agent-catalog (Couchbase Agent Catalog)

The mono-repo for the Couchbase Agent Catalog project.

Table of Contents

• Getting Started
  • Installing from Package
  • Installing from Source (with Makefile)
  • Installing from Source (with Anaconda)
• Docs and Templates

Getting Started

Installing from PyPI

Note: this section is in the works! We recommend installing from our pre-built packages in the meantime.

1. Make sure you have python3.11 installed!

2. Use pip to install the agentc package.

      pip install agentc

   If you are interested in developing with LangChain or LangGraph, install the helper agentc_langchain package and/or agentc_langgraph packages as extras:

   pip install agentc[langchain,langgraph]

   Similarly, for LlamaIndex Developers:

   pip install agentc[llamaindex]

Installing from Package

1. Make sure you have python3.11 installed!

2. Navigate to the releases page for Agent Catalog here and choose the latest version. Expand the "Assets" tab and download all *.whl files (e.g., agentc-0.2.0+g59944db-py3-none-any.whl) into your project location.

3. Install the agentc package using the .whl file and pip:

   pip install agentc_core-*.whl
   pip install agentc_cli-*.whl
   pip install agentc-*.whl

   Note that order matters here!

4. If you are interested in developing with LangChain or LangGraph, install the helper agentc_langchain and/or agentc_langgraph packages with the commands below:

   pip install agentc_langchain-*.whl
   pip install agentc_langgraph-*.whl

   Similarly, for LlamaIndex Developers:

   pip install agentc_llamaindex-*.whl

Installing from Source (with Makefile)

1. Make sure you have python3.11 and poetry installed!

2. Make sure you have make installed! For Mac-based installations, see here. For Windows-based installations, see here. For Ubuntu-based installations, see here.

3. Clone this repository.

   git clone https://github.com/couchbaselabs/agent-catalog

4. Navigate to the agent-catalog directory and run make. This will a) create a new virtual environment using Poetry and b) install all required packages and CLI tools.

5. Activate your newly created virtual environment using the outputs of make activate or poetry env activate. If you do not want to copy-and-paste the output, you can run the command with eval:

   eval $(poetry env activate)

   If your environment has been successfully activated, you should see (Activated) after running poetry env list...

   poetry env list
   > agent-catalog-UEfqTvAT-py3.13 (Activated)

   ...and you should see that your python now points to the python in your virtual environment (not your system default).

   which python
   > /Users/....../Library/Caches/pypoetry/virtualenvs/agent-catalog-UEfqTvAT-py3.13/bin/python

6. If you are interested in building a .whl file (for later use in .whl-based installation in other projects), run the following command:

   scripts/pre-build.sh
   scripts/build.sh
   scripts/post-build.sh

   Your .whl files will end up in the dist folder.

Installing from Source (with Anaconda)

1. Make sure you have python3.11 and conda installed!

2. Create a new virtual environment with Anaconda and subsequently activate your environment. Again, you must activate your environment before running any agentc commands!

   conda create -n my_agentc_env python=3.11
   conda activate my_agentc_env

3. Navigate to this directory and install Agent Catalog with pip:

   cd agent-catalog
   
   # Install the agentc package.
   pip install libs/agentc

   If you are interested in developing with LangChain or LangGraph, install the helper agentc_langchain and/or agentc_langgraph packages with the command below:

   pip install libs/agentc_integrations/langchain
   pip install libs/agentc_integrations/langgraph

   Similarly, for LlamaIndex Developers:

   pip install libs/agentc_integrations/llamaindex

Docs and Templates

Refer to docs/ to build our technical documentation (also hosted here) and explore Couchbase Agent Catalog before authoring your agent applications. For more information about the Agent Catalog and other AI Data Plane services, see the documentation here.