nuzo-memory AGENTS.md

nuzo-memory AGENTS.md is an instructions file for Codex, OpenCode from fabionfsc/nuzo-memory. It costs 1,121 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Nuzo, a local-first memory system for AI coding assistants and other MCP-compatible agents. Local-first means the main data stays on the user’s machine, and auditable means changes can be inspected.

In plain words
What is it for?
Guiding work on Nuzo’s core packages, command-line tool, MCP server, host plugins, documentation, and local setup.
Why use it?
They give contributors a starting point and architectural boundaries while warning them not to expose secrets or private memory data.

Instructions file for CodexOpenCode

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 instructions/fabionfsc/nuzo-memory/agents-md
Clone the repo
git clone --depth 1 https://github.com/fabionfsc/nuzo-memory

Made for: Codex, OpenCode.

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 nuzo-memory AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fabionfsc/nuzo-memory/agents-md.svg)](https://agentmods.dev/instructions/fabionfsc/nuzo-memory/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/fabionfsc/nuzo-memory/agents-md"><img src="https://agentmods.dev/badge/instructions/fabionfsc/nuzo-memory/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,121 This file is loaded in full into every session.
When invoked 1,121 The same file — it is already loaded in full.
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 $0.01121 $0.01121
Opus 5 $0.00561 $0.00561
Sonnet 5 $0.00224 $0.00224
Haiku 4.5 $0.00112 $0.00112

Measured 4d ago against content hash 368597dc7b3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nuzo-memory 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 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.

AGENTS.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

This repository is the design, implementation, and documentation home for Nuzo.

Nuzo is a local-first, auditable memory layer for Codex, Claude Code, and MCP-compatible AI agents. Version 1.2.0 is the current public release.

Start Here

Read these first:

  1. README.md
  2. CONTRIBUTING.md
  3. docs/getting-started/index.md
  4. docs/operations/roadmap.md
  5. docs/architecture/overview.md
  6. docs/architecture/boundaries.md
  7. docs/spec/tools.md
  8. docs/spec/memory-model.md
  9. docs/spec/capture-suggestions.md

Use docs in docs/ as the source of detail. Keep root files short entry points.

Local Notes

If AGENTS.local.md exists at the repository root, read it after this file.

AGENTS.local.md is for machine-local operator preferences, temporary environment notes, and non-public workflow guidance. It is ignored by Git and must not be committed.

Do not put secrets, real memory exports, credentials, tokens, private user data, or personal operator notes in public docs, issues, examples, or tests.

Architecture Rules

  • Business logic belongs in packages/core.
  • CLI, MCP server, and host plugins must call core use cases instead of duplicating behavior.
  • MCP tool schemas are public contracts. Update docs/spec/tools.md before or alongside tool contract changes.
  • Host plugins should remain thin wrappers around the MCP server.
  • Storage starts with SQLite and SQLite FTS.
  • Optional local embeddings shipped; sync, encryption, and UI remain outside the final upstream release.
  • Do not introduce telemetry, network calls, remote embeddings, or silent inferred writes by default.
  • Inferred memories are drafts until the user confirms them.

Package Direction

The intended package direction is:

core -> cli/mcp-server -> memory package -> host plugins

Most users install @nuzo/memory. MCP hosts and generated host plugin artifacts resolve @nuzo/memory. Library-level integrations use @nuzo/memory-core. The official MCP Registry resolves the single-entrypoint @nuzo/memory-mcp distribution starting with 1.1.0; it reuses the shared MCP server build and is not a second implementation.

Read the full file on GitHub · 153 lines

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 · 153 lines · 1,121 tokens per session scan A 368597dc7b3b

Subscribe to this mod's changes

nuzo-memory AGENTS.md is an instructions file published in the GitHub repository fabionfsc/nuzo-memory (2 stars, last pushed 20d ago), licensed Apache-2.0. It adds 1,121 tokens to every session, about $0.0056 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 instructions, from other repositories

engraphis AGENTS.md

AGENTS.md instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, internal subagent delegation, 0. read this first — two architectures live in one package, 1. commands and ── unified dashboard + memory inspector ──.

Coding-Dev-Tools/engraphis · 4,947 tokens

basic-memory CLAUDE.md

Claude Code instructions for basicmachines-co/basic-memory, a project described as: AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN.

basicmachines-co/basic-memory · 3 tokens

claude-memory-mcp AGENTS.md

Instructions for WhenMoon-afk/claude-memory-mcp, covering mooncite repository contract, product boundary, fixed architecture, sources of truth and change discipline.

WhenMoon-afk/claude-memory-mcp · 2,331 tokens

wenlan CLAUDE.md

Claude Code instructions for 7xuanlu/wenlan, a project described as: Wenlan is a knowledge base for the AI-native age. Your AI agents capture what they learn, Wenlan keeps it current and distills it into source-cited wiki pages you can trust.

7xuanlu/wenlan · 99 tokens

Khaos-Brain AGENTS.md

Instructions for liuyingxuvka/Khaos-Brain, covering repository expectations, bootstrap, start here, purpose and github publish default.

liuyingxuvka/Khaos-Brain · 4,956 tokens

Agent-Memory-Bridge AGENTS.md

Instructions for zzhang82/Agent-Memory-Bridge, covering agent memory bridge contributor instructions, setup and checks, architecture boundaries, mutation and migration invariants and benchmark expectations.

zzhang82/Agent-Memory-Bridge · 1,089 tokens