Borrowing it
Nothing to install: this file belongs to memgraph/ai-toolkit. 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/memgraph/ai-toolkit/main/AGENTS.mdgit clone --depth 1 https://github.com/memgraph/ai-toolkitWrote 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/memgraph/ai-toolkit/agents-md)<a href="https://agentmods.dev/instructions/memgraph/ai-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/memgraph/ai-toolkit/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/memgraph/ai-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/memgraph/ai-toolkit/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 | $0.04177 | $0.04177 |
| Opus 5.5 | $0.01671 | $0.01671 |
| Sonnet 5.5 | $0.00835 | $0.00835 |
| Haiku 4.5 | $0.00418 | $0.00418 |
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.
How it starts
The opening of the file, as written. The whole thing — 285 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 coding-agent sessions (Claude Code, Codex, Copilot CLI,
Cursor, OpenCode, Antigravity CLI, Grok Build) 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. |
hygm/ |
Shared graph schema/ontology model (NodeType, RelationType with start_labels/end_labels, identity), its validation gate, the generic default model (default_model(), core and catch-all labels), and the strategies that produce one (ManualStrategy YAML; LlmRecommendationStrategy, which grows a model from new sessions with a caller-supplied LLM and observer). Pure Python, no Memgraph. Not the same package as agents/sql2graph's HyGM. |
unstructured2graph/ |
Chunks unstructured input (files/URLs/text) and runs entity/relation extraction through a pluggable ExtractionBackend (GLiNER2Backend by default -- local and LLM-free; LightRAGBackend retained -- LLM-based). 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. |
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.
- 2d ago Changed · +1 tokens per session feb987d30929
- 3d ago Changed · +1 lines · +128 tokens per session 81cdb9cf2da9
- 4d ago Changed · +8 tokens per session 23a059555661
- 5d ago Changed · +14 lines · +273 tokens per session 80235c50c56b
- 7d ago Changed · +12 lines · +192 tokens per session e8558e51d530
- 8d ago Changed · +5 lines · +126 tokens per session ff6ffec19803
- 9d ago Changed · +21 lines · +264 tokens per session 3c60fae75095
- 10d ago Changed · +20 tokens per session 8f15263e18eb
- 11d ago Changed · +35 tokens per session b48cafc71bb7
- 16d ago First seen · 232 lines · 3,130 tokens per session scan A 76a4ca64022d
ai-toolkit AGENTS.md is an instructions file published in the GitHub repository memgraph/ai-toolkit (116 stars, last pushed 2d ago), licensed MIT. It adds 4,177 tokens to every session, about $0.0167 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 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.
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.
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).