supermemory CLAUDE.md

A set of project instructions for working on Supermemory, a codebase organized as a Turbo monorepo—a single repository containing multiple applications and shared packages.

In plain words
What is it for?
Use it when modifying Supermemory's web application, backend, shared packages, or development and checking workflows.
Why use it?
It gives an AI coding agent the repository structure, main technologies, and commands needed to work consistently across the project.

Instructions file

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/supermemoryai/supermemory/claude-md
Clone the repo
git clone --depth 1 https://github.com/supermemoryai/supermemory
Per session 884 This file is loaded in full into every session.
When invoked 884 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 $0.00884 $0.00884
Opus 5 $0.00442 $0.00442
Sonnet 5 $0.00177 $0.00177
Haiku 4.5 $0.00088 $0.00088

Measured 2d ago against content hash b4d129a7d8f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

supermemory CLAUDE.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.

CLAUDE.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Repository Structure

This is a Turbo monorepo containing multiple applications and shared packages:

Applications (apps/)

  • web/ - Next.js web application
  • mcp/ - Model Context Protocol server

Development Commands

Root Level (Monorepo)

  • bun run dev - Start all applications in development mode
  • bun run build - Build all applications
  • bun run check-types - Run TypeScript checks across all apps
  • bun run format-lint - Format and lint code using Biome

Web Application (apps/web/)

  • bun run dev - Start Next.js development server
  • bun run build - Build Next.js application
  • bun run lint - Run Next.js linting

Architecture Overview

Core Technology Stack

  • Runtime: Next.js (web)
  • Framework: Next.js (web)
  • Language: TypeScript throughout
  • Package Manager: Bun
  • Monorepo: Turbo
  • Authentication: Better Auth
  • Monitoring: Sentry

API Application (Primary Backend)

The API serves as the core backend with these key features:

Key API Routes

  • /v3/documents - CRUD operations for documents/memories
  • /v3/search - Semantic search across indexed content
  • /v3/connections - External service integrations (Google Drive, Notion, OneDrive)
  • /v3/settings - Organization and user settings
  • /v3/analytics - Usage analytics and reporting
  • /api/auth/* - Authentication endpoints

Web Application

Next.js application providing user interface for:

Key Libraries & Dependencies

Shared Dependencies

  • better-auth - Authentication system with organization support
  • drizzle-orm - Database ORM
  • zod - Schema validation
  • hono - Web framework (API & MCP)
  • @sentry/* - Error monitoring
  • turbo - Monorepo build system

Web-Specific

  • next - React framework
  • @radix-ui/* - UI components
  • @tanstack/react-query - Data fetching
  • recharts - Analytics visualization

Read the full file on GitHub · 121 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 · 121 lines · 884 tokens per session scan A b4d129a7d8f5

Subscribe to this mod's changes

supermemory CLAUDE.md is an instructions file published in the GitHub repository supermemoryai/supermemory (29,183 stars, last pushed today), licensed MIT. It adds 884 tokens to every session, about $0.0044 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.