skilld
All skills
shipshitdev avatar

/memory-systems

@d322667
by Ship Shitshipshitdev/library37 stars
3

Design and implement memory architectures for agent systems that persist state across sessions, maintain entity consistency, and reason over structured knowledge. Use when building agents that persist knowledge across sessions, choosing between memory frameworks, maintaining entity consistency, or designing memory architectures for production.

Ask your Agent

Use this Skill: https://skilld.dev/gh/shipshitdev/library/memory-systems

This session only. Nothing lands on disk.

README.md

≈589 tokens on demand. Your agent reads this file only when SKILL.md points to it.

memory-systems

Design layered agent memory architectures — working/short/long-term, entity, and temporal knowledge graphs — that persist state across sessions.

Upstream

Derived from muratcankoylan/Agent-Skills-for-Context-Engineering (MIT).

Field Value
Source skills/memory-systems/SKILL.md
Upstream ref main
Synced at commit 25e1fa79a33f
Last synced 2026-06-13
License MIT

Local modifications: Imported 2026-01-20 (this repo's commit ef42a98) from muratcankoylan/Agent-Skills-for-Context-Engineering at v1.0.0-era content. Ported forward 2026-06-13 to upstream HEAD (commit 25e1fa79a33f); local body now tracks upstream v4.1.0 — the largest drift of this cluster — carrying the Production Framework Landscape table (Mem0, Zep/Graphiti, Letta, Cognee, LangMem), named benchmark tables (DMR, LoCoMo, HotPotQA), 8-entry Gotchas, Error Recovery subsection, claim-* IDs, and updated framework-integration examples in references/implementation.md and scripts/memory_store.py. References to siblings not vendored here (filesystem-context, context-compression, bdi-mental-states) were stripped. Local divergence: a Neo4j backend mention in the references Graphiti example was genericized to 'graph database backend'. A 2026-06-13 review-hardening pass (CodeRabbit on PR #21) further diverges scripts/memory_store.py (deterministic SHA-256 embedding seed replacing salted hash(); time_filter now applied to the vector-search filters) and references/implementation.md (same SHA-256 seed fix, local RNG instead of global np.random.seed) — candidates to push upstream. To diff: compare the upstream path on main since commit 25e1fa79a33f.

Checking for upstream changes: when upstream has moved ahead of the synced marker above, diff skills/memory-systems/SKILL.md on main since commit 25e1fa79a33f, port anything worth bringing home, then bump metadata.upstream_commit (or metadata.upstream_version) and metadata.last_synced in SKILL.md and this table.

Source: SKILL.md on GitHub

Third-party checks

No alerts15d4 checks · Risk SAFE
  • Gen Agent Trust Hub15d

    The skill provides comprehensive design patterns and implementation examples for agent memory systems. It is technically sound and serves primarily as an architectural and educational resource. However, as with any system that ingests external data (such as documents or chat history) to be retrieved and injected into the agent's prompt, it establishes a surface for indirect prompt injection.

  • Socket15d

    No alerts

  • Snyk15d

    Risk: LOW · No issues

  • Runlayer7mo

    3/4 files flagged

Provenance

Signed by skilld at d322667. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated 3 months ago

Capability

Other metadata
metadata
{
  "version": "4.1.0",
  "source": "https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/blob/main/skills/memory-systems/SKILL.md",
  "upstream_repo": "muratcankoylan/Agent-Skills-for-Context-Engineering",
  "upstream_ref": "main",
  "upstream_commit": "25e1fa79a33f",
  "last_synced": "2026-06-13",
  "license": "MIT",
  "tags": "memory, agents, architecture"
}

README badge

README badge for shipshitdev/library/memory-systems