Memgentic: Instructions file for Claude Code

CLAUDE.md

Memgentic CLAUDE.md is an instructions file for Claude Code, Codex from Chariton-kyp/Memgentic. It costs 5,367 tokens per session, scanned A, original, Apache-2.0.

A project guide for Memgentic, a shared memory system that captures knowledge from AI conversations and makes it searchable. It describes a monorepo, which is one repository containing several related packages, including a reusable core.

In plain words
What is it for?
Use it when navigating Memgentic, changing its memory storage or search code, or deciding where new features and dependencies belong.
Why use it?
It helps keep work consistent across the repository and preserves the rule that lower-level core code must not depend on higher-level parts.

Instructions file for Claude CodeCodex

Written for Claude Code and Codex: SessionStart hook event, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is Chariton-kyp/Memgentic's own configuration. It tells Claude Code and Codex how to work on Memgentic itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Memgentic configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Chariton-kyp/Memgentic. 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/Chariton-kyp/Memgentic/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Chariton-kyp/Memgentic

Made for: Claude Code, Codex.

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 Memgentic CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chariton-kyp/memgentic/claude-md/github.svg)](https://agentmods.dev/instructions/chariton-kyp/memgentic/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/chariton-kyp/memgentic/claude-md"><img src="https://agentmods.dev/badge/instructions/chariton-kyp/memgentic/claude-md/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.

agentmods 80×15 button for Memgentic CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/chariton-kyp/memgentic/claude-md"><img src="https://agentmods.dev/badge/instructions/chariton-kyp/memgentic/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,367 This file is loaded in full into every session.
When invoked 5,367 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.05367 $0.05367
Opus 5 $0.02684 $0.02684
Sonnet 5 $0.01073 $0.01073
Haiku 4.5 $0.00537 $0.00537

Measured 9d ago against content hash abaaa12488cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Memgentic 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 9d 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 · 389 lines

How it starts

The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Overview

Memgentic (Μνήμη) — Universal AI Memory Layer. Zero-effort knowledge capture across all AI tools. Source-aware memory with semantic search, filtering, and knowledge graphs.

Named after the Greek Titaness of memory, mother of the Muses.

The Problem We Solve

Every AI conversation is ephemeral — knowledge is lost when the session ends. Worse, knowledge is siloed: what Claude knows, ChatGPT doesn't, and vice versa. No universal memory layer exists that captures knowledge automatically from all AI tools and makes it available everywhere.

Memgentic is that missing layer.

Architecture: Monorepo with Extractable Core

memgentic/              ← Independent package (core engine, extractable)
├── memgentic/
│   ├── config.py        Settings (Pydantic)
│   ├── models.py        Data models (Memory, SourceMetadata, SessionConfig)
│   ├── cli.py           CLI tool (Click + Rich)
│   ├── storage/
│   │   ├── metadata.py  SQLite + FTS5 (metadata, full-text search)
│   │   └── vectors.py   Qdrant (semantic vector search)
│   ├── processing/
│   │   ├── embedder.py  Embedding generation (Ollama / OpenAI)
│   │   ├── pipeline.py  Ingestion pipeline (chunk → embed → store)
│   │   ├── intelligence.py  LLM classification, extraction, summarization
│   │   └── llm.py       LLM client (Gemini Flash Lite)
│   ├── adapters/
│   │   ├── base.py           Base adapter interface
│   │   ├── registry.py       Adapter registry (auto-discovery)
│   │   ├── claude_code.py    Claude Code adapter (~/.claude/projects/)
│   │   ├── gemini_cli.py     Gemini CLI adapter
│   │   ├── chatgpt_import.py ChatGPT JSON import adapter
│   │   ├── aider.py          Aider adapter (.aider.chat.history.md)
│   │   ├── codex_cli.py      Codex CLI adapter
│   │   ├── copilot_cli.py    Copilot CLI adapter
│   │   ├── claude_web_import.py  Claude Web/Desktop import adapter
│   │   └── antigravity.py    Antigravity adapter (Protocol Buffers)
│   ├── graph/
│   │   ├── knowledge.py  NetworkX knowledge graph (entity co-occurrence)
│   │   └── search.py     Graph-enhanced retrieval
│   ├── daemon/
│   │   └── watcher.py   File system watcher (watchdog)
│   └── mcp/
│       └── server.py    MCP server (FastMCP) — 30 tools (see docs/MCP-TOOLS.md)

memgentic-api/               ← REST API package (FastAPI)
├── memgentic_api/
│   ├── main.py          FastAPI app with lifespan
│   ├── deps.py          Dependency injection
│   ├── schemas.py       Request/response Pydantic models
│   └── routes/
│       ├── memories.py  CRUD + search endpoints
│       ├── sources.py   Source stats endpoints
│       ├── stats.py     Analytics endpoints
│       ├── graph.py     Knowledge graph endpoints
│       └── import_export.py  Import/export endpoints

memgentic-native/            ← Rust native acceleration (PyO3, optional)
├── Cargo.toml
├── pyproject.toml       Maturin build config
└── src/
    ├── lib.rs           PyO3 module registration
    ├── textproc/        Credential scrubbing, noise detection, classification
    ├── parsers/         JSONL, ChatGPT JSON, Protobuf, Markdown parsers
    └── graph/           petgraph-based knowledge graph engine

dashboard/               ← Web Dashboard (Next.js 16, React 19, Tailwind v4, shadcn/ui)
docs/                    ← Research & architecture docs

Read the full file on GitHub · 389 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. 9d ago First seen · 389 lines · 5,367 tokens per session scan A abaaa12488cc

Subscribe to this mod's changes

Memgentic CLAUDE.md is an instructions file published in the GitHub repository Chariton-kyp/Memgentic (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 5,367 tokens to every session, about $0.0268 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 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens