You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Feature: Hierarchical Long-Term Memory for Squad Agents #1184
Feature: Hierarchical Long-Term Memory for Squad Agents
Problem
Squad's memory has gaps that worsen as projects grow:
history.md is chronological, not structural — agents know what happened but not how the system works. Architecture knowledge is scattered across summarized sessions.
No hierarchical loading — all context loads at once. A small bug fix gets the same context payload as a major refactor.
Coordinator has no memory — re-discovers user preferences, workflows, and project layout every session.
No ownership boundaries — any agent can read/write any file, risking mental model corruption across domains.
Solution
A two-tier structured memory layer alongside existing files (history.md and decisions.md remain unchanged):
Tier
File
Size Limit
Loaded
1 — Index
memory.md
≤10KB
Always at spawn
2 — Topics
memory-{topic}.md
≤20KB each
On demand per task
Index contains: quick reference, architecture overview, core interfaces, topic index, cross-cutting patterns, key decisions, user preferences.
Topic files contain deep knowledge per subsystem (e.g., memory-detection-engines.md, memory-keel.md, memory-kusto-queries.md).
Key Design Decisions
Agent ownership — each agent reads/writes only its own memory. Coordinator never writes to agent memory directly; it spawns the owning agent instead.
Coordinator memory — separate memory.md at .squad/ level for workflow patterns, user preferences, routing rules.
Human override — "Remember that…" / "Forget that…" / "Load memory" commands route through ownership rules.
Markdown over database — human-readable, git-versionable, works across all Copilot surfaces (CLI, VS Code, GitHub.com).
Purely additive — no changes to history.md, decisions.md, Scribe, progressive summarization, or any existing behavior.
Changes Required
Templates: new memory.md and coordinator-memory.md templates, ## Memory section in charter
Init/spawn flows: create and load memory files
Coordinator: handle remember/forget/load-memory intents, read/write own memory
Scribe: read-only access to memory for state preservation
Thanks for this! Tiered/hierarchical memory is tracked in #600, #595, and #686 which cover the hot/cold/wiki layer architecture. Closing as duplicate — please follow those issues for updates.
Activity
bradygaster commentedon Jun 9, 2026
Thanks for this! Tiered/hierarchical memory is tracked in #600, #595, and #686 which cover the hot/cold/wiki layer architecture. Closing as duplicate — please follow those issues for updates.