Couchbase Agent Catalog Project

Welcome to the Couchbase Agent Catalog (agentc) project! The purpose of the agentc project is to make building reliable agents more accessible. For more information about the Agent Catalog and other AI Data Plane services, see the documentation here.

Table of Contents

Getting Started

• Installation
  • Installing from PyPI
  • Installing from Pre-Built Package
  • Installing from Source (with Makefile)
  • Installing from Source (with Anaconda)
• Concepts
  • Metrics Driven Development
  • Couchbase-Backed Agent Catalogs
  • Assessing Agent Quality
• Tutorial
  • Introduction
  • Step #0: Defining a Smart Travel Application
  • Step #1: Building Agent Tools and Prompts
  • Step #2: Building Agents with LangGraph
  • Step #3: Iteratively Improving our Agent

API Reference

• agentc CLI Tool
  • add Command
  • clean Command
  • env Command
  • execute Command
  • find Command
  • index Command
  • init Command
  • ls Command
  • publish Command
  • status Command
• Package Reference
  • agentc Package
  • Integration Packages
• Tool / Prompt Records
  • Tool Catalog Records
  • Prompt Records
• Spans and Log Records
  • Schema of Logs
  • Content in Logs
• Log Analysis
  • logs Collection
  • Views Over logs
• Configuration
  • Config
  • RemoteCatalogConfig
  • LocalCatalogConfig
  • EmbeddingModelConfig
  • ToolRuntimeConfig
  • CommandLineConfig
  • VersioningConfig

Help / Questions

• FAQs
  • Couchbase & Capella Questions
  • Logging Questions
  • Git Versioning Questions
  • Installation Questions

Indices and Tables

• Index