Back to Signal Feed
CodeTracked since May 18, 2026

Engram adds recall-based promoted observations for context reuse

Engram introduces read-side recall telemetry and promotion for stored observations by adding `recall_count` and `last_recalled_at`, then exposing a `/promoted` API and `mem_promoted` tool so high-recall observations can be surfaced by frequency.

recall_countlast_recalled_atPromotedObservations()GET /promoted

What Happened

  • Engram introduces read-side recall telemetry and promotion for stored observations by adding `recall_count` and `last_recalled_at`, then exposing a `/promoted` API and `mem_promoted` tool so high-recall observations can be surfaced by frequency.
  • Engram introduces read-side recall telemetry and promotion for stored observations by adding `recall_count` and `last_recalled_at`, then exposing a `/promoted` API and `mem_promoted` tool so high-recall observations can be surfaced by frequency.
  • 1 evidence item attached for review.

What is Different

Before

Scattered source updates, isolated context, and manual follow-up across multiple feeds.

Now

Adds a concrete memory-priority mechanism: read-frequency metrics are persisted per observation and a dedicated promotion path returns frequently recalled items first, enabling clients to prioritize high-value context at session start.

Why Track This

Why It Matters

Agents and tool integrators using Engram will get faster access to the memories that are actually reused most often, improving context quality and reducing time spent re-surfacing stale or irrelevant observations during session startup. The system now tracks recall frequency on reads (`Search()` and `GetObservation()`), stores it in `recall_count`/`last_recalled_at`, and exposes promoted results via `/promoted` and `mem_promoted`, so consumer code can implement memory promotion policies without scanning all observations. Continue monitoring whether automated traffic inflates recall metrics, whether fire-and-forget increments can silently miss updates, and whether promotion thresholds (`min_recalls`, `limit`) select useful context instead of noisy repeats.

Impact

Agents and tool integrators using Engram will get faster access to the memories that are actually reused most often, improving context quality and reducing time spent re-surfacing stale or irrelevant observations during session startup. The system now tracks recall frequency on reads (`Search()` and `GetObservation()`), stores it in `recall_count`/`last_recalled_at`, and exposes promoted results via `/promoted` and `mem_promoted`, so consumer code can implement memory promotion policies without scanning all observations. Continue monitoring whether automated traffic inflates recall metrics, whether fire-and-forget increments can silently miss updates, and whether promotion thresholds (`min_recalls`, `limit`) select useful context instead of noisy repeats.

What To Watch Next

  • Watch whether recall_count becomes a repeated pattern.
  • Track follow-up changes around AI Coding Agents.
  • Compare future signals against this evidence trail.
  • Re-check risk flags: automated_read_polling_inflates_recall_count, fire_and_forget_db_writes_drop_recall_updates.
Open Topic TimelineOpen Technical EventOpen Original Sourceautomated_read_polling_inflates_recall_count / fire_and_forget_db_writes_drop_recall_updates / promotion_threshold_may_surface_low_signal_items / scope_or_project_filter_misuse_exposes_wrong_context

Supporting Evidence

GITHUB ISSUEHigh Trust

Gentleman-Programming/engram Issue #95: feat(store): add recall tracking and promoted observations endpoint

Issue #95 proposes adding `recall_count` and `last_recalled_at` to `observations`, incrementing them on `Search()`/`GetObservation()`, and returning top-recalled items via `PromotedObservations()` through `GET /promoted` and `mem_promoted`.