Skip to main content

Modular agent framework combining LLMs and Tools

Project description

agents-for-all

Modular agent framework combining LLMs and tools.

Built with uv Test Coverage Python 3.10 Python 3.11 Python 3.12 Python 3.13

Designed to help developers quickly build task-solving agents using large language models and pluggable toolchains.


✨ Features

  • 🔌 Pluggable tool architecture
  • 🤖 LLM integration (OpenAI, Anthropic, Gemini, Direct, etc.)
  • 🧪 Built-in testing with pytest
  • 📝 Documentation support via sphinx
  • ⚡ Fast dependency management using uv

📦 Installation and Usage

pip install agents-for-all
from agents_for_all import Agent
from agents_for_all.llms.direct import DirectModel
from agents_for_all.tools.python import Python

llm = DirectModel(
  api_endpoint="http://localhost:1234/v1/chat/completions",
  model="deepseek-r1-distill-llama-8b"
)
agent = Agent(llm=llm, tools=[Python()])
result = agent.do("Generate a Fibonacci sequence of length 10.")
print(result.output) # Final output
print(result.history) # History of steps taken

🚀 Getting Started

Prerequisites

  • Python 3.10+
  • uv installed:
    curl -Ls https://astral.sh/uv/install.sh | sh
    

Installation

Create a virtual environment and install dependencies:

uv sync

🧪 Running Tests

uv run pytest

📚 Documentation

To build the Sphinx docs (if configured):

uv run sphinx-build docs docs/_build

🛠 Project Structure (Sample)

agents_for_all/
├── agent.py           # Agent class
├── tools/             # Modular tools the agent can use
├── llms/              # Collection of LLMs the agent can connect to
├── tests/             # Pytest test cases
├── README.md
├── pyproject.toml
└── .gitignore

🤝 Contributing

  1. Fork this repository
  2. Create your feature branch (git checkout -b feature/YourFeature)
  3. Commit your changes (git commit -am 'Add YourFeature')
  4. Push to the branch (git push origin feature/YourFeature)
  5. Create a new Pull Request

📄 License

Apache License 2.0


🔗 Links

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agents_for_all-0.1.3.tar.gz (9.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agents_for_all-0.1.3-py3-none-any.whl (11.6 kB view details)

Uploaded Python 3

File details

Details for the file agents_for_all-0.1.3.tar.gz.

File metadata

  • Download URL: agents_for_all-0.1.3.tar.gz
  • Upload date:
  • Size: 9.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.17

File hashes

Hashes for agents_for_all-0.1.3.tar.gz
Algorithm Hash digest
SHA256 aece1d36834f6b9c583d414ce8dd80b4f3063b62eb68653a155450aeb8d3e9b7
MD5 3783979f3c1d5ed868f219cf6bc9d986
BLAKE2b-256 672d0ac3f042425cb1c2ad2855b1d4c32910311bb10487bf1df96726e40f614e

See more details on using hashes here.

File details

Details for the file agents_for_all-0.1.3-py3-none-any.whl.

File metadata

  • Download URL: agents_for_all-0.1.3-py3-none-any.whl
  • Upload date:
  • Size: 11.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.17

File hashes

Hashes for agents_for_all-0.1.3-py3-none-any.whl
Algorithm Hash digest
SHA256 57278fc5d0af8d8d268823f8ac1a8894cb8adc86df0485a2f2cbba4f0a64aa01
MD5 a502938b6cb877bd679e19878196a3e4
BLAKE2b-256 43d4a4ccce9708b102d2945c4d86bd90f05228ad012a3cf213badd56a6ce57da

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page