CompozyOS coordinates agent command line tools as a team that shares project memory and tasks.
Steel Browser
Steel Browser provides a browser API and sandbox for automating web tasks with AI agents.

About Steel Browser
Steel Browser is an open-source browser API and sandbox for automating web tasks with AI agents and apps. It manages sessions, pages, and browser processes, allowing programmatic control of Chrome instances through Puppeteer, Playwright, Selenium, and CDP, with support for session state, proxies, extensions, and page conversion to markdown, screenshots, or PDFs.
It can be used through Steel Cloud, deployed to a cloud provider, or run locally with Docker. The project is in public beta and is still evolving.
Key features
- Control Chrome instances via Puppeteer, Playwright, Selenium and CDP
- Maintain sessions with cookies and local storage across requests
- Built-in proxy chain management for IP rotation
- Stealth plugins and fingerprint management
- Convert pages to markdown, screenshots, PDFs and readability view
- Load custom Chrome extensions for added functionality
- Open-source codebase that can be self-hosted or deployed to cloud providers
- Works with existing automation libraries including Puppeteer, Playwright and Selenium
- Includes session management, proxy support and page-conversion tools
- In public beta and evolving, so behavior and APIs may change
- Local use requires Docker setup, with extra configuration on Mac Silicon
Steel Browser at a glance
- Category
- AI & Machine Learning › AI Agent Frameworks
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
Steel Browser alternatives
Tools and sites you could use instead, ranked by how closely they match.
PraisonAI supports agents that research, plan, code, and execute tasks, with memory and RAG features.
Pydantic AI provides Python tools for building agents with voice, image generation, and embedding capabilities.
Agent Skills defines a specification and documentation for giving AI agents reusable capabilities.
The open-multi-agent project provides a self-hosted TypeScript runtime with approvals and verifiable records.
MCP Memory Service provides persistent memory for AI agent pipelines through an API and knowledge graph.
Popular in AI Agent Frameworks
Well-known listings from the same topic.
Steel Browser FAQ
What deployment options are available?
How can I run Steel Browser locally?
Which automation libraries can connect to it?
Tell us and an editor will check it.
Claim the listing and suggest updates yourself. An editor checks every claim first.












