Borrowing it
Nothing to install: this file belongs to Vortx-AI/emem. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Vortx-AI/emem/main/AGENTS.mdgit clone --depth 1 https://github.com/Vortx-AI/ememWrote 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.
[](https://agentmods.dev/instructions/vortx-ai/emem/agents-md)<a href="https://agentmods.dev/instructions/vortx-ai/emem/agents-md"><img src="https://agentmods.dev/badge/instructions/vortx-ai/emem/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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 | $0.02595 | $0.02595 |
| Opus 5.5 | $0.01038 | $0.01038 |
| Sonnet 5.5 | $0.00519 | $0.00519 |
| Haiku 4.5 | $0.00260 | $0.00260 |
Grade A, and why
emem 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 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.
How it starts
The opening of the file, as written. The whole thing — 189 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 toolemem_ask, oremem_intent/POST /v1/intentfor a structured single-shot). The classifier routes the question to one of four paths: a self-description of emem, a corpus audit (a redirect to the coverage endpoints, with no receipt), a hunter sweep over a region, or a point answer. The hunter sweep and the point answer carry a signed receipt. Ask answers point questions with a current value, so send a change question ("how has X changed") toemem_intentwithdid_change, or toemem_diff. This is the fastest path. - Or take control.
POST /v1/locate {"place":"Mount Fuji"}→ acell64, thenPOST /v1/recall {"cell":"<cell64>"}(auto-materialises on a miss). - Cite it. Verify the receipt offline at
/verifyor viaPOST /v1/verify_receipt; hand other agents anemem:fact:token fromemem_memory_token(oremem_memory_bundlefor 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 2.4.4, 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 (HTTP/MCP router plus every inline materializer) and
crates/emem-fetch/src/*.rs (27 data connectors + 8 utility modules).
Earlier versions ran Clay, Prithvi, Galileo and JEPA-v2 on a GPU sidecar;
facts they signed still verify. Web surface in web/ is plain HTML, no build step, included via
include_str!.
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.
- 4d ago Changed b230b794155c
- 6d ago Changed · +14 lines · +208 tokens per session scan B → A 22bc23fa26b7
- 12d ago Changed 6aaa4eb8a128
- 13d ago Changed 5359f8e953a7
- 23d ago Changed · +5 lines · +94 tokens per session c9463442c989
- 24d ago Changed bddf2ff26150
- 28d ago Changed · -3 lines · -62 tokens per session f7b9064f81d1
- 29d ago Changed 31566b5a1c11
- 1mo ago Changed · +17 tokens per session 9c7f249e9f2d
- 1mo ago First seen · 173 lines · 2,338 tokens per session scan B c1de2dcd81ce
emem AGENTS.md is an instructions file published in the GitHub repository Vortx-AI/emem (72 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,595 tokens to every session, about $0.0104 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 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.