cortex-mem AGENTS.md

A set of instructions for Cortex Memory, a Rust framework that gives AI agents persistent, searchable long-term memory.

In plain words
What is it for?
Use it when working on Cortex Memory or modifying how agents store, classify, retrieve, and search memories.
Why use it?
It explains how memories are organized across sessions, users, agents, and shared resources, including different levels of detail.

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/sopaco/cortex-mem/agents-md
Clone the repo
git clone --depth 1 https://github.com/sopaco/cortex-mem

Made for: Codex, OpenCode.

Per session 1,620 This file is loaded in full into every session.
When invoked 1,620 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 $0.01620 $0.01620
Opus 5 $0.00810 $0.00810
Sonnet 5 $0.00324 $0.00324
Haiku 4.5 $0.00162 $0.00162

Measured 2d ago against content hash a9fdfeb8e4e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cortex-mem 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 · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cortex Memory - AI Agent Context Guide

Essential context for AI coding agents working on this project.


Project Overview

Cortex Memory is a Rust-based AI-native memory framework providing persistent long-term memory for AI agents via:

  • Three-tier memory hierarchy (L0/L1/L2)
  • Virtual filesystem with cortex:// URI scheme
  • Vector-based semantic search (Qdrant)

Core Concepts

Memory Dimensions

Dimension Purpose Path Pattern
session Conversation memories cortex://session/{id}/timeline/...
user User-specific memories cortex://user/{user_id}/{category}/...
agent Agent-specific memories cortex://agent/{agent_id}/{category}/...
resources Shared knowledge cortex://resources/{name}/...

Three-Tier Layers

Layer Tokens Purpose File
L0 ~100 Quick relevance filtering .abstract.md
L1 ~2000 Context understanding .overview.md
L2 Full Complete original {name}.md

Search scoring: 0.2×L0 + 0.3×L1 + 0.5×L2

Data Flow

Message → Session (timeline/*.md) → Close → LLM Extract → Classify
    → user/agent/resources → Generate L0/L1 → Vector Index (Qdrant)

Workspace Structure

cortex-mem-core/      # Core business logic (src/lib.rs)
cortex-mem-service/   # REST API server (src/main.rs)
cortex-mem-cli/       # CLI tool (src/main.rs)
cortex-mem-mcp/       # MCP protocol server (src/main.rs)
cortex-mem-tools/     # MCP tool definitions (src/lib.rs)
cortex-mem-config/    # Configuration parsing (src/lib.rs)
cortex-mem-rig/       # Rig integration (src/lib.rs)
cortex-mem-insights/  # Web dashboard (Svelte)

Build & Test

cargo build --workspace
cargo test --workspace
cargo clippy --workspace --all-targets -- -D warnings
cargo fmt --check

# Run service
cargo run --bin cortex-mem-service -- --config config.toml

# Run CLI
cargo run --bin cortex-mem -- --help

Read the full file on GitHub · 236 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 · 236 lines · 1,620 tokens per session scan A a9fdfeb8e4e4

Subscribe to this mod's changes

cortex-mem AGENTS.md is an instructions file published in the GitHub repository sopaco/cortex-mem (306 stars, last pushed 1mo ago), licensed MIT. It adds 1,620 tokens to every session, about $0.0081 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.