# Cloud agents overview > Run background agents in the cloud from events, schedules, or integrations with team-wide observability. - 网址：https://funcoding.ai/agents/warp/platform/ - 来源：Warp 官方文档原文（英文），MIT 许可，同步于 2026-10-11 - 官方原文：https://docs.warp.dev/platform/ --- Cloud agents execute a request away from your laptop, on Warp-hosted compute or your own infrastructure. For example, an agent can investigate a failed build, review a pull request, or respond to an issue filed in your tracker. For a standing team workflow with agents, automations, and tools to evaluate results, start with [Warp Factories](https://funcoding.ai/agents/warp/factories/). To run cloud agents directly from Warp, use the [cloud agents quickstart](https://funcoding.ai/agents/warp/platform/quickstart/). Already using the Oz web app or Oz CLI? See [transitioning from Oz to Warp Factories](https://funcoding.ai/agents/warp/platform/transitioning-from-oz/). The standalone workflows below remain distinct from factory setup. ## Monitor, inspect, and share cloud agent runs For factory work, open the factory's [Runs page](https://funcoding.ai/agents/warp/factories/factory-dashboard/#inspect-runs). For standalone workflows, use the [Agent Management Panel](https://funcoding.ai/agents/warp/platform/managing-cloud-agents/) in Warp or the [Oz web app Runs page](https://funcoding.ai/agents/warp/platform/oz-web-app/#runs). Open a run's transcript to inspect its prompt, commands, logs, and outputs, or to share its session link with teammates. See [viewing cloud agent runs](https://funcoding.ai/agents/warp/platform/viewing-cloud-agent-runs/) for steering and continuing a session. ## What cloud agents are designed for * **Event-driven work** - Respond to bug reports, [Slack messages](https://funcoding.ai/agents/warp/platform/integrations/slack/), or CI failures. * **Parallel tasks** - Use [multi-agent orchestration](https://funcoding.ai/agents/warp/platform/orchestration/) to divide independent work among agents running in the cloud. * **Recurring maintenance** - Run [scheduled agents](https://funcoding.ai/agents/warp/platform/triggers/scheduled-agents/) for dependency checks, cleanup, or reports. Cloud agents can assist throughout the development lifecycle.
![Cloud agent use cases across the development lifecycle: Plan, Prototype, Build, Validate, Review + Merge, Deploy + Monitor](https://funcoding.ai/official-assets/warp/src/assets/agent-platform/oz-use-cases.webp)
Cloud-agent work spans the software development lifecycle.
Before automating a task, identify its trigger, the context the agent needs, and how someone will validate its result. ## How cloud agents work The [Automation Platform overview](https://funcoding.ai/agents/warp/platform/overview/) explains the execution model shared by factories and standalone agents, including environments and credentials. The exact way tasks are triggered and executed depends on your deployment model. [Deployment patterns](https://funcoding.ai/agents/warp/factories/deployment-patterns/) covers Warp-hosted and managed self-hosted execution for factories. For standalone agents, see [Unmanaged execution](https://funcoding.ai/agents/warp/platform/unmanaged-execution/). For teams that need execution to stay within their network boundary, self-hosting supports two architectures: a **managed** worker daemon that lets the Automation Platform orchestrate agents in Docker containers on your machines, and an **unmanaged** mode where you run `oz agent run` directly in your CI, Kubernetes, or dev environment. See [Self-hosting](https://funcoding.ai/agents/warp/factories/self-hosting/) for details. ## What you get by default The following features apply to standalone cloud-agent workflows. For factory configuration, see [definitions as code](https://funcoding.ai/agents/warp/factories/factory-as-code/). ### Codebase Context Cloud agent runs automatically benefit from [Codebase Context](https://funcoding.ai/agents/warp/agents/capabilities/codebase-context/) for semantic code understanding and search, as long as Codebase Context is enabled for your account. See [Codebase Context in cloud agent runs](https://funcoding.ai/agents/warp/agents/capabilities/codebase-context/#codebase-context-in-cloud-agent-runs) for details. ### Centralized configuration Configure [MCP servers](https://funcoding.ai/agents/warp/platform/mcp/) and [secrets](https://funcoding.ai/agents/warp/platform/secrets/) for the tools your task needs. The [shared configuration reference](https://funcoding.ai/agents/warp/platform/overview/#shared-configuration) links to each configuration type and its scope. ### API access to runs The [Warp Platform API](https://funcoding.ai/agents/warp/factories/api-and-sdk/) lets you query run status, metadata, and results from your own services. ## Using cloud agents with or without the Warp app Cloud agents do not require the Warp app. Teams can deploy and operate them through the [Automation Platform](https://funcoding.ai/agents/warp/platform/overview/) using: * [Oz CLI](https://funcoding.ai/agents/warp/agents/cli/oz-cli/) — run agents from scripts, CI, or the terminal * [Oz web app](https://funcoding.ai/agents/warp/platform/oz-web-app/) — visual interface for managing runs, schedules, environments, and integrations (works on mobile) * [Agent Session Sharing](https://funcoding.ai/agents/warp/agents/local-agents/session-sharing/) — attach to running tasks to monitor or steer * [Agent Management Panel](https://funcoding.ai/agents/warp/platform/managing-cloud-agents/) — view agent activity and run history in the Warp app * [APIs and SDKs](https://funcoding.ai/agents/warp/factories/api-and-sdk/) — programmatic access for custom integrations Use [Handoff](https://funcoding.ai/agents/warp/platform/handoff/) to continue work between local and cloud sessions. --- ## Billing and plan requirements Check [access and billing requirements](https://funcoding.ai/agents/warp/platform/team-access-billing-and-identity/) before running cloud agents or setting up integrations. --- ## Related pages * [Cloud agents quickstart](https://funcoding.ai/agents/warp/platform/quickstart/) — run a cloud agent with an environment. * [Automation Platform](https://funcoding.ai/agents/warp/platform/overview/) — CLI, Warp Platform API, orchestration, tasks, environments, hosts, integrations, and more. * [Warp Factories](https://funcoding.ai/agents/warp/factories/) — configure a standing development workflow and evaluate its results. * [Harnesses](https://funcoding.ai/agents/warp/platform/harnesses/) — pick between Warp Agent, Claude Code, and Codex for any cloud agent run. * [Agents](https://funcoding.ai/agents/warp/platform/agents/) — cloud agents that own and execute runs on your team. * [Multi-agent orchestration](https://funcoding.ai/agents/warp/platform/orchestration/) — coordinate a parent agent and its child agents across local and cloud runs to build supervisor/worker, fan-out, critic, DAG, and swarm workflows. * [Skills as Agents](https://funcoding.ai/agents/warp/platform/skills-as-agents/) — run agents based on reusable skill definitions from the CLI, web app, API, or on a schedule. * [Oz CLI](https://funcoding.ai/agents/warp/agents/cli/oz-cli/) — shows how to run agents in non-interactive mode from CI, scripts, or remote machines, including auth and common commands. * [Environments](https://funcoding.ai/agents/warp/platform/environments/) — explains how environments provide the runtime context (repo, image, startup commands) for agent tasks. * [Warp Platform API](https://funcoding.ai/agents/warp/factories/api-and-sdk/) — documents the REST API for creating, querying, and monitoring agent tasks programmatically. * [Agent Secrets](https://funcoding.ai/agents/warp/platform/secrets/) — covers how to store, scope, and inject credentials into agent runs safely. * [MCP Servers](https://funcoding.ai/agents/warp/platform/mcp/) — how to configure MCP servers for agent tool access and how MCP configuration is applied across runs. * [Deployment Patterns](https://funcoding.ai/agents/warp/factories/deployment-patterns/) (beta) — compares common ways to deploy cloud agents and when to use each. * [Access, Billing, and Identity Permissions](https://funcoding.ai/agents/warp/platform/team-access-billing-and-identity/) — explains individual and team-level requirements, credit billing behavior, and the permission model for who can run, view, and steer cloud agent tasks.