whynowlab/jarvis-orb

Overview

A free, open-source MCP server that visualizes Claude Code reasoning in a 3D orb. It streams the model's internal thought process in real time, giving developers a spatial view of how the AI arrives at its outputs.

Best for

Best for
Developers using Claude Code who want to see and understand its reasoning process in real time.

Use cases

• Debugging Claude Code's reasoning chain during code generation
• Monitoring AI decision-making in real time for transparency
• Understanding model thought patterns to improve prompt design

How to use

Install

curl -fsSL https://raw.githubusercontent.com/thestack-ai/jarvis-orb/main/install.sh | bash

Tools exposed

• memory_save
• memory_search
• memory_verify
• entity_create
• entity_update
• entity_query
• entity_relate

Tested with

Claude Code, Cursor, Windsurf

Example client config

{\n  "mcpServers": {\n    "jarvis-brain": {\n      "command": "python3",\n      "args": ["-m", "jarvis_brain.mcp_server"],\n      "env": {\n        "PYTHONPATH": "~/.jarvis-orb/lib:~/.jarvis-orb"\n      }\n    }\n  }\n}

Notes

A free, open-source MCP server that visualizes Claude Code reasoning in a 3D orb. It streams the model’s internal thought process in real time, giving developers a spatial view of how the AI arrives at its outputs.

6 stars on GitHub. Last updated 2026-04-28. Licensed MIT.

Use cases

• Debugging Claude Code’s reasoning chain during code generation
• Monitoring AI decision-making in real time for transparency
• Understanding model thought patterns to improve prompt design

Pros

• Open-source and free with no usage limits
• Provides real-time visual insight into AI reasoning
• Lightweight MCP server that integrates easily with Claude Code

Cons

• Very early stage with only 6 GitHub stars and minimal community
• Limited to Claude Code and requires an MCP server setup
• Visualization may not scale well for complex or long reasoning chains

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.