Installation

Building From Package

Important

This part is in-the-works! For now, please refer to the Installing from Source (with Makefile) section below.

Installing from Source (with Makefile)

  1. Make sure you have python3.12 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)
    

    Note

    Note that you must activate your environment before running any agentc commands!

    If your environment has been activated properly, you should see the following output:

    $ agentc
    Usage: agentc [OPTIONS] COMMAND [ARGS]...
    
      The Couchbase Agent Catalog command line tool.
    
    Options:
      -v, --verbose  Flag to enable verbose output.  [default: 0; 0<=x<=2]
      -i, --interactive / -ni, --no-interactive
                     Flag to enable interactive mode.  [default: i]
      -h, --help     Show this message and exit.
    
    Commands:
      add      Interactively create a new tool or prompt and save it to the...
      clean    Delete all or specific (catalog and/or activity) Agent Catalog...
      env      Return all Agent Catalog related environment and configuration...
      execute  Search for and subsequently execute a specific tool.
      find     Find items from the catalog based on a natural language string...
      index    Walk the source directory trees (sources) to index source files...
      init     Initialize the necessary files/collections for your working Agent...
      ls       List all indexed tools and/or prompts in the catalog.
      publish  Upload the local catalog and/or logs to a Couchbase instance.
      status   Show the (aggregate) status of your Agent Catalog environment.
      version  Show the current version of Agent Catalog.
    
    See https://couchbaselabs.github.io/agent-catalog/index.html for more
    information.
    
  6. If you are interested in building a .whl file (for later use in .whl-based installation in other projects), run the following command:

    $ cd libs/agentc
    $ poetry build
    

Installing from Source (with Anaconda)

  1. Make sure you have python3.12 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=3.12
    $ 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 package and/or agentc_langgraph package with the command(s) below:

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

    Similarly, for LlamaIndex Developers:

    $ pip install libs/agentc_integrations/llamaindex