O

Openeye

@dumbspacecookie

About Openeye

Persistent memory + visual session tracking + RL trajectory capture for AR/XR/mobile procedure verification. Bring your own vision model (Claude, GPT-4o, Ollama).

#memory #ar #xr #computer-vision #mcp #agent #procedure-verification #ollama #claude #dpo

Basic information

Category

AI & Agents

Transports

stdio

Publisher

dumbspacecookie

Submitted by

dumbspacecookie

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "openeye": {
      "command": "python3",
      "args": [
        "sidecar/mcp_server.py"
      ],
      "env": {
        "ANTHROPIC_API_KEY": "sk-ant-..."
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Openeye?

Openeye provides persistent memory, visual session tracking, and reinforcement learning trajectory capture for procedure verification in AR, XR, and mobile environments. It allows users to bring their own vision model, such as Claude, GPT-4o, or Ollama.

How to use Openeye?

—

Key features of Openeye

Persistent memory for sessions.
Visual session tracking.
RL trajectory capture.
Supports Claude, GPT-4o, Ollama.
Designed for AR/XR/mobile verification.

Use cases of Openeye

Procedure verification in AR, XR, or mobile environments.

FAQ from Openeye

What vision models does Openeye support?

Openeye supports Claude, GPT-4o, and Ollama.

What environments is Openeye designed for?

Openeye is designed for AR, XR, and mobile procedure verification.

Does Openeye include persistent memory?

Yes, Openeye includes persistent memory for sessions.

Comments

More AI & Agents MCP servers

LinkedIn MCP Server

Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, and messages.

meGPT - upload an author's content into an LLM

Code to process many kinds of content by an author into an MCP server

Open Multi-Agent Canvas

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

Mcp Agent

Build effective agents using Model Context Protocol and simple workflow patterns

MCP-LLM Bridge

Bridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools