Security & privacy
Secrets live in your vault. Sensitive information can be encrypted end to end. See how each kind of data is stored. Hooks help with custom policies.
Build hundreds of task-specific AI agents. Search runs the right agent for each request. Avoid context rot, unpredictable workflows, and runaway LLM costs.
Agent framework
Build a working agent in minutes, in your browser with AI assistance
Hybrid architecture
Stateless agent servers. State managed in Search2o Cloud.
Platform
Built for the enterprise
Access & roles
Four roles: users, developers, administrators and owners. Service accounts for bots and scripts. Built-in authentication as well as single sign-on.
Change control
An agent's LLM, API, database, MCP and optionally prompts live in profiles, not its code. Every profile knows which agents use it. Every change is in the audit log.
Cost control
Each agent uses only the model its workflow needs, whether frontier, cheap or free. Every run has a spend limit, and reports show spend per agent and user.
Horizontal scalability
Agent servers are stateless, so you can run as many as you need behind a load balancer. Configuration changes are live on the next agent run on every server.
API & automation
The agent server exposes a REST API. Use it to run non-interactive agent workflows — event-driven or in batch. The bundled GUI uses the same API.