memory-systems

A guide to giving AI agents long-term memory so they can retain knowledge between conversations. It compares memory frameworks and persistence designs, including systems that store relationships between entities.

In plain words
What is it for?
It is for choosing or implementing memory systems, storing and retrieving past knowledge, maintaining entity consistency, and designing cross-session agent behaviour.
Why use it?
Without persistent memory, an agent loses important context when a session ends and may not keep facts consistent over time.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/luizedupp/rememb/memory-systems
Any agent
npx skills add LuizEduPP/Rememb --skill memory-systems
Clone the repo
git clone --depth 1 https://github.com/LuizEduPP/Rememb

Made for: Claude Code, Codex.

Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,311 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00115 $0.03311
Opus 5 $0.00057 $0.01656
Sonnet 5 $0.00023 $0.00662
Haiku 4.5 $0.00012 $0.00331

Measured 2d ago against content hash cd0fbc8fc3ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memory-systems scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/memory_store.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

src/rememb_skills/memory-systems/SKILL.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory System Design

Memory provides the persistence layer that allows agents to maintain continuity across sessions and reason over accumulated knowledge. Simple agents rely entirely on context for memory, losing all state when sessions end. Sophisticated agents implement layered memory architectures that balance immediate context needs with long-term knowledge retention. The evolution from vector stores to knowledge graphs to temporal knowledge graphs represents increasing investment in structured memory for improved retrieval and reasoning.

When to Use

Activate this skill when:

  • Building agents that must persist knowledge across sessions
  • Choosing between memory frameworks (Mem0, Zep/Graphiti, Letta, LangMem, Cognee)
  • Needing to maintain entity consistency across conversations
  • Implementing reasoning over accumulated knowledge
  • Designing memory architectures that scale in production
  • Evaluating memory systems against benchmarks (LoCoMo, LongMemEval, DMR)
  • Building dynamic memory with automatic entity/relationship extraction and self-improving memory (Cognee)

Core Concepts

Think of memory as a spectrum from volatile context window to persistent storage. Default to the simplest layer that meets retrieval needs, because benchmark evidence shows tool complexity matters less than reliable retrieval — Letta's filesystem agents scored 74% on LoCoMo using basic file operations, beating Mem0's specialized tools at 68.5%. Add structure (graphs, temporal validity) only when retrieval quality degrades or the agent needs multi-hop reasoning, relationship traversal, or time-travel queries.

Detailed Topics

Production Framework Landscape

Select a framework based on the dominant retrieval pattern the agent requires. Use this table to narrow the shortlist, then validate with the benchmark data below.

Framework Architecture Best For Trade-off
Mem0 Vector store + graph memory, pluggable backends Multi-tenant systems, broad integrations Less specialized for multi-agent
Zep/Graphiti Temporal knowledge graph, bi-temporal model Enterprise requiring relationship modeling + temporal reasoning Advanced features cloud-locked
Letta Self-editing memory with tiered storage (in-context/core/archival) Full agent introspection, stateful services Complexity for simple use cases
Cognee Multi-layer semantic graph via customizable ECL pipeline with customizable Tasks Evolving agent memory that adapts and learns; multi-hop reasoning Heavier ingest-time processing
LangMem Memory tools for LangGraph workflows Teams already on LangGraph Tightly coupled to LangGraph
File-system Plain files with naming conventions Simple agents, prototyping No semantic search, no relationships

Read the full file on GitHub · 238 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 238 lines · 115 tokens per session scan A cd0fbc8fc3ab

Subscribe to this mod's changes

memory-systems is a skill published in the GitHub repository LuizEduPP/Rememb (4 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 3,311 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

claude-api

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…

Prismer-AI/PrismerCloud · 193 tokens

agent-coordination

Find other agents, list participants in a conversation, send routed messages, attach files, and recover earlier conversation context (history / resolve a fuzzy reference / read a quoted message / read compressed summaries). Use whenever you need to delegate to another agent, address a peer in a multi-agent…

Prismer-AI/PrismerCloud · 122 tokens

image-generate

Generate an image from a text prompt via the cloud LLM image proxy, persist it as a content-addressed workspace asset, and return a ContentBlock that downstream renderers can attach. Use whenever the user asks "draw / generate / make an image of …", an agent needs a diagram / illustration as a follow-up artifact, or a…

Prismer-AI/PrismerCloud · 103 tokens

claim-agent-ownership

Orchestrator skill for resolving multi-daemon binding contention. Use when you (the orchestrator) detect an agent.binding.contested sync event indicating two daemons are racing for the same agent — explicitly rebind ownership to a chosen target daemon so subsequent dispatches route deterministically. Implements Gap…

Prismer-AI/PrismerCloud · 101 tokens

prismer-im-collab

Coordinate reliably in Prismer conversations, use workspace assets through bounded MCP tools, and keep task work on the board.

Prismer-AI/PrismerCloud · 30 tokens

human-approval

Request human approval before performing a SAFETY-CRITICAL, IRREVERSIBLE, or SCOPE-EXPANDING action — submit a structured context (action, scope, risk, consequence) plus options, then STOP the current turn. The platform redispatches the agent after the human decides. NEVER use for routine deliverables (writing docs /…

Prismer-AI/PrismerCloud · 168 tokens