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.
Developers build, validate and publish task‑focused agents on the agent server. They describe when to use each one in plain English.
Users start a conversation with a request. The agent server finds the right agent with semantic search, and runs it on that request. Follow‑up requests can bring in other agents, and build on previous results.
The agent server keeps every run safe, bounded and observable.
pip install search2oAgents share conversation context and build on the LLM message history from previous agents.
Draft with AI and the schema‑aware code editor help you build an agent in minutes, just by describing it.
// A simple RAG agent that answers from a knowledge base.{
"functions": {
"main": {
"commands": {
"api": {
// The API profile 'knowledgeBase', defined externally, is used to connect. "profile": "knowledgeBase",
"queryParams": {
// The API query parameter is set to sys.query, a built-in variable that contains the user’s request. "q": "{ sys.query }"
}
},
"var": {
// 'result' is a built-in variable that is set to the result of the API call. A variable called 'passages' is set with a Python expression using 'result'."passages": "{ [hit['text'] for hit in result[:5]] }" },
"llm": {
// An LLM profile, 'gpt5_mini', is used. LLM profiles specify the vendor and the model in use. "profile": "gpt5_mini",
// A prompt named 'answer' is used to talk to the LLM. This prompt is specific to this agent and defined externally. "prompt": "answer",
"streamOutput": true
}
}
}
}
}
The agent server runs stateless in your organization and keeps its state in the cloud.
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.
Four roles: users, developers, administrators and owners. Service accounts for bots and scripts. Built-in authentication as well as single sign‑on.
Everything that runs in your organization can be built from the source: the agent server and the UI. Set the logging configuration to see every call to the cloud.
An agent refers to enterprise systems by profile name. Dev and prod profiles point at their own systems, so the same agent runs unchanged.
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.
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.