image, startup commands) for agent tasks.
Agent API and SDK — documents the REST API for creating, querying, and monitoring agent tasks programmatically.
Agent Secrets — covers how to store, scope, and inject credentials into agent runs safely.
MCP Servers for Agents — describes how to configure MCP servers for agent tool access and how MCP configuration is applied across runs.
Deployment Patterns (beta) — compares common ways to deploy cloud agents and when to use each.
Team Access Billing And Identity Permissions — explains team-level requirements, credit billing behavior, and the permission model for who can run, view, and steer cloud agent tasks.
Last updated
Was this helpful?