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.

click to watch original video on youtube

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.

Metadata

Release files for archytas 2.0.8

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for archytas 2.0.8
File	Size	Uploaded
archytas-2.0.8.tar.gz	87.9 kB	Oct 15, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for archytas 2.0.8
File	Interpreter	ABI	Platform	Reset
archytas-2.0.8-py3-none-any.whl 103.0 kB Oct 15, 2026	Python 3	none	any	Details

Total release size: 190.8 kB

Release files / archytas-2.0.8.tar.gz

Download URL	archytas-2.0.8.tar.gz
Size	87.9 kB
Tags	Source
SHA-256 checksum How to use checksums	`9074d5e23c6b78e176e320b53cd77f2cc386866734ad586289f9266b40f55114`
BLAKE2b-256 checksum How to use checksums	`0e4cafac39b6b62b4a99b0be5a97893543134affd709641a545b220f283b45c5`
Upload date	Oct 15, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/jataware/archytas
Publishing commit: github.com/jataware/archytas/tree/6fce51527a9b6e45136bc03025560ca5421820b1

Workflow

Publishing configuration: github.com/jataware/archytas/blob/6fce51527a9b6e45136bc03025560ca5421820b1/.github/workflows/publish.yml
Publishing logs: github.com/jataware/archytas/actions/runs/38821253450/attempts/1

Artifact

Subject: archytas-2.0.8.tar.gz
SHA-256 checksum: 9074d5e23c6b78e176e320b53cd77f2cc386866734ad586289f9266b40f55114 Verifying attestations

Release files / archytas-2.0.8-py3-none-any.whl

Download URL	archytas-2.0.8-py3-none-any.whl
Size	103.0 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`cbc2d9a89e77f9d51c60e42eff50fce5caccb24327f38609cfbf329276bf1335`
BLAKE2b-256 checksum How to use checksums	`a9a88ec1991f5a596f01b67617eab621678c80168a0616346763356bea5c7e10`
Upload date	Oct 15, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/jataware/archytas
Publishing commit: github.com/jataware/archytas/tree/6fce51527a9b6e45136bc03025560ca5421820b1

Workflow

Publishing configuration: github.com/jataware/archytas/blob/6fce51527a9b6e45136bc03025560ca5421820b1/.github/workflows/publish.yml
Publishing logs: github.com/jataware/archytas/actions/runs/38821253450/attempts/1

Artifact

Subject: archytas-2.0.8-py3-none-any.whl
SHA-256 checksum: cbc2d9a89e77f9d51c60e42eff50fce5caccb24327f38609cfbf329276bf1335 Verifying attestations