SDK

Automate Computer Agents from Python.

The Python SDK mirrors the same ACP platform model as the JavaScript SDK. It works well for data systems, internal tooling, scheduled operations, and service backends that already standardize on Python.

Automate work

Run agents from scripts, services, notebooks, CI jobs, and research pipelines.

Control resources

Create computers, upload files, deploy functions, bind secrets, and inspect logs from Python.

Manage projects

Create project tasks, comments, releases, and task-linked threads from backend systems.

Monitor usage

Read budget state, usage stats, model availability, and product notifications programmatically.

Install and initialize

The Python SDK uses the same product model and API semantics as the JavaScript SDK. Start with one client and then decide whether you want the convenience run() flow or explicit control over threads and resources.

Install and initialize
InstallInstall from PyPI in scripts, services, notebooks, backend jobs, and internal tools. Python 3.9 or newer is required.
AuthenticateCreate an API key in Computer Agents and pass it through COMPUTER_AGENTS_API_KEY or api_key.
Start fastUse client.run() when Python should hand a task to an agent and stream events back to your process.
Use as a control planeMove to explicit managers when your service controls threads, computers, tasks, resources, and usage state.
Install the Python SDK
Loading...
Initialize the Python client
Loading...

Core execution managers

Python exposes the same platform primitives: threads, tasks, computers, agents, files, resources, databases, and automation managers. That keeps service behavior consistent across SDK languages.

Core execution managers
ThreadsMulti-turn agent sessions with messages, logs, reasoning, diffs, permission requests, feedback, and resumable state.
ComputersPersistent cloud workspaces where agents browse, code, run CLIs, install packages, edit files, and keep state.
ProjectsShared workspaces for strategy, releases, tickets, comments, resources, review state, and task-linked threads.
AgentsReusable execution profiles with model, instructions, skills, reasoning effort, and analytics.
Files and GitAutomate workspace file access, folder downloads, git status, diffs, commits, branches, clone, and push.
Run ACP from Python
Loading...

Tasks, review feedback, and permission decisions

Project work has a dedicated Python surface. Tasks can start multiple linked threads, thread turns can collect thumbs up/down or issue reports, and paused runtime permission requests can be decided from backend services.

Tasks, review feedback, and permission decisions
Create tasksCreate planned work with project, release, priority, assignee, reviewer, comments, and status metadata.
Start task threadsUse start_thread() for application-controlled streaming or run_thread() for backend jobs that execute immediately.
Capture feedbackUse set_feedback() and report_issue() to collect structured quality signals on thread outputs.
Approve safelyList, approve, or deny runtime permission requests when an agent pauses before a sensitive action.
Run planned task work in Python
Loading...

Product-shaped managers in Python

Python also now exposes first-class product managers rather than forcing every app surface through one generic resources object. That keeps day-to-day usage clearer and closer to the ACP product model.

Product-shaped managers in Python
Web appsDeploy dashboards, internal tools, portals, prototypes, and AI apps from a source computer.
FunctionsDeploy APIs, webhooks, jobs, data transforms, and backend actions, then invoke them from Python.
DatabasesCreate structured app state with databases, collections, and JSON documents.
AuthCreate authentication modules for sign-up, sign-in, sessions, and user administration.
SecretsStore API keys, tokens, credentials, and private runtime configuration in vaults instead of source code.
ResourcesUse generic resource operations for cross-kind automation when one workflow handles multiple deployed surfaces.
Create app resources in Python
Loading...

Runtime helpers and Python control

The Python SDK controls Computer Agents resources from Python services, notebooks, CI, and jobs. Deployed Node Functions and server-rendered Web Apps use the JavaScript runtime helpers for in-resource access to secrets, databases, auth, and agent runs.

Runtime helpers and Python control
Python control planeCreate computers, upload files, deploy resources, bind databases and secrets, invoke functions, and inspect logs from Python.
Node runtime helpersInside deployed Node resources, import helpers from computer-agents/runtime/server to read secrets and use bound resources.
BindingsUse Python to connect databases, auth modules, secrets, web apps, functions, and agent runtimes before deployment.
OperationsMonitor deployments, logs, analytics, billing state, and budget state from service backends.
Bind resources from Python
Loading...

Automation and platform operations

The Python SDK is especially useful when ACP needs to live inside recurring jobs or backend operations. Skills, schedules, triggers, orchestrations, billing, and git helpers all stay available from one client.

Automation and platform operations
SchedulesCreate recurring ACP work from Python services and jobs.
TriggersStart work from webhook, GitHub, Slack, email, or app events.
OrchestrationsCoordinate multi-agent workflows around one objective, including research, build, review, and deployment phases.
Git and filesAutomate repository-aware work with git helpers and workspace file operations.
Schedule and trigger work from Python
Loading...

Models, budget, and SDK surface

Use Python to discover model availability, create reusable agents, check budget state, read usage, and choose the right manager for each ACP surface.

Models, budget, and SDK surface
ModelsCreate agents with Anthropic, OpenAI, Gemini, DeepSeek, Kimi, or connected external models available to the workspace.
BudgetCheck whether a task can execute before starting work and display account status inside your product.
BillingRead usage stats, transactions, checkout state, and plan information for account-aware applications.
NotificationsList in-app notifications and manage push tokens for product surfaces that embed Computer Agents.
Context managerUse ComputerAgentsClient as a context manager in scripts and jobs that should release resources deterministically.
Model discovery and budget checks
Loading...