MemOS CLAUDE.md

A Claude Code project guide for MemTensor’s MemOS repository, a Python library and web service for AI-agent memory. It describes Claude-specific helpers and where the project’s API contract is documented.

In plain words
What is it for?
It supports code exploration, design and code review, backend development, integration testing, and keeping the documented API in sync with changes.
Why use it?
It helps Claude Code choose the right specialist for a task and follow the repository’s testing and API-update rules.

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/memtensor/memos/claude-md
Clone the repo
git clone --depth 1 https://github.com/MemTensor/MemOS
Per session 284 This file is loaded in full into every session.
When invoked 284 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 $0.00284 $0.00284
Opus 5 $0.00142 $0.00142
Sonnet 5 $0.00057 $0.00057
Haiku 4.5 $0.00028 $0.00028

Measured 2d ago against content hash b0f641e6388a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

MemOS 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 · 24 lines

What it actually says

CLAUDE.md

Claude Code Entry

Project facts live in AGENTS.md. This file only covers Claude Code runtime adaptation.

Sub-agents

Five project-recommended sub-agents live under .claude/agents/*.md. Claude Code loads them automatically; the main agent should dispatch by task boundary:

Agent Permissions When to use
explorer Read-only Locate code, trace call chains, gather evidence
design-reviewer Read-only Review design docs (architecture / interface / performance / security / requirement coverage)
code-reviewer Read-only Review diffs and return APPROVE or CHANGES_REQUESTED
backend-dev Read-write Implement backend / library code under src/memos/ (TDD)
integration-tester Read-write Author and run integration / end-to-end cases under tests/

The main repo has no frontend stack, so no frontend-dev is provided; TypeScript sub-projects under apps/ use their own AI configuration.

Project knowledge

Before starting a task, run ls docs/. docs/openapi.json is the source of truth for the API contract; after touching src/memos/api/, run make openapi to regenerate it.

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 · 24 lines · 284 tokens per session scan A b0f641e6388a

Subscribe to this mod's changes

MemOS CLAUDE.md is an instructions file published in the GitHub repository MemTensor/MemOS (11,141 stars, last pushed today), licensed Apache-2.0. It adds 284 tokens to every session, about $0.0014 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.