Free Agent Browser Automation

Let your AI agents browse the web securely in isolated sandboxes.
Production-ready in minutes
Zero infrastructure management
Built-in AI models & tools

Why Choose EdgeOne Makers for Agent Browser

Secure browser automation for AI agents — isolated per session, no browser agent security risk, with built-in web search and page interaction capabilities.
feature icon
One-Command Deployment
Deploy with `git push` for auto-deploy or `edgeone makers deploy` via CLI — no Docker, no Kubernetes, no server provisioning.
feature icon
Built-in Agent Runtime
Managed runtime with session-sticky routing, up to 1-hour execution time, and in-memory state reuse — purpose-built for LLM calls and multi-step agent loops.
feature icon
Integrated AI Models
Access DeepSeek, MiniMax, Hunyuan, and more through a unified AI gateway. New accounts receive 500K free tokens with zero configuration.
feature icon
Full Observability
Zero-instrumentation distributed tracing — view complete call chains, LLM interactions, tool invocations, and latency metrics in local and cloud dashboards.

How to Use Agent Browser on EdgeOne Makers

Deploy your agent and get instant browser automation — navigate, scrape, and interact with web pages securely, no browser setup required.
How to Use Agent Browser on EdgeOne Makers
1
Write Your Agent
Build in the `agents/` directory with any framework (OpenAI SDK, Claude SDK, LangGraph, CrewAI, DeepAgents).
2
Deploy to Production
Push to Git (GitHub/GitLab/Gitee) for auto-deploy, or run `edgeone makers deploy` via CLI.
3
Go Live
Deploys globally in minutes with automatic SSL and edge routing.

Complete Agent Browser Features

Secure browser automation built into the agent runtime — navigate, interact, and extract data without browser agent security risk.
Feature
Description
Agent RuntimeHosts LLM calls, Agent loop orchestration, and business logic, with session-based routing and automatic scaling.
Sandbox ToolsProvides two separate yet interoperable API layers for both LLMs and developers. Browser automation, code execution, Shell, and file operations all run in an isolated sandbox environment.
Conversation StorageProvides framework-compatible memory management, with unified APIs for sessions and messages.
ObservabilityAutomatically collects call traces with zero-intrusion instrumentation, enabling unified trace viewing in both local and cloud dashboards.
Built-in ModelsAccess Hunyuan and other mainstream Chinese models through AI Gateway with a limited-time free token quota.

Build with Any AI Agent Framework

Bring your preferred framework — deploy agents built with any major SDK or orchestration library, in JavaScript or Python.

Frequently Asked Questions

What is the agent browser on EdgeOne Makers?

The agent browser is a built-in browser automation tool that lets AI agents navigate web pages, click elements, fill forms, extract content, and search the web — all running in an isolated sandbox environment.

How does EdgeOne Makers address browser agent security risk?

Every agent browser instance runs in a per-session isolated sandbox. No cookies, browsing history, or network state is shared between sessions, completely eliminating browser agent security risk from cross-session data leakage.

Is the agent browser free to use?

Yes. Browser automation is included in the sandbox free tier: 100,000 GB-s memory time, 20 concurrent instances, and up to 3,600-second runtime. No additional cost for agent browser usage.

What can my agent do with the browser?

The agent browser supports: page navigation, element clicking, form filling, content extraction, screenshot capture, and web search. All actions run in the isolated sandbox, ensuring no browser agent security risk.

Can multiple agents use browser simultaneously?

Yes. Up to 20 concurrent sandbox instances are available on the free tier, each with its own isolated agent browser. Sessions are independent with no shared state.