No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by mindmuxai · Codex Skill · ★ 541
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is brain.md safe to install? View the security audit →
brain.md A persistent memory layer for your coding agents. An open, agent-agnostic standard for capturing a project's durable knowledge as plain Markdown — read and written through one small CLI. It lives in your repo and travels across agents, machines, and models. Why · Quick start · See it work · CLI · How it works This repository is the toolkit, not a brain itself. Install it once, then run inside any project: it scaffolds a protocol file and a directory into your repo. From then on, any coding agent — Claude Code, Codex, anything that reads files — learn
| Stars | 541 |
| Forks | 49 |
| Language | JavaScript |
| Category | Codex Skill |
| License | Apache-2.0 |
| Quality Score | 67.8121626508309/100 |
| Last Updated | 2026-09-11 |
| Created | 2026-06-18 |
| Platforms | claude-code, cli, codex, node |
| Est. Tokens | ~11k |
These tools work well together with brain.md for enhanced workflows:
Looking for a brain.md alternative? If you're comparing brain.md with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Project memory for long-running AI work across agents, models, and sessions. Keep context, decisions, progress
Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules
Reusable project context and specialist workflows for the AI tools you already use. Agents, skills, rules and
Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software
The control plane for AI coding agents.
Let Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw C
Explore other popular codex skill tools:
brain.md is A persistent, file-based memory layer for coding agents — give Claude Code, Codex & others a project brain (durable decisions, requirements, constraints) via a zero-dependency CLI.. It is categorized as a Codex Skill with 541 GitHub stars.
brain.md is primarily written in JavaScript. It covers topics such as agent-memory, ai-agents, claude-code.
You can find installation instructions and usage details in the brain.md GitHub repository at github.com/mindmuxai/brain.md. The project has 541 stars and 49 forks, indicating an active community.
brain.md is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to brain.md on Agent Skills Hub include recall-loom, project-butler, aiwg. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: