Archytas: A Tools Interface for AI Agents

Implementation of the ReAct (Reason & Action) framework for Large Language Model (LLM) agents. Extensible to a variety of LLMs and LLM providers.

Easily create tools from simple python functions or classes with the @tool decorator. A tools list can then be passed to the ReActAgent which will automagically generate a prompt for the LLM containing usage instructions for each tool, as well as manage the ReAct decision loop while the LLM performs its task.

Tools can be anything from internet searches to custom interpreters for your domain. Archytas provides a few built-in demo tools e.g. datetime, fibonacci numbers, and a simple calculator.

Demos

Short demo of using the PythonTool to download a COVID-19 dataset, and perform some basic processing/visualization/analysis/etc.

MCP Demos

# Install with MCP support (includes langchain-mcp-adapters + fastmcp)
uv pip install -e ".[mcp]"

# Vision demo with local MCP server
python demos/demo_mcp_vision.py

# External MCP server (DuckDuckGo search via npx)
python demos/demo_mcp_duckduckgo.py

# HTTP MCP server (Context7 - requires API key)
export CONTEXT7_API_KEY="your-api-key"
python demos/demo_mcp_context7.py

To use mcp tools with archytas, you will need to install the optional deps uv pip install -e ".[mcp]"

Read the mcp quick start doc for more info

Quickstart

# clone and install
git clone git@github.com:jataware/archytas.git
cd archytas
uv pip install -e .

# make sure OPENAI_API_KEY var is set
# or pass it in as an argument to the agent
export OPENAI_API_KEY="sk-..."

# run demo
uv run chat-repl

Simple Usage

Import pre-made tools from the tools module

from archytas.react import ReActAgent, FailedTaskError
from archytas.tools import PythonTool

from easyrepl import REPL

# create the agent with the tools list or a `custom_prelude` (if desired)
some_tools = [PythonTool, ..., etc.]
agent = ReActAgent(tools=some_tools, verbose=True)

# REPL to interact with agent
for query in REPL():
    try:
        answer = agent.react(query)
        print(answer)
    except FailedTaskError as e:
        print(f"Error: {e}")

Documentation

See the wiki docs for details.