CartoGopher for Openclaw

An AI-native code intelligence tool that provides 30+ MCP tools for navigating and understanding codebases with massive token efficiency.

jakenesler
v1.0.1
Feb 21, 2026
0
0
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install cartogopher

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install cartogopher using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is CartoGopher?

CartoGopher is a high-performance code intelligence layer designed to empower AI agents with deep codebase awareness. By parsing your project into a compact graph (bake.json), it allows agents to perform complex operations like symbol lookup, API tracing, and architecture mapping using 94% fewer tokens than traditional file reading methods. This makes it an essential addition to your collection of Openclaw Skills, enabling more accurate and cost-effective AI-assisted development.

The tool bridges the gap between raw text files and structural understanding, offering AST-aware search and specific analysis for modern frontend frameworks like React and Vue. Whether you are using Cursor, Claude Code, or other AI-native environments, CartoGopher provides the structural context needed for high-fidelity code generation and refactoring.

CartoGopher Use Cases

  • Setting up a robust intelligence layer for project-wide code understanding.
  • Tracing full-stack API flows from frontend components down to the database.
  • Mapping complex project architectures to identify the best placement for new features.
  • Reducing LLM token costs when analyzing large repositories through graph-based lookups.

How CartoGopher Works

  1. The user requests a 7-day trial API key using their email address via the CartoGopher API.
  2. The system verifies the key and downloads the platform-specific binary and MCP server bundle.
  3. CartoGopher installs dependencies and configures the CARTOGOPHER_API_KEY within the user's shell profile.
  4. The MCP server is registered with the host AI tool (such as OpenClaw, Cursor, or Claude Code).
  5. The tool parses the codebase into a bake.json file to expose over 30 specialized tools for the AI agent.

CartoGopher Setup

To begin using this tool within your Openclaw Skills workflow, request a trial key:

curl -s -X POST https://cartogopher.com/api/agent-trial -H 'Content-Type: application/json' -d '{"email":"YOUR_EMAIL"}'

Download and install the MCP server based on your platform (e.g., macOS Apple Silicon):

curl -sL https://cartogopher.com/downloads/cartogopher/v4/mac/arm64 -o cg.zip && unzip cg.zip -d ~/.cartogopher/mcp-server && rm cg.zip
cd ~/.cartogopher/mcp-server && npm install

Finally, add the API key to your shell profile:

echo "export CARTOGOPHER_API_KEY=your_key_here" >> ~/.zshrc
source ~/.zshrc

CartoGopher Data Schema & Taxonomy

CartoGopher organizes its intelligence through the following structure:

Component Description
bake.json A compact graph representation of the codebase used for fast context retrieval.
~/.cartogopher/ Local directory containing the MCP server binaries and configuration.
CARTOGOPHER_API_KEY Environment variable required for authenticating with the code intelligence API.
CURSOR_WORKSPACE Environment variable defining the root path for project analysis.

CartoGopher Advanced Features

  • AST-aware semantic search that goes beyond simple text matching.
  • Deep frontend analysis for Vue and React, including hooks, props, and store usage.
  • Automated machine-id generation for consistent licensing in Docker and containerized environments.
  • Cross-platform support for Linux and macOS (Intel and Apple Silicon).
  • Integration with major AI coding tools via the Model Context Protocol (MCP).

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*