OpenBrowser
OpenBrowser is a general-purpose agentic browser for giving an AI agent a real browser. Its page presents it as a tool for browser control and for tasks such as navigating, clicking, typing, and extracting data, with support for autonomous browsing and scheduled browser workflows.
The product highlights a text-first architecture and says it uses one execute_code tool with a persistent Python namespace. It also says the browser can be watched in real time through VNC streaming, so agent actions are visible as they happen. Example text on the page shows an agent navigating to a web address, and the scheduled-workflow section says recurring tasks can reuse saved login sessions.
OpenBrowser says it works with 15 LLM providers out of the box and with any OpenAI-compatible endpoint. The named providers are Gemini, OpenAI, Claude, DeepSeek, Groq, Ollama, Qwen, Azure, Bedrock, OpenRouter, Cerebras, OCI, Azure AI, Novita, and LiteLLM. It also says it integrates with any MCP-compatible client, and the page names Claude Code, Cursor, Windsurf, VS Code, n8n, Any MCP Client, and Cline Roo Code among the tools shown.
Delivery options listed on the page include Docker, Kubernetes, and cloud deployment. Installation is shown with a pip command, and the example code uses imports such as CodeAgent and ChatGoogle. OpenBrowser is open source and MIT licensed, and the page includes a waitlist for early access to a hosted version.
Open SourceMITCLISelf-hosted
235stars
19forks
8features
2025since
Overview
8 featuresOpenBrowser sits in PulseGate's Developer Tools category. It focuses on enabling AI agents to interact with and control browsers programmatically for automation and testing. It is built as an open-source project for AI developers and agent framework builders. The project is open source (MIT). It runs on the command line, and it can be self-hosted.
OpenBrowser first shipped in 2025. Development happens publicly on GitHub with 235 stars and 37 commits in the last 90 days. Key capabilities include agentic browser, CLI control, and MCP server. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
- Agentic browser
- CLI control
- MCP server
- VNC streaming
- Open source
- Docker deployment
- Kubernetes support
- Extensible architecture
Tags
agentic-browsermcp-serverai-automation
AI capabilities
Text
Inference: LocalWeights: Open
Built with & integrations
Framework
Next.js
Hosting
AWS
AI providers
anthropiclocal_ossopenai
Connectors
MCP
Runs on
CLISelf-hosted
Detected from
- AWS
- x-amz-cf-id header · x-amz-cf-pop header · via header
- Next.js
- /_next/static/ in the HTML · __next_f in the HTML
- anthropic
- bclaude in the HTML
- local_oss
- bollama in the HTML
Trust & compliance
License
MIT
Verified signals
Indexing history
1What PulseGate has recorded for this listing
Frequently asked questions about OpenBrowser
- What does OpenBrowser do?
- OpenBrowser focuses on enabling AI agents to interact with and control browsers programmatically for automation and testing. It is catalogued under Developer Tools on PulseGate.
- Who should use OpenBrowser?
- OpenBrowser is an open-source project built for AI developers and agent framework builders.
- Does OpenBrowser have a free plan?
- Yes — OpenBrowser is open source under the MIT license and free to use.
- What platforms does OpenBrowser run on?
- OpenBrowser runs on the command line. It can also be self-hosted.
- Is OpenBrowser still active?
- The GitHub repository shows 37 commits in the last 90 days.
- What projects are similar to OpenBrowser?
- Similar projects tracked by PulseGate include BrowserMan, Nanobrowser, and BotBrowser.BrowserManNanobrowserBotBrowser
- When did OpenBrowser launch?
- OpenBrowser first shipped in 2025.
- Is OpenBrowser open source?
- Yes — OpenBrowser is open source under the MIT license, developed on GitHub.
Similar projects
Closest matches by what these projects do