Proactive Memory

SkillDocs & knowledge

Turn repeated failures, corrections, and recurring requests into durable follow-up work.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Proactive Memory skill

About this skill

Self-hosted AI workspace where chat becomes visual workflows, multi-agent operations, and reviewable automations. Local memory; local or cloud models

What this skill tells your AI

The instructions your AI receives, as published by aaronnat23/disp8ch in skills/proactive-memory/SKILL.md and read by ahel’s review.

Turn repeated failures, corrections, and recurring requests into durable follow-up work.

  • When an agent hits the same failure twice, create a short memory note with the trigger, failed approach, corrected approach, and verification result.
  • Convert important corrections into board tasks or scheduled follow-ups instead of leaving them only in chat history.
  • After a user changes a preference, record the new preference in memory and mention the update in the next relevant run.
  • Pair with scheduler for check-ins such as "retest this flow tomorrow" or "review this integration every Monday".
  • Pair with hierarchy goals when the lesson belongs to a team, project, or organization rather than one agent.
  • Keep entries concise: problem, correction, evidence, next trigger.
  • Prefer updating an existing memory cluster over creating duplicate notes for the same issue.
  • If a correction changes a standard operating pattern, recommend enabling or updating the matching skill pack.

Signals

GitHub stars
100
Forks
2
Last commit
Sep 2026
Advanced
Item type
skill
Key
proactive-memory
Source
github.com/aaronnat23/disp8ch