agentmods.dev

memv CLAUDE.md

memv CLAUDE.md is an instructions file for coding agents from vstorm-co/memv. It costs 1,576 tokens per session, scanned A, original, MIT.

Repository instructions for memv, a Python system that stores and retrieves time-based knowledge from conversations. They explain the project setup, commands, and quality checks.

In plain words
What is it for?
Use them when developing memv, installing dependencies with uv, running tests and checks, managing pre-commit hooks, or building its documentation.
Why use it?
They give an agent the project context and the exact commands needed to work consistently, format code, run tests, check types, and build documentation.

Instructions file

not rated 89 2d ago A scan 1,576 tokens original MIT
View the source file vstorm-co/memv
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/vstorm-co/memv/claude-md
Clone the repo
git clone --depth 1 https://github.com/vstorm-co/memv

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.

agentmods badge for memv CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vstorm-co/memv/claude-md.svg)](https://agentmods.dev/instructions/vstorm-co/memv/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vstorm-co/memv/claude-md"><img src="https://agentmods.dev/badge/instructions/vstorm-co/memv/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,576 This file is loaded in full into every session.
When invoked 1,576 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 $0.01576 $0.01576
Opus 5 $0.00788 $0.00788
Sonnet 5 $0.00315 $0.00315
Haiku 4.5 $0.00158 $0.00158

Measured 4d ago against content hash 96823732a2a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memv 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 4d 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 · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 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.

Project Overview

memv is a structured, temporal memory system for AI agents. It extracts and retrieves knowledge from conversations using a predict-calibrate approach (inspired by Nemori): importance emerges from prediction error, not upfront LLM scoring.

PyPI package name: memvee. Import name: memv.

Development Setup

Uses uv for dependency management. Requires Python 3.13.

make install                # uv sync + pre-commit hooks
make sync                   # update deps

Commands

# Quality
make format                 # ruff format + fix
make lint                   # ruff check + format check
make typecheck              # ty check src/
make all                    # format + lint + typecheck + test

# Testing
uv run pytest                                    # all tests
uv run pytest tests/test_models.py::test_name    # single test

# Docs
make docs                   # mkdocs build --strict
make docs-serve             # local preview

# Pre-commit
uv run pre-commit run --all-files

Pre-commit hooks (ruff-check, ruff-format, ty) run on src/ only.

Architecture

Data Flow

Messages → BatchSegmenter → Episodes → EpisodeGenerator → PredictCalibrateExtractor → SemanticKnowledge
                                                                    ↓
                                                    VectorIndex + TextIndex (per type)
                                                              ↓
                                                    Retriever (RRF fusion)

Key Modules (src/memv/)

memory/ — Memory class is the public API. Internally split into:

  • _api.py: add_message, add_exchange, retrieve, clear_user
  • _lifecycle.py: LifecycleManager (init/open/close, wires all components)
  • _pipeline.py: Pipeline (orchestrates processing stages)
  • _task_manager.py: TaskManager (auto-processing, buffering, background tasks)

Read the full file on GitHub · 130 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. 4d ago First seen · 130 lines · 1,576 tokens per session scan A 96823732a2a0

Subscribe to this mod's changes

memv CLAUDE.md is an instructions file published in the GitHub repository vstorm-co/memv (89 stars, last pushed 2d ago), licensed MIT. It adds 1,576 tokens to every session, about $0.0079 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.

agenticagentic-aiagentic-frameworkai-agentsai-memoryllm-agents
Related

Other instructions, from other repositories

deer-flow AGENTS.md

AGENTS.md instructions for bytedance/deer-flow, covering agents.md, what is deerflow, service topology, repository map and commands: root vs. module.

bytedance/deer-flow · 3,552 tokens

deer-flow copilot-instructions.md

Copilot instructions for bytedance/deer-flow, covering copilot onboarding instructions for deerflow, 1) repository summary, 2) runtime and toolchain requirements, 3) build/test/lint/run - verified command sequences and a. bootstrap and install.

bytedance/deer-flow · 1,714 tokens

deer-flow CLAUDE.md

Claude Code instructions for bytedance/deer-flow: The repo's agent guidance lives in AGENTS.md so it is shared across coding agents (Claude Code, Codex, and others). Claude Code imports it below.

bytedance/deer-flow · 50 tokens

agent-swarm CLAUDE.md

Claude Code instructions for desplega-ai/agent-swarm, covering agent swarm, architecture invariants, commands, code search and workflow.

desplega-ai/agent-swarm · 8,197 tokens

timps AGENTS.md

Instructions for Sandeeprdy1729/timps, covering agents.md — timps codebase guide, repo layout, typescript config drift, agent entrypoints (timps-code) and auto-capture & context-anywhere (timps setup / recall).

Sandeeprdy1729/timps · 24,407 tokens

code-conductor CLAUDE.md

Instructions for ryanmac/code-conductor, covering claude.md, project overview, documentation map, key development commands and running tests.

ryanmac/code-conductor · 2,962 tokens