claude-brain

Name: claude-brain
Author: memvid

Warning

Give Claude Code photographic memory in ONE portable file. No database, no SQLite, no ChromaDB - just a single .mv2 file you can git commit, scp, or share. Native Rust core with sub-ms operations.

496stars

48forks

TypeScript

Added 1/8/2026

View on GitHub Download ZIP

AI Agentsai-toolsanthropicclaudeclaude-agentsclaude-ai

Installation

# Add to your Claude Code skills
git clone https://github.com/memvid/claude-brain

Getting Started

Guides for using ai agents skills like claude-brain.

Security ReportWarning

Last scanned: 5/16/2026

{
  "issues": [
    {
      "type": "npm-audit",
      "message": "ajv: ajv has ReDoS when using `$data` option",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "brace-expansion: brace-expansion: Zero-step sequence causes process hang and memory exhaustion",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "flatted: flatted vulnerable to unbounded recursion DoS in parse() revive phase",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "langsmith: LangSmith Client SDK Affected by Server-Side Request Forgery via Tracing Header Injection",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "lodash: Lodash has Prototype Pollution Vulnerability in `_.unset` and `_.omit` functions",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "minimatch: minimatch has a ReDoS via repeated wildcards with non-matching literal in pattern",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "picomatch: Picomatch: Method Injection in POSIX Character Classes causes incorrect Glob Matching",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "postcss: PostCSS has XSS via Unescaped </style> in its CSS Stringify Output",
      "severity": "medium"
    },
    {
      "type": "npm-audit",
      "message": "rollup: Rollup 4 has Arbitrary File Write via Path Traversal",
      "severity": "high"
    },
    {
      "type": "npm-audit",
      "message": "vite: Vite Vulnerable to Path Traversal in Optimized Deps `.map` Handling",
      "severity": "high"
    }
  ],
  "status": "WARNING",
  "scannedAt": "2026-05-16T06:22:58.269Z",
  "semgrepRan": false,
  "npmAuditRan": true,
  "pipAuditRan": true
}

README.md

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

ECC

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

192,952

web-agent-protocol codexUI

Give Claude Code photographic memory.

https://github.com/user-attachments/assets/b57cb3db-576b-4c1f-af92-95796ba3fb5b

Install in 30 seconds · How it Works · Commands · Full Demo

The Problem

You: "Remember that auth bug we fixed?"
Claude: "I don't have memory of previous conversations."
You: "We spent 3 hours on it yesterday"
Claude: "I'd be happy to help debug from scratch!"

200K context window. Zero memory between sessions.

You're paying for a goldfish with a PhD.

The Fix

You: "What did we decide about auth?"
Claude: "We chose JWT over sessions for your microservices.
        The refresh token issue - here's exactly what we fixed..."

One file. Claude remembers everything.

Installation

# One-time setup (if you haven't used GitHub plugins before)
git config --global url."https://github.com/".insteadOf "git@github.com:"

# In Claude Code
/plugin add marketplace memvid/claude-brain

Then: /plugins → Installed → mind Enable Plugin → Restart.

Done.

How it Works

After install, Claude's memory lives in one file:

your-project/
└── .claude/
    └── mind.mv2   # Claude's brain. That's it.

No database. No cloud. No API keys.

What gets captured:

Session context, decisions, bugs, solutions
Auto-injected at session start
Searchable anytime

Why one file?

git commit → version control Claude's brain
scp → transfer anywhere
Send to teammate → instant onboarding

Commands

In Claude Code:

/mind stats                       # memory statistics
/mind search "authentication"     # find past context
/mind ask "why did we choose X?"  # ask your memory
/mind recent                      # what happened lately

Or just ask naturally: "mind stats", "search my memory for auth bugs", etc.

CLI (Optional)

For power users who want direct access to their memory file:

npm install -g memvid-cli

memvid stats .claude/mind.mv2           # view memory stats
memvid find .claude/mind.mv2 "auth"     # search memories
memvid ask .claude/mind.mv2 "why JWT?"  # ask questions
memvid timeline .claude/mind.mv2        # view timeline

Full CLI reference →

FAQ

Empty: ~70KB. Grows ~1KB per memory. A year of use stays under 5MB.

100% local. Nothing leaves your machine. Ever.

Sub-millisecond. Native Rust core. Searches 10K+ memories in <1ms.

rm .claude/mind.mv2

Built on memvid - the single-file memory engine

If this saved you time, star the repo

Send me your .mv2 file and I'll tell you what's wrong with your code. No context needed - I already know everything.