hebb-mind AGENTS.md

A project instruction file named AGENTS.md for the Hebb Mind project, an open-source framework researching memory for AI agents. It describes project priorities, directory layout and the current research and implementation phase.

In plain words
What is it for?
Use it to guide work on academic surveys, open-source memory analysis, architecture design and implementation across the project's documentation and research folders.
Why use it?
It gives coding agents shared context and rules when working in the repository.

Instructions file for CodexOpenCode

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/afx-team/hebb-mind/agents-md
Clone the repo
git clone --depth 1 https://github.com/afx-team/hebb-mind

Made for: Codex, OpenCode.

Per session 1,472 This file is loaded in full into every session.
When invoked 1,472 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 $0.01472 $0.01472
Opus 5 $0.00736 $0.00736
Sonnet 5 $0.00294 $0.00294
Haiku 4.5 $0.00147 $0.00147

Measured 3d ago against content hash 17fc788c74c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hebb-mind 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 3d 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 · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hebb Mind

Agent memory framework — open-source project under github.com/afx-team.


Priority Hierarchy

When rules conflict, follow this priority order:

  1. MUST — Non-negotiable constraints (违反则输出无效)
  2. SHOULD — Strong recommendations (默认遵守,可明确说明理由后偏离)
  3. MAY — Optional suggestions (视具体情况采用)

Project Context

Type: Research & design phase → Production implementation Domain: Agent memory for LLMs (inspired by hippocampus = memory consolidation center) Organization: github.com/afx-team

Current Phase Focus

  • Survey academic papers on agent memory
  • Analyze open-source memory implementations
  • Design Hebb Mind architecture
  • Implement core components

Directory Architecture

hebb-mind/
├── repo_pages/           # VuePress site → GitHub Pages (PUBLIC-FACING)
│   ├── .vuepress/        # VuePress configuration
│   └── *.md              # Public documentation pages
├── reports/              # Internal research outputs (NOT for publication)
│   ├── papers/           # Academic paper notes and summaries
│   ├── analysis/         # Open-source project analysis reports
│   ├── design/           # Architecture and design documents
│   └── surveys/          # Research survey reports
├── src/                  # Source code (TBD)
├── eval/                 # Benchmark evaluations on open datasets
└── results/              # Evaluation outputs

CRITICAL DISTINCTION:

  • repo_pages/ = Public website (VuePress → GitHub Pages) — curated documentation for users
  • reports/ = Internal research — raw notes, analysis, design drafts (not for publication)

File Placement Rules:

Content Type Location Visibility
User documentation repo_pages/ Public (GitHub Pages)
Paper summaries reports/papers/ Internal
Project analysis reports/analysis/ Internal
Architecture design reports/design/ Internal
Research surveys reports/surveys/ Internal

Read the full file on GitHub · 184 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. 3d ago First seen · 184 lines · 1,472 tokens per session scan A 17fc788c74c5

Subscribe to this mod's changes

hebb-mind AGENTS.md is an instructions file published in the GitHub repository afx-team/hebb-mind (50 stars, last pushed 1mo ago), licensed MIT. It adds 1,472 tokens to every session, about $0.0074 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.