openbrowser
A TypeScript-based autonomous web browsing framework enabling AI agents to independently complete web tasks.
- Region
- Overseas
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 9.5k
- Source
- GitHub
- Added
- 2026-06-05
- Last verified
- 2026-06-05
Overview
Open Browser is a TypeScript-based autonomous web browsing framework designed to allow AI agents to independently complete web tasks. It eliminates the need for manually writing scripts for web interactions by enabling users to perform actions such as clicking, typing, navigating, and data extraction through natural language descriptions. Ideal for developers or teams requiring automation of web-based workflows.
Key features
- ▪Supports multiple models: Compatible with OpenAI, Anthropic, Google
- ▪Interactive REPL: Real-time debugging and exploration
- ▪Sandboxed execution environment: Resource limits and monitoring
- ▪Production-ready: Error handling and cost tracking
Use cases
Pros
- ＋Easy to get started
- ＋Highly extensible
- ＋Robust error handling mechanism
Limitations / notes
- －Requires API key configuration
- －Dependent on network connectivity
Who it's for
This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.
FAQ
How do I get started?
After installing dependencies, set your API key and run the command to start the AI agent.
Which AI models are supported?
Default support includes OpenAI, Anthropic, and Google models.
Similar agents
Cursor
FeaturedAI-powered code editor with Agent mode
Dify
FeaturedOpen-source LLMOps + Agent orchestration platform
扣子 Coze
FeaturedByteDance's no-code Agent/Bot building platform
Trae
FeaturedAI IDE (with Agent) from ByteDance
LangChain
FeaturedThe most mainstream LLM/Agent orchestration framework
Devin
FeaturedAutonomous software engineer Agent by Cognition
Something wrong? Let us know on the About page and we'll fix it.