Agent Overview
What Reeve agents are, how roles work, and the difference between built-in and custom agents.
Agent Overview
An agent is a persistent AI identity with its own role, model, workspace, and memory. Agents are the core building block of Reeve — they do the work.
What Makes an Agent
Every agent has:
| Property | What it controls |
|---|---|
| Role | Behavior defaults (model, heartbeat, permissions) |
| Model | Which LLM powers it (Claude Opus, Sonnet, GPT-4, etc.) |
| Workspace | Directory with AGENTS.md, SOUL.md, MEMORY.md, and daily logs |
| Channel bindings | Which messaging platforms it responds on |
| Heartbeat | Periodic check-in schedule for autonomous work |
| Subagent policy | Which other agents it can spawn |
| Tool policy | Which tools it can use |
Roles
Roles provide sensible defaults so you don't have to configure everything from scratch:
| Role | Model | Heartbeat | Use case |
|---|---|---|---|
coordinator | Opus | 30 min | Top-level orchestrator — routes work, never resets |
manager | Opus | 2 hours | Domain lead (marketing, engineering) — spawns workers |
worker | Sonnet | None | Task executor — fast, cheap, resets after 1h idle |
research | Opus | 4 hours | Deep analysis — resets after 24h idle |
assistant | Opus | 2 hours | General helper — conversational, resets after 48h idle |
Roles are starting points — you can override any default per agent.
Single vs Multi-Agent
Single Agent
The simplest setup: one agent handles everything. Good for personal use, small teams, or getting started.
You ←→ Reeve (assistant)Multi-Agent
For complex work, agents specialize and coordinate:
Coordinator
├── Marketing Manager
│ ├── Content Writer (worker)
│ └── Ad Analyst (worker)
└── Engineering Manager
├── Frontend Dev (worker)
└── Backend Dev (worker)Managers spawn workers for parallel execution, coordinate results, and report back. Workers are cheap (Sonnet) and reset quickly. Managers and coordinators maintain longer context.
See Multi-Agent for the full coordination system.
Built-in vs Custom Agents
Built-in
Every Reeve installation starts with a default agent (typically assistant role). This agent is ready to go with sensible defaults — you just need an LLM API key.
Custom
Create agents tailored to specific roles:
reeve agents addThe interactive wizard asks for:
- Name — A human-readable name (e.g., "Marketing Manager")
- Role — One of the five built-in roles
- Model — Which LLM to use
- Workspace — Where to store config and memory
Or create agents from the Cockpit at Settings → Agents → New Agent.
Agent Lifecycle
Create → Configure → Active → [Sessions, Memory, Goals] → Archive/Delete- Create — Via CLI wizard or Cockpit UI
- Configure — Set model, tools, heartbeat, workspace files
- Active — Agent responds to messages, runs heartbeats, executes goals
- Memory grows — Daily logs accumulate, MEMORY.md gets curated
- Archive/Delete — When no longer needed
Agents persist across gateway restarts. Their memory, configuration, and workspace survive indefinitely.
Configuration Files
AGENTS.md, SOUL.md, USER.md, and per-agent config
Memory
How agents remember things long-term
Tools
Available tools and custom tool creation
Creating Agents
Step-by-step agent creation
Agents are identified by a unique ID (e.g., marketing-manager). This ID is used in configuration, CLI commands, and inter-agent communication.