Moorcheh Agent Skills
Agent Skills for building AI applications with Moorcheh- the Universal Memory Layer for Agentic AI.
Documentation ·
Console ·
Python SDK ·
Agent Skills Spec
Each skill is a folder containing instructions, scripts, and resources that agents like Claude Code, Cursor, GitHub Copilot, Codex, Windsurf, Antigravity, and others can discover to work more accurately and efficiently with Moorcheh.
Works with any agent that supports the Agent Skills format.
Installation
Using npx skills (Cursor, Claude Code, Gemini CLI, Codex, etc.)
npx skills add moorcheh-ai/agent-skills
Using Claude Code Plugin Manager
# Step 1- Add the marketplace (one time only)
/plugin marketplace add moorcheh-ai/agent-skills
# Step 2- Install the plugin
/plugin install moorcheh
Manual: clone and point your agent to the directory
git clone https://github.com/moorcheh-ai/agent-skills.git
cd agent-skills
claude --plugin-dir .
Quickstart
New to Moorcheh? Run the interactive onboarding to set up your environment variables, import sample data, and explore the full functionality:
/moorcheh:quickstart
Configuration
Moorcheh Account
Create a free account at console.moorcheh.ai.
Required Environment Variables
export MOORCHEH_API_KEY="your-api-key"
Available Skills
Moorcheh
Core operations for interacting with the Moorcheh platform:
- Namespace Management- Create, list, and delete namespaces
- Data Operations- Upload text documents and vector embeddings
- Semantic Search- Search with ITS scoring, metadata filters, and relevance labels
- AI Generation- Generate RAG-powered answers with structured output
Cookbooks
Blueprints for complete AI applications powered by Moorcheh:
- Knowledge Base RAG- Document Q&A with source citations
- Customer Support Bot- Conversational chatbot with chat history
- Semantic Search App- Search with ITS scoring and filtering
- AI Q&A System- Structured Q&A with multi-namespace routing
- Frontend Interface- Next.js frontend (optional)
- LangChain Integration- Use Moorcheh as a LangChain vector store
- LLM Wiki- Self-maintaining personal knowledge base (Karpathy pattern + Moorcheh ITS)
- Deep Ingest- Ingest large documents (>200K chars) or binary files (PDF, DOCX, XLSX) without local extraction- Moorcheh handles parsing, chunking, and indexing automatically
Usage
Commands (Claude Code Plugin)
# Interactive onboarding
/moorcheh:quickstart
# Semantic search across namespaces
/moorcheh:search query "machine learning" namespaces "my-documents"
# Search with metadata filters
/moorcheh:search query "best practices #category:tech" namespaces "articles" top_k 5
# Generate AI-powered RAG answers
/moorcheh:answer query "What are the key features?" namespace "product-docs"
# List all namespaces
/moorcheh:namespaces
# Upload data to a namespace
/moorcheh:upload namespace "my-documents" file "data.json"
# Explore data in a namespace
/moorcheh:explore namespace "my-documents"
Skills (Any Compatible Agent)
The skill is automatically discovered by compatible agents. Simply describe what you want:
- "Search my Moorcheh namespace for information about vector databases"
- "List all my Moorcheh namespaces"
- "Upload these documents to Moorcheh for semantic search"
- "Build a knowledge base chatbot using Moorcheh"
- "Generate an AI answer from my documentation"
- "Build a customer support bot with Moorcheh"
- "Build an LLM Wiki knowledge base with Moorcheh"
- "Set up a self-maintaining wiki using Karpathy's pattern"
- "Ingest a large PDF into my wiki using deep ingest"
Requirements
- Python 3.10+
- uv (recommended) or pip
- A Moorcheh account
Resources
