# Hybrid Vision

> Hybrid Vision is a local "Visual Memory" server for AI Agents (Claude, Cursor, etc.). It acts as a Semantic Recorder that efficiently captures, indexes, and lets agents query your screen history without sending pixels to the cloud. Think of it as "Open Recall" for your AI assistant - running entirely on your local hardware.

- **Type:** MCP server
- **Install:** `agentstack add mcp-yashasviasthana-hybrid-vision`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [YashasviAsthana](https://agentstack.voostack.com/s/yashasviasthana)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [YashasviAsthana](https://github.com/YashasviAsthana)
- **Source:** https://github.com/YashasviAsthana/hybrid-vision

## Install

```sh
agentstack add mcp-yashasviasthana-hybrid-vision
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Hybrid Vision MCP Server
> **Privacy-First Visual Memory System for MCP Agents**

## Project Mission
**Hybrid Vision** is a local "Visual Memory" server for AI Agents (Claude Desktop, Cursor, etc.). It acts as a **Semantic Recorder** that efficiently captures, indexes, and lets agents query your screen history without sending pixels to the cloud.
Think of it as "Open Recall" for your AI assistant—running entirely on your local hardware.

## Architecture

- **Core Logic**: Rust (Async/Tokio)
- **MCP SDK**: Official `rmcp` crate v0.9
- **Memory System**: In-memory Ring Buffer (metadata only) + SQLite with vector embeddings
- **OCR Engine**: PaddleOCR via ONNX Runtime (DBNet + SVTR)
- **Embeddings**: all-MiniLM-L6-v2 via ONNX Runtime (384-dim vectors)
- **Protocol**: Model Context Protocol (Stdio/JSON-RPC)
- **Parallelization**: `tokio::spawn_blocking` + channels for non-blocking OCR
- **Hardware Target**: Consumer CPU (optimized for multi-core)

## Available Tools

The server exposes the following MCP tools:

| Tool Name | Description | Parameters |
| :--- | :--- | :--- |
| `read_screen` | Returns last captured frame with timestamp & OCR text | None |
| `get_screen_history` | Retrieves screen history from last N minutes | `minutes` (default: 5), `limit` (default: 10) |
| `search_screen_history` | Full-text or semantic search across history | `query`, `limit`, `semantic` (bool) |

***

## Quick Start

See [SETUP.md](SETUP.md) for detailed installation and configuration instructions.

### Prerequisites
- Rust toolchain (1.75+)
- **Linux**: `build-essential libssl-dev pkg-config libx11-dev libxcb1-dev libdbus-1-dev`
- **Windows**: Visual Studio Build Tools with C++ support
- **macOS**: Xcode Command Line Tools

### Build
```sh
cargo build --release
```

### Configure Claude Desktop
Edit `claude_desktop_config.json`:

**Linux/macOS**:
```json
{
  "mcpServers": {
    "hybrid-vision": {
      "command": "/absolute/path/to/hybrid-vision/target/release/hybrid-vision-server",
      "args": []
    }
  }
}
```

**Windows**:
```json
{
  "mcpServers": {
    "hybrid-vision": {
      "command": "C:\\Users\\\\code\\hybrid-vision\\target\\release\\hybrid-vision-server.exe",
      "args": []
    }
  }
}
```

**Example Usage:**
> "I had a compile error 5 minutes ago, what was it?"

Expected response: (Agent searches history and returns the error message)

***

## Technical Design

### Why Stdio Transport?
Standard input/output is the fastest way for local agents (Claude Desktop, Cursor) to communicate with tools. No HTTP overhead, no network stack, just pure IPC.

### Why SQLite?
- Serverless, runs in-process (no separate DB server to manage).
- Native `ORDER BY` support - no workarounds needed.
- Lightweight (~500KB bundled) and battle-tested.
- Easy debugging with any SQLite viewer (DB Browser, DBeaver, etc.).
- Vector embeddings stored as BLOB with cosine similarity in Rust.

### Why Ring Buffer?
- Keeps RAM usage predictable (~1GB limit).
- Avoids filling up the hard drive with video files.

***

## Project Structure

```
hybrid-vision/
├── src/
│   ├── main.rs              # Entry point, rmcp stdio transport
│   ├── server.rs            # MCP server with tool definitions
│   ├── recorder.rs          # Memory-efficient ring buffer
│   ├── screen_recorder.rs   # Parallel capture with spawn_blocking OCR
│   ├── memory.rs            # SQLite with embedding support
│   ├── embedding.rs         # all-MiniLM-L6-v2 text embeddings
│   ├── config.rs            # Unified YAML configuration
│   ├── vision.rs            # Screen capture abstraction
│   └── ocr.rs               # PaddleOCR text extraction
├── config.yml               # User configuration
├── data/
│   ├── memory.db            # SQLite database (gitignored)
│   └── hybrid-vision.log    # Log file (gitignored)
├── Cargo.toml               # Rust dependencies
├── README.md                # This file
└── SETUP.md                 # Installation & configuration guide
```

***

## Testing

### Manual Test
```sh
# Run the server (Linux/macOS)
./target/release/hybrid-vision-server
# Windows: .\target\release\hybrid-vision-server.exe

# Send a JSON-RPC initialize message (paste and press Enter)
{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}
```

### With Claude Desktop
1. Configure as shown in SETUP.md
2. Restart Claude Desktop completely
3. Ask: "What tools do you have available?"
4. Should see `read_screen`, `get_screen_history`, and `search_screen_history` listed
5. Ask: "What was I doing 5 minutes ago?"

***

## License
MIT License. Copyright (c) 2025 Yashasvi Asthana.

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [YashasviAsthana](https://github.com/YashasviAsthana)
- **Source:** [YashasviAsthana/hybrid-vision](https://github.com/YashasviAsthana/hybrid-vision)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-yashasviasthana-hybrid-vision
- Seller: https://agentstack.voostack.com/s/yashasviasthana
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.