What is zenbrain AGENTS.md?

A project instruction file for ZenBrain, a zero-dependency memory system for AI agents that models how memories are learned, recalled, and forgotten.

Working on ZenBrain's memory algorithms, seven-layer coordinator, or its TypeScript packages.

It explains the repository structure and rules so changes preserve the system's algorithms, package boundaries, and scientific correctness.

How zensation-ai/zenbrain configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to zensation-ai/zenbrain. 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/zensation-ai/zenbrain/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/zensation-ai/zenbrain

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/zensation-ai/zenbrain/agents-md/github.svg)](https://agentmods.dev/instructions/zensation-ai/zenbrain/agents-md)

Your own site

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

Per session 1,300 This file is loaded in full into every session.

When invoked 1,300 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	$0.01300	$0.01300
Opus 5.5	$0.00520	$0.00520
Sonnet 5.5	$0.00260	$0.00260
Haiku 4.5	$0.00130	$0.00130

Measured 20d ago against content hash a0823185d484, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zenbrain 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 20d 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 · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Context

This file gives coding agents (Claude Code, Cursor, Copilot, Aider, etc.) the context needed to make correct, style-consistent changes to this repository. Humans: see CONTRIBUTING.md for the full guide.

Mission

ZenBrain is a neuroscience-inspired, zero-dependency memory system for AI agents: spaced repetition (FSRS), Hebbian learning, Ebbinghaus forgetting curves, emotional tagging, sleep consolidation, and Bayesian confidence propagation, organized into a 7-layer memory architecture. The open-source package ships 20 algorithm modules (10 core + 10 advanced) plus a MemoryCoordinator that creates all seven layers and works on five of them. Correctness and scientific defensibility come before cleverness or performance.

Project map

packages/
  algorithms/        @zensation/algorithms — pure algorithm functions, ZERO runtime
                      dependencies. Every module is also a tree-shakeable subpath
                      export (e.g. @zensation/algorithms/fsrs). This package must
                      stay dependency-free — do not add a runtime dependency here.
  core/               @zensation/core — MemoryCoordinator, the 7 memory layers,
                      pluggable storage/embedding/LLM-provider interfaces. Depends
                      on @zensation/algorithms.
  adapters/postgres/  @zensation/adapter-postgres — PostgreSQL + pgvector storage.
  adapters/sqlite/    @zensation/adapter-sqlite — zero-config SQLite storage.
  mcp/                @zensation/mcp — MCP server (five tools) over core + adapter-sqlite.
  ai-sdk/             @zensation/ai-sdk — Vercel AI SDK middleware over core, no runtime deps.
backend/              Ablation runner for the paper's mechanism tables; CI checks its
                      point estimates against backend/results.
apps/playground/      Interactive browser demo (also deployed as the HF Space and
                      zensation.ai/playground).
examples/              Runnable integration examples (plain chatbot, Claude, CrewAI,
                      LangChain, LlamaIndex, Mastra, Vercel AI SDK).
docs/                  architecture.md, api-reference.md, benchmarks.md, FAQ.md,
                      ROADMAP.md, getting-started.md, recipes.md.
scripts/               CI checks (zero dependencies, package contents, MCP smoke test) and
                      compare-mechanisms.sh, the mechanism comparison you run by hand.

Read the full file on GitHub · 104 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.

20d ago Changed · +7 lines · +167 tokens per session a0823185d484
2mo ago First seen · 97 lines · 1,133 tokens per session scan A 5bfa94f77c0f

Subscribe to this mod's changes

zenbrain AGENTS.md is an instructions file published in the GitHub repository zensation-ai/zenbrain (27 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,300 tokens to every session, about $0.0052 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.

Memory and context agent-memory fsrs hebbian-learning long-term-memory neuroscience spaced-repetition

zenbrain AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
zenbrain AGENTS.mdzensation-ai/zenbrain	Instructions file	27	yesterday	Apache-2.0	A	1,300	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

zenbrain: Instructions file for Codex