Project guidance for Cortex, a Rust-based memory engine for AI agents. It describes an embedded database, graph and vector search, network APIs, client libraries, and commands for building and testing the workspace.

Building the Cortex server, running all workspace tests, testing without the optional Warren adapter, running the Rust linter, and initialising Cortex configuration.

It gives the coding agent a map of the repository and the commands needed to check changes. This makes work across its Rust crates and language libraries more predictable.

How MikeSquared-Agency/cortex configures Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to MikeSquared-Agency/cortex. 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/MikeSquared-Agency/cortex/main/.cursorrules

Clone the repo

git clone --depth 1 https://github.com/MikeSquared-Agency/cortex

Made for: Cursor.

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/rules/mikesquared-agency/cortex/cursorrules/github.svg)](https://agentmods.dev/rules/mikesquared-agency/cortex/cursorrules)

Your own site

<a href="https://agentmods.dev/rules/mikesquared-agency/cortex/cursorrules"><img src="https://agentmods.dev/badge/rules/mikesquared-agency/cortex/cursorrules/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/rules/mikesquared-agency/cortex/cursorrules"><img src="https://agentmods.dev/badge/rules/mikesquared-agency/cortex/cursorrules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 777 This file is loaded in full into every session.

When invoked 777 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	$0.00777	$0.00777
Opus 5.5	$0.00311	$0.00311
Sonnet 5.5	$0.00155	$0.00155
Haiku 4.5	$0.00078	$0.00078

Measured 2mo ago against content hash 145806383846, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cursorrules 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 2mo 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.

.cursorrules · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Cortex Agent Guide

What is this?

Cortex is an embedded graph memory engine for AI agents. Rust, redb (embedded DB), gRPC + HTTP APIs, vector search (HNSW), auto-linking.

Repo structure

crates/
  cortex-core/     — Storage, graph, vector, auto-linker, types. The library.
  cortex-server/   — gRPC/HTTP server, CLI, config. The binary.
  cortex-client/   — Rust gRPC client crate.
  cortex-proto/    — Protobuf definitions + generated code.
  warren-adapter/  — Optional Warren integration (feature-gated).
sdks/
  typescript/      — @cortex/client npm package
  python/          — cortex-memory PyPI package
  go/              — Go client module
specs/             — Design specs (tagged IMPLEMENTED/DEFERRED)
docs/              — User-facing documentation
examples/          — Integration examples (LangChain, CrewAI, etc.)

Build & test

cargo test --workspace                          # All 176 tests
cargo test --workspace --no-default-features    # Without warren adapter
cargo build -p cortex-server --release          # Release binary
cargo clippy --workspace                        # Lint

Run

cortex init                    # Create cortex.toml
cortex serve                   # Start server (gRPC :9090, HTTP :9091)
cortex node create --kind fact --title "..."
cortex search "query"
cortex briefing <agent-id>
cortex shell                   # Interactive REPL

Key types

NodeKind / Relation — validated string newtypes (not enums)
Cortex::open(path) — library mode, no server needed
Storage trait — RedbStorage implements it
IngestAdapter trait — pluggable event sources
Config: cortex.toml with #[serde(default)] on all structs

Architecture decisions

redb for storage (embedded, ACID, zero-copy mmap)
HNSW for vector search (instant-distance crate)
gRPC (tonic) for production API, HTTP (axum) for debug/viz
warren-adapter is optional (--features warren), cortex-core has zero network deps
Auto-linker runs background loop: similarity rules → edges, decay → prune, dedup → merge

Read the full file on GitHub · 88 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.

2mo ago First seen · 88 lines · 777 tokens per session scan A 145806383846

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository MikeSquared-Agency/cortex (11 stars, last pushed 3mo ago), licensed MIT. It adds 777 tokens to every session, about $0.0031 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.

Databases Memory and context

cursorrules next to 6 cursor rules from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cursorrulesMikeSquared-Agency/cortex	Cursor rule	11	3mo ago	MIT	A	777	Cursor
mongodb-memory-server-setupprisma/orm	Cursor rule	48k	yesterday	Apache-2.0	A	28	Cursor
token-optimizationprest/prest	Cursor rule	4.6k	3d ago	MIT	A	876	Cursor
memorymatrixorigin/memoria	Cursor rule	623	2d ago	Apache-2.0	A	2,700	Cursor
memory-branching-patternsmatrixorigin/memoria	Cursor rule	623	2d ago	Apache-2.0	A	18	Cursor
cursor-rulesMatthewSherlin/mushroomdb	Cursor rule	5	today	none	A	1,337	Cursor
common_memory_bankshalomeir/common-memory-bank	Cursor rule	30	7mo ago	Unlicense	A	1,801	Cursor

cortex: Cursor rule for Cursor