What is emem AGENTS.md?

Repository instructions for coding agents working on emem, a service that answers questions, finds stored information, and returns signed receipts that can be checked later.

Use them when developing emem or calling its question, location, recall, verification, and agent-integration interfaces.

They explain how to use the service, understand the codebase, and follow its build, testing, debugging, and safety rules.

emem AGENTS.md — Instructions file for Codex and OpenCode by Vortx-AI: Repository instructions for coding agents working on emem, a…

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/vortx-ai/emem/agents-md

Clone the repo

git clone --depth 1 https://github.com/Vortx-AI/emem

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/vortx-ai/emem/agents-md.svg)](https://agentmods.dev/instructions/vortx-ai/emem/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/vortx-ai/emem/agents-md"><img src="https://agentmods.dev/badge/instructions/vortx-ai/emem/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,338 This file is loaded in full into every session.

When invoked 2,338 The same file — it is already loaded in full.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.02338	$0.02338
Opus 5	$0.01169	$0.01169
Sonnet 5	$0.00468	$0.00468
Haiku 4.5	$0.00234	$0.00234

Measured 5d ago against content hash e65331702de3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

emem AGENTS.md scanned grade B with 1 finding 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 5d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo setcap 'cap_net_bind_service=+ep' target/release/emem-server

AGENTS.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is the README for coding agents working on the emem source. Per the agents.md convention (OpenAI Codex, 2025; Linux Foundation AAIF, Dec 2025): build commands, test rules, code style, and what's off-limits during autonomous runs. End users of the protocol should read docs/agents.md and skills.md instead; those describe how to use emem from an agent.

First 5 minutes (using emem as an agent)

If you only want to call emem (not edit its source), here is zero to a signed answer in three calls:

Ask. POST /v1/ask {"question":"what is the NDVI near Mount Fuji?"} (MCP tool emem_ask, or emem_intent / POST /v1/intent for a structured single-shot). The classifier picks the primitive and returns a signed receipt. This is the fastest path.
Or take control. POST /v1/locate {"place":"Mount Fuji"} → a cell64, then POST /v1/recall {"cell":"<cell64>"} (auto-materialises on a miss).
Cite it. Verify the receipt offline at /verify or via POST /v1/verify_receipt; hand other agents an emem:fact: token from emem_memory_token (or emem_memory_bundle for several).

Newer "connect & evolve" surfaces (typed temporal edges, the contradiction-fed refinement loop) are walked end-to-end in examples/connect-and-evolve.md. Full usage guide: docs/agents.md. The rest of this file is for agents editing the source.

Repo shape

Rust workspace, 19 crates, version 2.3.0, MSRV 1.91. emem-guard is the verdict server for AI inference checkpoints (Anthropic Inference hooks, Claude Code hooks); it is a separate binary and shares no code path with the responder. The bulk of the code lives in crates/emem-api-rest/src/lib.rs (~29 k lines: HTTP/MCP router plus every inline materializer plus the foundation-embedding fan-out for /v1/ask) and crates/emem-fetch/src/*.rs (27 data connectors + 7 utility modules). FastAPI sidecar in python/jepa_v2_sidecar/ serves Clay v1.5, Prithvi-EO-2.0, Galileo, and JEPA-v2 over a Unix socket. Web surface in web/ is plain HTML, no build step, included via include_str!.

Read the full file on GitHub · 173 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.

5d ago First seen · 173 lines · 2,338 tokens per session scan B e65331702de3

Subscribe to this mod's changes

emem AGENTS.md is an instructions file published in the GitHub repository Vortx-AI/emem (56 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,338 tokens to every session, about $0.0117 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Memory and context a2a-protocol agent-interoperability agent-memory long-term-memory mcp shared-memory

zenbrain AGENTS.md

AGENTS.md instructions for zensation-ai/zenbrain, covering agent context, mission, project map, non-negotiables and testing.

zensation-ai/zenbrain · 1,133 tokens

Pseudolife-MCP CLAUDE.md

Claude Code instructions for Pseudogiant-xr/Pseudolife-MCP, covering pseudolife-mcp — project conventions, shipping checklist (any change that lands on master), derived state / caches / indexes, running tests (exit-code discipline) and review discipline.

Pseudogiant-xr/Pseudolife-MCP · 4,473 tokens

emem AGENTS.md