iGenius Memory — Persistent AI Memory for Any Agent

A structured, AI-powered memory backend that gives any MCP-compatible agent persistent memory via the iGenius Memory service. All AI processing happens server-side — you just need an API key.

3 Ways to Use iGenius

Get a free API key at igenius-memory.online — all three clients use the same key.

1. VS Code Extension (Marketplace)

Install directly from the VS Code Marketplace — no pip, no config files:

ext install igenius-memory.igenius-memory

Or search "iGenius Memory" in the Extensions panel. Includes sidebar UI, memory browser, status bar indicator, AI provider settings, and auto-warms briefings on a configurable interval.

2. MCP Server (pip)

For any MCP-compatible client (VS Code Copilot, Claude Desktop, Cursor, Windsurf, etc.):

pip install igenius-mcp

Then add to your MCP config:

VS Code — ~/.vscode/mcp.json:

{
  "servers": {
    "igenius-memory": {
      "command": "igenius-mcp",
      "env": { "IGENIUS_API_KEY": "ig_your_key_here" },
      "type": "stdio"
    }
  }
}

Claude Desktop / Cursor / Windsurf — add to your MCP config file:

{
  "mcpServers": {
    "igenius-memory": {
      "command": "python",
      "args": ["-m", "igenius_mcp.server"],
      "env": { "IGENIUS_API_KEY": "ig_your_key_here" }
    }
  }
}

⚠️ Windows users: If VS Code can't find igenius-mcp, use python -m igenius_mcp.server instead.

3. Desktop App (Windows)

Standalone system-tray application — works alongside any editor or IDE:

• Download Installer (NSIS setup or MSI)

• Built with Tauri + Rust — lightweight, native, ~5 MB

• System tray with quick access to briefings, search, and memory stats

• Configure LLM provider (LM Studio, OpenAI, Anthropic, Google) from the UI

Restart VS Code after installing the extension or adding MCP config — all 17 memory tools become available to Copilot and any MCP-compatible agent.

Related MCP server: aimemory

Available Tools

LLM Requirements

iGenius uses an LLM backend for AI extraction, consolidation, and (optionally) visual analysis. You can use a local or remote LLM provider.

Local Setup (LM Studio, Ollama, etc.)

⚠️ IMPORTANT: Do NOT use thinking/reasoning models (e.g. QwQ, DeepSeek R1, o1, o3). Thinking models emit <think> chains before the actual response, which breaks iGenius's structured JSON extraction pipeline. Only use standard non-thinking (instruct/chat) models.

Why these specs? iGenius sends structured extraction prompts that expect clean JSON output. A 4B-parameter non-thinking model at 3k context is the sweet spot for fast, accurate extraction without hallucination or timeouts. Larger models (8B+) work too — just ensure you have the VRAM headroom and that the model is a non-thinking variant.

Remote Setup (OpenAI, Anthropic, Google, etc.)

No local hardware requirements. Any API-accessible model works — configure the provider, model name, and API key in the VS Code extension settings or environment variables.

Environment Variables

Visual Tools (Optional)

Give your AI agent eyes — render any URL, take a pixel-perfect screenshot, and get instant UI/UX analysis from a local vision model.

Install

pip install "igenius-mcp[visual]"
python -m playwright install chromium

Then load a vision-capable model in LM Studio (e.g. Qwen 3.5 9B Vision, non-thinking).

⚠️ Do NOT use thinking/reasoning vision models — same restriction as above.

Visual MCP Tools

Visual Environment Variables

100% local — screenshots and analysis never leave your machine.

Agent Instructions

For best results, add the iGenius agent instructions to your workspace:

• VS Code: Place igenius.instructions.md in ~/.vscode/prompts/

• Claude Code: Add to CLAUDE.md

• Workspace: Add to .github/copilot-instructions.md

Get the template at igenius-memory.info

How It Works

Agent ←→ MCP (stdio) ←→ igenius-mcp ←→ REST API ←→ iGenius Backend

The memory tools are a thin proxy — they translate MCP tool calls into REST API requests. All AI extraction, LLM summarization, and encryption happens server-side.

The visual tools run locally — Playwright renders URLs on your machine and a local vision model (e.g. LM Studio + Qwen2.5-VL) analyzes the screenshots. Screenshots and analysis never leave your machine.

Plans

Details at igenius-memory.store

Coming Soon

iGenius Context Engine — unlimited effective context for local LLMs through intelligent recursive summarization. Run a 3B model with a 4K context window and handle conversations of any length.

Links

• Landing Page

• Documentation

• API Portal & Free Key

• Store & Plans

• VS Code Extension

• Desktop App

Support the Project

iGenius Memory is built and maintained by NovaMind Labs. If you find it useful, here's how you can help:

• Star the repo — it helps more developers discover iGenius

• Upgrade to Pro — $19/mo directly funds development → igenius-memory.store

• Report bugs & ideas — open an issue

• Spread the word — tell your friends, tweet about it, write a blog post

Every user, star, and subscription helps keep iGenius alive and improving. Thank you!

License

MIT