Knowledge3D

danielcamposramos/Knowledge3D

Web knowledge is fragmented — duplicated across fonts, embeddings, metadata, and renderings. Humans see pixels, AI sees tokens, neither shares the source. Knowledge3D: a sovereign GPU-native reference implementation for W3C PM-KR, where humans and AI consume the same procedural knowledge from one source.

34 stars

5 forks

Python

128 views

View on GitHub Add to Favorites

Installation

Option 1: Use slash command in Claude Code

/install-skill https://github.com/danielcamposramos/Knowledge3D

Option 2: Clone to skills directory

# Global (all projects)

git clone https://github.com/danielcamposramos/Knowledge3D ~/.claude/skills/Knowledge3D

# Project-specific

git clone https://github.com/danielcamposramos/Knowledge3D .claude/skills/Knowledge3D

Add MCP server to .cursor/mcp.json:

{
  "mcpServers": {
    "skillz": {
      "command": "npx",
      "args": ["-y", "skillz-mcp", "https://github.com/danielcamposramos/Knowledge3D"]
    }
  }
}

Restart Cursor after adding the configuration.

Option 1: Use Gemini CLI command

gemini extensions install https://github.com/danielcamposramos/Knowledge3D

Option 2: Clone to extensions directory

git clone https://github.com/danielcamposramos/Knowledge3D ~/.gemini/extensions/Knowledge3D

Topics

3d-knowledge-graph boundary-framework gltf gpu-native k3d knowledge-representation neurosymbolic-ai neurosymbolic-integration pm-kr procedural-compression procedural-knowledge ptx rpn rpn-engine sovereign-ai spatial-knowledge spatial-ui three-brain-system threejs w3c-community