| Key features | - Atlas manager agent that breaks down tasks and delegates to specialists
- Ready-made team templates for marketing, research, operations, and more
- Agent Marketplace with 20+ built-in specialists
- Four control modes from Minimal to Manual for agent autonomy
- Support for Claude, OpenAI, Gemini, and GitHub Copilot on one team
- Live activity feed, task board, and team inbox with file previews
- Agent memory and shared Decision Ledger across sessions
- Agent Creator to build custom specialists in plain English
- MCP server integration to connect agents to outside services
| - SEO audit: checks titles, headings, canonicals, robots rules, structured data and redirects
- GEO audit: checks HTML that AI crawlers read before JavaScript and robots.txt permissions
- AXO audit: tests whether agents can name buttons, fields and use forms
- Whole site crawl: up to 200 pages for broken links, duplicates, orphans and soft 404s
- AI answer reading: integrates with ChatGPT, Gemini, Claude, Perplexity, Google AI Mode and AI Overview
- Agent journeys: runs up to 15-step browser agent tests on your own API keys or Chrome's built-in model
- MCP server: hosted at mcp.workpods.ai/mcp for use in Claude and other MCP-compatible clients
- CI/CD integration: npx command to fail builds on high-severity checks
- Copy fix prompts: converts findings into prompts for coding agents
- Severity levels: every check passes, fails, or partly passes with severity ratings
|
|---|
| What makes it different | - One team can use multiple AI providers simultaneously
- Atlas manager agent coordinates specialist agents with real-time task handoffs
- Agents maintain memory across sessions with no re-explaining preferences
| - Free and open source under Apache 2.0 licence with all checks visible on GitHub
- Agent journeys stop before submitting forms or making purchases, safe to run on live sites
- Works with your own API keys or Chrome's free built-in model, no vendor lock-in
|