📄️ Agents Overview
Covia agents are persistent, stateful AI actors that live on a venue. They receive tasks, call tools, coordinate with other agents, and produce auditable results — all within the venue's governance and capability framework.
📄️ Creating Agents
Agents are created with the agent:create operation. The key decision is what to put in the config — this determines the agent's personality, tools, capabilities, and LLM backend.
📄️ Sessions
A session is a persistent conversation thread inside an agent. Every piece of inbound work — a task, a chat, or a notification — attaches to a session, and an agent can hold many sessions at once, each with its own conversation and scratch space. Sessions are how a single agent keeps several independent conversations straight.
📄️ Agent Operations
This page documents every operation available for managing agent lifecycle and interaction. All operations are invoked via the REST API (POST /api/v1/invoke) or as MCP tools.
📄️ LLM Agent
The LLM Agent adapter (llmagent:chat) provides a simple conversational agent model with a flat per-session conversation and a tool call loop. It is the default transition function for new agents.
📄️ Goal Tree
The Goal Tree adapter (goaltree:chat) provides hierarchical goal decomposition for complex agent tasks. The agent pursues goals via a frame stack — each subgoal opens a child frame with its own scoped conversation, and results propagate back to the parent.
📄️ Tools and Context
Every agent turn, the context builder assembles the complete input for the LLM — system prompt, tools, loaded context, and the session conversation. Understanding this pipeline helps you configure agents effectively and debug unexpected behaviour.
📄️ LLM Backends
The Level 3 LLM call is a stateless operation that sends messages and tool definitions to a language model and returns the response. Covia is model-agnostic — it talks to several providers through the LangChain adapter, and the choice of provider and model is yours. The models shown below are illustrative examples, not recommendations.