Security & privacy
Secrets live in your vault. Conversations and memories are encrypted, by default or, optionally, end to end. Data privacy lists how each kind of data is handled.
Transform your enterprise AI with Search2o agent server
Developers build and describe task-focused agents on the server. Users just ask for what they need: the built-in search picks the right agent, and the client runs it on the server. Hundreds of agents work as one safe and observable application for any client, including an agent harness.
Developers
Client
Search2o agent server
pip install search2oAgents
Build, validate, publish agents
search("My laptop keeps freezing") IT helpdesk
Describe agents in EnglishIT helpdesk: Handles employees’ IT support requests. Troubleshoots hardware and software, and manages accounts and access.
execAgent(convId, IT helpdesk, "My laptop keeps freezing") Ticket IT-4821 opened. A technician will call at 2 pm.
Live demo: Draft an agent with AI · Chat with agents · Trace an agent run
All the plumbing taken care of
Agent server
Agent editor
Draft with AI
Externalized prompts
Externalized system calls
Trace and validation
Agent versioning
Multi‑developer publishing
Live configuration
Hooks
Audit log
LLM calls
Model neutrality
Tool calling loop
API and database calls
MCP
Connection pools
Secret vault
Authentication
Parallel execution
Error handling
Runtime limits
Guardrails
Human in the loop
Streaming
Progress
Save/Restore conversations
Agent memory
Observability
Fits into your environment as is
Built for enterprise operations
Multi-user access
Four roles: users, developers, administrators and owners. Service accounts for bots and scripts. Built-in authentication as well as single sign‑on.
Source available
Everything that runs in your enterprise can be built from the source: the agent server and the UI. Set the logging configuration to see every call to the cloud.
Multiple environments
An agent refers to enterprise systems by profile name. Dev and prod profiles point at their own systems, so the same agent runs unchanged.
Horizontally scalable
Agent servers are stateless and can be run in a cluster. Configuration and profile changes are live on the next agent run on every server, without a restart.
Integration
Integrate at three levels: from Python expressions inside an agent, through the REST API, and with hooks that run your code at the server’s decision points.