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.
npx skills add Mnemosyne-OS/Mnemosyne-Neural-OS --skill mnemosyne-memorygit clone --depth 1 https://github.com/Mnemosyne-OS/Mnemosyne-Neural-OSWrote 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.
[](https://agentmods.dev/skills/mnemosyne-os/mnemosyne-neural-os/mnemosyne-memory)<a href="https://agentmods.dev/skills/mnemosyne-os/mnemosyne-neural-os/mnemosyne-memory"><img src="https://agentmods.dev/badge/skills/mnemosyne-os/mnemosyne-neural-os/mnemosyne-memory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mnemosyne-os/mnemosyne-neural-os/mnemosyne-memory"><img src="https://agentmods.dev/badge/skills/mnemosyne-os/mnemosyne-neural-os/mnemosyne-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.01395 |
| Opus 5.5 | $0.00029 | $0.00558 |
| Sonnet 5.5 | $0.00014 | $0.00279 |
| Haiku 4.5 | $0.00007 | $0.00139 |
Grade A, and why
mnemosyne-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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mnemosyne Memory
Mnemosyne OS is a local-first memory operating system owned by a human. Their memory
is organized into vaults — isolated stores, one per life domain (code, notes, research,
journal…). Each memory is a chronicle: content + a spineType (its semantic kind) +
a vector embedding. You reach it through the @mnemosyne_os/mcp MCP server, which exposes
semantic retrieval (mnemosyne_memory_query, mnemosyne_memory_ask) and persistence (mnemosyne_memory_ingest).
You are a guest in someone's memory. That framing decides everything below.
Setup (if the mnemosyne_* tools are not available)
This skill relies on MCP tools (mnemosyne_memory_query, mnemosyne_memory_ask, mnemosyne_vault_list,
mnemosyne_memory_ingest, …) provided by the @mnemosyne_os/mcp server, which bridges to a
locally running Mnemosyne OS Infinity.
If those tools are not present in your session, do not install or configure anything yourself. Ask the human to add the server to their agent's MCP configuration — the recipe for every major client is in the package README.
Configuration is deliberately the human's gesture, because it is the scope grant:
the MNEMO_VAULTS list decides which vaults this agent may reach, plus the default vault.
A vault outside it is refused (UNREACHABLE_VAULT). Suggest keeping the grant narrow and
pointing the default write vault at a vault dedicated to agent work.
The covenant — non-negotiable rules
- Discover before you target. Call
mnemosyne_vault_listbefore choosing a vault. Never guess a vault id.UNREACHABLE_VAULTorSCOPE_DENIEDmeans the human did not grant it — say so and stop; never try to route around it. - Read before you write. Operate as an observer first: query, learn the shape of the human's memory, and only persist once you understand where a memory belongs.
- Respect protection levels. A vault marked MAXIMUM (private — e.g. a journal)
must never be read for cross-domain work, mixed, or written to, unless the human
explicitly asks in the current conversation. A vault marked isolated
(
mixableWith: []) must never be blended with content from other vaults. - Ingest is permanent and shared. Everything you persist will be read by every future agent and by the human. Never ingest secrets, credentials, raw dumps, or transient chatter.
- Never bypass the MCP. Do not open, copy, or edit Mnemosyne's vault databases or watched folders directly on the filesystem — even if you have file tools. The MCP is the governed door; the filesystem is not.
- Deletion belongs to the human. Never delete or rewrite existing chronicles. If something looks wrong or stale, tell the human and let them decide.
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.
- 12d ago Changed 44e284d2c036
- 1mo ago Changed 45186ae0b893
- 1mo ago First seen · 99 lines · 72 tokens per session scan A bf9f66887cf1
mnemosyne-memory is a skill published in the GitHub repository Mnemosyne-OS/Mnemosyne-Neural-OS (20 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 1,395 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
knowledge-base
Skill "knowledge-base" from Pinvou/pinvou-agent, covering ima knowledge base, operations, routing rules, examples and file upload guard.
notes
Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
plur-create-engrams
Create or improve PLUR engrams from conversations, documents, decisions, observations, and explicit preferences. Use for memory extraction, engram authoring, or reviewing proposed memories, including global, scoped, pinned, retrieved, and provisional knowledge. Ordinary use of existing memories does not require this…
plur-memory
Persistent learning for AI agents. Open engram format. Your agent learns from corrections, remembers across sessions, and transfers knowledge across domains.
plur-session-end
Extract durable learnings at the end of a session. Saves corrections, preferences, and codebase patterns as engrams — nothing ephemeral, nothing sensitive.