memoria-memory

memoria-memory is a skill for Claude Code, Codex from matrixorigin/memoria. It costs 50 tokens per session (416 once invoked), scanned A, original, Apache-2.0.

A memory system for saving and retrieving durable facts about a user, project, or earlier session. It also supports correcting and deleting stored memories.

In plain words
What is it for?
Use it when someone asks to remember, recall, update, correct, or forget information.
Why use it?
It prevents useful context from being lost between sessions and avoids relying on ordinary memory files when a durable record is needed.

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/matrixorigin/memoria/memoria-memory
Any agent
npx skills add matrixorigin/memoria --skill memoria-memory
Clone the repo
git clone --depth 1 https://github.com/matrixorigin/memoria

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for memoria-memory

README.md
[![agentmods](https://agentmods.dev/badge/skills/matrixorigin/memoria/memoria-memory.svg)](https://agentmods.dev/skills/matrixorigin/memoria/memoria-memory)
Your own site
<a href="https://agentmods.dev/skills/matrixorigin/memoria/memoria-memory"><img src="https://agentmods.dev/badge/skills/matrixorigin/memoria/memoria-memory.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 416 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 $0.00050 $0.00416
Opus 5 $0.00025 $0.00208
Sonnet 5 $0.00010 $0.00083
Haiku 4.5 $0.00005 $0.00042

Measured 4d ago against content hash 134fab5cebc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memoria-memory 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 4d ago.

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.

plugins/openclaw/skills/memoria-memory/SKILL.md · 44 lines

What it actually says

Memoria Memory

Use Memoria tools for durable memory. Do not default to MEMORY.md or memory/YYYY-MM-DD.md unless the user explicitly asks for file-based memory.

When to use

  • The user asks you to remember a fact, preference, decision, or workflow.
  • The user asks what you already know about them, the project, or a prior session.
  • The user asks to correct, update, or delete stored memory.

Store

  1. Choose the smallest durable fact worth keeping.
  2. Use the most specific tool available:
    • memory_profile for stable user preferences or profile traits
    • memory_store for facts, procedures, and project knowledge
  3. Prefer short, atomic entries.
  4. After storing something important, verify with memory_recall or memory_search.

Recall

  1. When the user asks "what do you know", "what do you remember", or refers to a prior session, query Memoria first.
  2. Use memory_recall for semantic retrieval and memory_get only when you already have a specific memory id.

Repair

  1. If the user says a memory is wrong, use memory_correct.
  2. If the user wants it removed, use memory_forget or memory_purge.
  3. After repair, verify with memory_recall or memory_search.

Rules

  • Do not claim only memory_search and memory_get exist when other memory_* tools are available.
  • Do not store transient small talk unless the user asks or it is clearly a stable preference.
  • Prefer Memoria for durable cross-session memory; prefer workspace files only for explicit file-based notes.
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. 4d ago First seen · 44 lines · 50 tokens per session scan A 134fab5cebc0

Subscribe to this mod's changes

memoria-memory is a skill published in the GitHub repository matrixorigin/memoria (592 stars, last pushed 8d ago), licensed Apache-2.0. It adds 50 tokens to every session and 416 once invoked, about $0.0003 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 2026-08-30.