Let AI agents work in your signed-in Chrome browser with scoped access, human approval, and verified results
A platform to build, run, and use AI microagents through search
Stage
Not given
MVP
Founded
Not given
Not given
Based in
Not given
US
Pricing model
Not given
Free trial
Pricing
Free: €0/month with 100 task credits per month and 1 connected browser. Pro: €5/month with 2,000 task credits per billing month and 5 connected browsers. Extra credits: 1,000 credits for €3 on Pro (do not expire).
The agent server is free and source available with no license fee. Search2o Cloud is free during the beta period. Production pricing will include a platform fee, developer fee, storage fee, and usage fee with no per-user charges. Paid service planned for January 2027.
Key features
Redacted sensitive values including passwords, OTPs, card data, and API keys
Effect verification to prevent blindly repeating uncertain browser side effects
Integration with ChatGPT and Claude via MCP connectors
REST API and custom agent key support for own scripts
Task credit model with no separate browser-hour or AI model billing
Built-in agent discovery and multi-agent conversations
Agent framework to define and publish agents
Encrypted conversations and memories by default
Multi-user access with four roles plus service accounts
Human-in-the-loop controls for critical actions
Stateless horizontally scalable architecture
Environment profiles for dev and prod
Source available server and UI
What makes it different
Keeps your signed-in sessions in your own Chrome profile instead of copying them to a remote browser fleet
Brings the agent into your existing browser instead of moving your browser to a remote server
Charges only for accepted tasks, not for browser hours or AI model calls
Prevents uncertain side effects from being blindly replayed through durable task state and effect verification
Treats all page content as untrusted data so websites cannot grant themselves new permissions
Search that retrieves and runs AI workflows instead of matching documents
Agents that combine deterministic workflows with LLM-driven reasoning
Hybrid cloud architecture requiring only stateless servers in your environment
No per-user licensing, pay only for developers, storage and usage
Enterprise-grade reliability and security standards