What is openmembrane AGENTS.md?

Project instructions for OpenMembrane, a local tool that stores useful knowledge from AI coding sessions.

They are for guiding work on OpenMembrane, including its memory extraction, filtering, storage, exporting, and MCP-server components.

They give coding agents the project’s purpose, architecture, data flow, and monorepo layout; a monorepo is one repository containing multiple related packages or applications.

How mohamadalhusseinie/openmembrane configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to mohamadalhusseinie/openmembrane. 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/mohamadalhusseinie/openmembrane/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/mohamadalhusseinie/openmembrane

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mohamadalhusseinie/openmembrane/agents-md/github.svg)](https://agentmods.dev/instructions/mohamadalhusseinie/openmembrane/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/mohamadalhusseinie/openmembrane/agents-md"><img src="https://agentmods.dev/badge/instructions/mohamadalhusseinie/openmembrane/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mohamadalhusseinie/openmembrane/agents-md"><img src="https://agentmods.dev/badge/instructions/mohamadalhusseinie/openmembrane/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,237 This file is loaded in full into every session.

When invoked 1,237 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.

Model	Per session	Once invoked
Fable 5.1	$0.01237	$0.01237
Opus 5.5	$0.00495	$0.00495
Sonnet 5.5	$0.00247	$0.00247
Haiku 4.5	$0.00124	$0.00124

Measured 18d ago against content hash 307e1bc3fcff, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

openmembrane 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 18d 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 · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project context for AI coding tools working on the OpenMembrane codebase.

Project Overview

OpenMembrane is a local-first, private, tool-agnostic memory membrane for AI coding tools. It autonomously extracts durable project knowledge from session transcripts, filters out secrets and noise, and persists approved memories — without any manual effort from the user.

Deployment Modes

The current release ships Local Private mode as the default and GitHub Team mode for shared memory through a dedicated private repository. Self-Hosted Team and Managed Team are planned. Static exports are distinct from GitHub Team sync; use Deployment Modes as the canonical product and residency reference.

Architecture

Pipeline

session transcript
  -> secret redaction
  -> memory extraction
  -> classification
  -> policy / safety / noise filtering
  -> deduplication
  -> conflict detection
  -> action recommendation (auto_save / ask_user / reject)
  -> memory store or pending candidate queue

Monorepo Structure

packages/core/       — Domain types, extraction interface, pipeline orchestration,
                       classification, policy, deduplication, conflict detection
packages/storage/    — Local JSON persistence (memories, pending candidates, audit, diagnostics)
packages/exporters/  — Static fallback file generation (AGENTS.md, CLAUDE.md, etc.)
packages/shared/     — IDs, time helpers, generic result types
packages/protocol/   — Versioned local-daemon HTTP schemas and shared endpoint resolution
packages/client/     — Authenticated local-daemon client used by CLI and review UI
packages/adapter-*/ — Thin tool adapters (hooks, OpenCode, Claude Code, Codex, VS Code); daemon clients only
apps/mcp-server/     — MCP server (tool registration, validation, error responses)
apps/daemon/         — Per-user HTTP daemon, token authentication, project routing,
                       single-instance locking, and CLI lifecycle
apps/review-ui/      — Loopback review UI proxying project operations to the daemon
tests/               — All test files (unit and integration)

Read the full file on GitHub · 129 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.

18d ago Changed · +1 lines · +28 tokens per session 307e1bc3fcff
23d ago Changed · +6 lines · +120 tokens per session e07aa167970a
1mo ago Changed · +4 lines · +56 tokens per session d4d88be2aaec
1mo ago Changed · +9 lines · +97 tokens per session 19dd50857d02
2mo ago First seen · 109 lines · 936 tokens per session scan A 7c3e54a6c09b

Subscribe to this mod's changes

openmembrane AGENTS.md is an instructions file published in the GitHub repository mohamadalhusseinie/openmembrane (0 stars, last pushed 2d ago), licensed MIT. It adds 1,237 tokens to every session, about $0.0049 per session on Opus 5.5. 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.

openmembrane AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
openmembrane AGENTS.mdmohamadalhusseinie/openmembrane	Instructions file	0	2d ago	MIT	A	1,237	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

openmembrane: Instructions file for Codex