---

name: distill description: Distill session episodes into persistent memory patterns user_invocable: true

/distill - Memory Distillation

Transforms episodic session logs into refined semantic memory patterns.

Usage

Copy/distill           # Distill episodes at current scope
/distill show      # Show current memory without distilling
/distill episodes  # Show pending episodes awaiting distillation

How It Works

Episode Collection

During agent work, learnings are logged to .context/EPISODES.md:

Copy## Session: 2026-01-10T14:30:00Z
- **Task**: Fix authentication bug
- **Outcome**: success
- **Learnings**:
  - JWT tokens need refresh handling in middleware
  - Error messages should include request ID

Distillation Process

When /distill runs:

1. Extract patterns from each episode's learnings
2. Classify as pattern, pitfall, preference, or approach
3. Match against existing patterns in memory
4. Reinforce matching patterns (increases confidence)
5. Add new patterns with low initial confidence
6. Decay old patterns not recently reinforced
7. Prune patterns below confidence threshold

Memory Output

Results are saved to .context/MEMORY.md:

Copy# Memory: [Scope]

## Patterns Observed
- JWT tokens need refresh handling
  Confidence: high | Last reinforced: 2026-01-10

## Pitfalls Discovered
- Avoid storing tokens in localStorage
  Confidence: medium | Last reinforced: 2026-01-08

Implementation

When invoked, run:

Copypython3 ~/.claude/plugins/agent-swarm/context/memory.py distill .

For showing memory:

Copypython3 ~/.claude/plugins/agent-swarm/context/memory.py show .

For pending episodes:

Copypython3 ~/.claude/plugins/agent-swarm/context/memory.py episodes .

Logging Learnings

Agents can log learnings by including in their output:

CopyLEARNING: [description of pattern, pitfall, or approach]

These are captured by post-task hooks and added to EPISODES.md.

Confidence Mechanics

• Reinforcement: Each observation increases confidence
• Decay: Patterns not seen in 30+ days lose confidence
• Pruning: Patterns below 0.2 are removed

Automatic Distillation

Distillation triggers automatically when:

• Episode count exceeds threshold (default: 10)
• Session ends (if configured)
• Manually via /distill command