Borrowing it
Nothing to install: this file belongs to 28naem-del/mnemosyne. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/28naem-del/mnemosyne/main/AGENTS.mdgit clone --depth 1 https://github.com/28naem-del/mnemosyneWrote 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/instructions/28naem-del/mnemosyne/agents-md)<a href="https://agentmods.dev/instructions/28naem-del/mnemosyne/agents-md"><img src="https://agentmods.dev/badge/instructions/28naem-del/mnemosyne/agents-md/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/instructions/28naem-del/mnemosyne/agents-md"><img src="https://agentmods.dev/badge/instructions/28naem-del/mnemosyne/agents-md.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 | $0.01220 | $0.01220 |
| Opus 5.5 | $0.00488 | $0.00488 |
| Sonnet 5.5 | $0.00244 | $0.00244 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
mnemosyne AGENTS.md 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 3d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for coding agents (Claude Code, Cursor, Codex, Copilot and others) that work inside this repository or want to use it as memory. A shorter, link-only summary for retrieval is in llms.txt.
What this repository is
mnemosy-ai is local-first, long-term memory for AI agents: a SQLite store that keeps memories with their evidence, retires dependent guidance when a source is corrected, and serves recall and context over TypeScript, MCP, CLI and HTTP. The README states the measured results and the two release targets that are not met; keep both halves when you touch any claim.
It is a separate project from mnemosyne-oss/mnemosyne, the Python mnemosyne-memory package; the two share a name, not code or maintainers. Do not mix their APIs, install commands or issue trackers.
Use it as memory for your own agent
- Install:
npm install mnemosy-ai(latestis the stable 2.0.0; pin[email protected]for a reproducible install; the older 1.x engine stays installable asmnemosy-ai@1). The newest pre-release is 3.0.0-rc.4 on thenextchannel:npm install mnemosy-ai@next(or pin[email protected]); it is a breaking release, see docs/MIGRATION-v3.md. - MCP: see the server entry in the README. Tools are named
memory_*;--read-onlyremoves mutation tools;--allow-destructiveis required for forgetting. - SDK:
createLocalMemoryfrommnemosy-ai/local; contracts in docs/api.md and docs/CONTEXT.md. - Trust and scope are controller assertions. A model talking to the MCP server cannot change its workspace, raise its own trust or record its own skill trials.
Work on the code
- Node.js 22.16 or newer (24 recommended).
npm ci --ignore-scripts, thennpm run build, thennpm rebuild hnswlib-node && npm run setup:embedder && npm run setup:reranker(the optional native dense index and the pinned local models;npm testfails its env-gate check if tests that need them were skipped, as in CI). See CONTRIBUTING.md. - Full gate before any pull request:
npm run check(typecheck, tests, example typecheck),npm run check:docs(local Markdown links and anchors),npm run check:public(package identity and public surfaces). CI runs the same three plusnpm auditand an isolated install of the packed tarball. - Tests live in
tests/(Vitest). Add a failing test before a fix; the repository history records tests red before green. - Source is
src/; published code isdist/(built, not committed). Public entry points are listed underexportsin package.json. - Documentation is part of the contract. If behaviour changes, update the matching guide in
docs/and the CHANGELOG entry under[Unreleased]with the commit that made the change.
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.
- 3d ago Changed · +2 lines · +144 tokens per session 1079c0d3a90f
- 4d ago Changed · +6 lines · +255 tokens per session 17122be92088
- 5d ago Changed · +20 tokens per session d2b659001a97
- 11d ago First seen · 40 lines · 801 tokens per session scan A 8cbc9e30a879
mnemosyne AGENTS.md is an instructions file published in the GitHub repository 28naem-del/mnemosyne (154 stars, last pushed 3d ago), licensed MIT. It adds 1,220 tokens to every session, about $0.0049 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 2026-10-22.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.