ai-toolkit AGENTS.md

Project instructions for Memgraph AI Toolkit, a collection of Python packages for building AI and agent applications on Memgraph, a graph database. They explain the repository layout, setup, and context-graph components.

In plain words
What is it for?
Navigating the packages, setting up the uv workspace, working with graph-database integrations and document-to-graph tools, and maintaining the context graph built from agent sessions.
Why use it?
They help an agent understand which package owns a change and keep shared instructions accurate as this multi-package workspace evolves.

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/memgraph/ai-toolkit/agents-md
Clone the repo
git clone --depth 1 https://github.com/memgraph/ai-toolkit

Made for: Codex, OpenCode.

Per session 2,316 This file is loaded in full into every session.
When invoked 2,316 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 $0.02316 $0.02316
Opus 5 $0.01158 $0.01158
Sonnet 5 $0.00463 $0.00463
Haiku 4.5 $0.00232 $0.00232

Measured 2d ago against content hash f629c4871565, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-toolkit 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 2d 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 · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for coding agents working in memgraph/ai-toolkit. Keep it in sync with the codebase — update it in the same PR as the change that makes part of it stale.

What this repo is

Memgraph AI Toolkit — a uv workspace of independently-versioned Python packages for building AI/agent applications on Memgraph: core DB utilities, framework integrations (LangChain, MCP, LightRAG), a document-to-graph pipeline, a SQL-to-graph migration agent, and Context Graph, a family of components that turn Claude Code / Codex agent sessions into a queryable Memgraph graph.

Repository layout

Path What it is
memgraph-toolbox/ Core Memgraph client/tooling. Dependency of nearly everything else here.
integrations/langchain-memgraph/ LangChain graph store, QA chain, toolkit.
integrations/mcp-memgraph/ MCP server exposing Memgraph to LLMs.
integrations/lightrag-memgraph/ LightRAG storage backends (KV/vector/doc-status/graph) on Memgraph.
unstructured2graph/ Chunks unstructured input (files/URLs/text) and hands chunks to LightRAG for entity extraction. Outside the Context Graph family but shares its testing conventions.
agents/sql2graph/ MySQL/Postgres → Memgraph migration agent. Has its own uv.lock/.python-version; run it with cd agents/sql2graph && uv run main.py.
context-graph/ The Context Graph family — see below.
scripts/dev-memgraph.sh Local dev lifecycle: exploration Memgraph + isolated test Memgraph for the context-graph family and unstructured2graph.
skills/release/SKILL.md Release process for every PyPI/Docker-published package.

The Context Graph family (context-graph/)

Package Role
agent-context-graph Event hub. Normalizes runtime hooks / SDK activity into a shared Event Protocol and routes it to graph connectors.
actions-graph Records tool calls/results/messages/subagent activity as (:Action)/(:Agent) nodes — observability, not memory.
skills-graph Tracks Agent-Skills-spec (:Skill) usage per session.
sessions-graph Owns (:User)/(:Session), durable (:Memory) writes/recall, and session reconciliation into (:Episode) + extracted entities.

Read the full file on GitHub · 178 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. 2d ago First seen · 178 lines · 2,316 tokens per session scan A f629c4871565

Subscribe to this mod's changes

ai-toolkit AGENTS.md is an instructions file published in the GitHub repository memgraph/ai-toolkit (112 stars, last pushed 4d ago), licensed MIT. It adds 2,316 tokens to every session, about $0.0116 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

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).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,040 tokens

langchain 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.

langchain-ai/langchain · 4,345 tokens