What is ainative-zerodb-memory-mcp AGENTS.md?

Repository instructions for AI coding agents working on a Node.js server that gives agents memory, planning, and write-back tools. They describe the project layout, constraints, and test commands.

Use them to understand the repository, find key files, run its tests, and follow requirements when modifying the MCP server.

They give an agent the local rules it needs before changing code, reducing mistakes such as using the wrong test runner or ignoring project-specific constraints.

How AINative-Studio/ainative-zerodb-memory-mcp configures Codex and Op

Reuse

Borrowing it

Nothing to install: this file belongs to AINative-Studio/ainative-zerodb-memory-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/AINative-Studio/ainative-zerodb-memory-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/AINative-Studio/ainative-zerodb-memory-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ainative-studio/ainative-zerodb-memory-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/ainative-studio/ainative-zerodb-memory-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ainative-studio/ainative-zerodb-memory-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ainative-studio/ainative-zerodb-memory-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ainative-studio/ainative-zerodb-memory-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ainative-studio/ainative-zerodb-memory-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 603 This file is loaded in full into every session.

When invoked 603 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00603	$0.00603
Opus 5.5	$0.00241	$0.00241
Sonnet 5.5	$0.00121	$0.00121
Haiku 4.5	$0.00060	$0.00060

Measured 13d ago against content hash 8be7bf6f358f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ainative-zerodb-memory-mcp 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 13d 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 · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Instructions for AI coding agents (Claude Code, Cursor, Windsurf, etc.) working in this repository.

What this repo is

An MCP (Model Context Protocol) server providing 18 tools for AI agent memory: 9 memory tools (store/search/semantic-search/context/embedding/session management), 4 plan-artifact tools (persistent plans/PRDs with diff history across sessions), and 5 write-back tools (Slack, Gmail, Calendar, GitHub, Notion). Plain Node.js (no TypeScript build step), type: module.

Project structure

index.js — MCP server entry point
src/tools/memory-tools.js — the 9 memory tools
src/tools/plan-tools.js — the 4 plan-artifact tools
src/tools/writeback-tools.js — the 5 write-back tools
src/client/zerodb-client.js — HTTP client talking to the ZeroDB backend (POST /api/v1/public/memory/v2/recall and /remember)
src/utils/memory-manager.js — scope/session resolution logic sitting between the tools and the client
tests/*.test.js — Node's built-in test runner (node --test), no Jest/Mocha

Running tests

npm test             # node --test tests/*.test.js
npm run test:coverage  # same, with c8 coverage

Always run tests before committing. No separate lint/build step — this is plain JS.

Key constraints

Backend namespace model: the ZeroDB backend only recognizes two namespaces — global and session:<id> (see _validate_namespace in the core backend). There is no per-agent namespace. scope: 'agent' and scope: 'global' are therefore equivalent in zerodb-client.js — both search broadly; only scope: 'session' narrows the query, and it requires a sessionId. Don't reintroduce a fictional per-agent scope without a corresponding backend change.
No build step: this package ships plain JS directly (see package.json's lack of a build script). Don't add TypeScript or a bundler without discussing it first — every consumer currently runs this via npx against the published JS.
Versioning discipline: bump package.json's version and publish to npm (npm publish) whenever a change affects runtime behavior — a merged-but-unpublished fix is invisible to every consumer running npx ainative-zerodb-memory-mcp@latest.

Read the full file on GitHub · 39 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.

13d ago First seen · 39 lines · 603 tokens per session scan A 8be7bf6f358f

Subscribe to this mod's changes

ainative-zerodb-memory-mcp AGENTS.md is an instructions file published in the GitHub repository AINative-Studio/ainative-zerodb-memory-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 603 tokens to every session, about $0.0024 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 2026-10-24.

Building agents

ainative-zerodb-memory-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ainative-zerodb-memory-mcp AGENTS.mdAINative-Studio/ainative-zerodb-memory-mcp	Instructions file	1	2d ago	MIT	A	603	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

ainative-zerodb-memory-mcp: Instructions file for Codex