Using Memory - Agents Squads

Why Memory?

Without memory, every session starts fresh. Your agents forget everything. With memory:

Continuity — Pick up where you left off
Learning — Build on previous work
Coordination — Share context between agents

Memory Structure

.agents/memory/
├── research/              # Squad memory
│   ├── goals.md           # Measurable targets
│   ├── feedback.md        # Last cycle's evaluation
│   └── analyst/
│       └── state.md       # Agent memory
└── company/
    └── strategy.md        # Company-wide "why" — read by every squad

See Memory for how these layers cascade into an agent’s context, in priority order, on every run.

Querying Memory

# Search across all memory
squads memory query "competitor analysis"

# Read a specific squad's memory
squads memory read research

# List all entries
squads memory list

Memory in Action

When an agent runs:

Load    → Retrieve relevant memory
Inject  → Add to agent context
Execute → Agent works with full context
Update  → Store new learnings

Writing Good Memory

Memory files are markdown. Keep them structured:

<!-- .agents/memory/research/analyst/state.md -->

# Research Analyst Memory

## Current Focus
Q1 2025 market analysis for enterprise AI agents.

## Recent Work
- Completed competitive analysis (Jan 15)
- Identified 3 new market entrants
- Pricing research in progress

## Key Findings
- Market growing 15% YoY
- Main competitor raised Series B
- Enterprise buyers want transparency

## Blockers
- Need access to Gartner reports
- Waiting on customer interview data

## Next Steps
- Deep dive on pricing strategies
- Interview customer segment

Memory Types

Agent Memory

Private to each agent:

Task history
Learned preferences
Work in progress

Squad Memory

Shared across agents in a squad:

Domain knowledge
Coordination state
Team decisions

Best Practices

Update memory after work

Run squads memory write <squad> "<learning>" after significant work.

Keep it current

Stale memory is worse than no memory. Prune outdated info.

Structure consistently

Use the same sections across agents for predictability.

Focus on context, not logs

Memory isn’t a log file. Store insights, not events.

Next Steps

CLI Reference

All memory commands

Core Concepts

Deep dive on memory

Working with Squads Learning Loop

​Why Memory?

​Memory Structure

​Querying Memory

​Memory in Action

​Writing Good Memory

​Memory Types

​Agent Memory

​Squad Memory

​Best Practices

​Next Steps