Agents
Everything about building a single agent — from the first Agent instance to advanced cognitive composition.
Sections
- Fundamentals — Agents, roles, actions, and the event bus. Start here.
- Behavior — Prompts, output parsing, streaming, memory, variants.
- Reliability — Resilience, error handling, schema identity.
- Advanced — Cognitive support, planner/reasoner handles, ensemble execution.
Related
- Multi-Agent — When one agent isn't enough.
- Capabilities — Tools, intelligence, RAG, LLM.
- Agent-level action RAG
@AgentSpec.knowledge()/retrieval()(@since 0.14.0).
Tutorial: Agent with Tool Approval
A full code walkthrough is still being written. In the meantime this page describes the shape and points at the framework pieces you can wire up today. Open a discussion if you start the implementation and hit something missing.
Fundamentals
The core moving parts of a single agent. This page covers the Agent class itself — construction, chat, memory, lifecycle. See the other pages in this section for Roles, the Action System, Capabilities, and Events.