Skip to main content

An open-source, domain-agnostic, capability-based architecture for building intelligent agents

Project description

Alpha Berkeley Framework

🚧 Early Access Release
This is an early access version of the Alpha Berkeley Framework. While the core functionality is stable and ready for experimentation, documentation and APIs may still evolve. We welcome feedback and contributions!

An open-source, domain-agnostic, capability-based architecture for building intelligent agents that can be adapted to any specific domain.

📄 Research
This work was presented as a contributed oral presentation at ICALEPCS'25 and will be featured at the Machine Learning and the Physical Sciences Workshop at NeurIPS 2025.

🚀 Quick Start

# Install the framework
pip install alpha-berkeley-framework

# Create a new project from a template
framework init my-weather-agent --template hello_world_weather

# Navigate to your project
cd my-weather-agent

# Setup environment
cp .env.example .env
# Edit .env with your API keys

# Start the command line chat interface
framework chat

# Or use the web interface at http://localhost:8080

📚 Documentation

📖 Read the Full Documentation →

Key Features

  • Scalable Capability Management - Efficiently scales to large sets of specialized agents
  • Structured Orchestration - Converts freeform inputs into clear, executable plans
  • Modular Architecture - Easily integrates new capabilities without disrupting workflows
  • Human-in-the-Loop Ready - Transparent execution plans for inspection and debugging
  • Domain-Adaptable - Designed for heterogeneous scientific infrastructure

📖 Citation

If you use the Alpha Berkeley Framework in your research or projects, please cite our paper:

@misc{hellert2025alphaberkeley,
      title={Alpha Berkeley: A Scalable Framework for the Orchestration of Agentic Systems}, 
      author={Thorsten Hellert and João Montenegro and Antonin Sulc},
      year={2025},
      eprint={2508.15066},
      archivePrefix={arXiv},
      primaryClass={cs.MA},
      url={https://arxiv.org/abs/2508.15066}, 
}

For detailed installation instructions, tutorials, and API reference, please visit our complete documentation.


Copyright Notice

Alpha Berkeley Framework (alpha berkeley) Copyright (c) 2025, The Regents of the University of California, through Lawrence Berkeley National Laboratory (subject to receipt of any required approvals from the U.S. Dept. of Energy). All rights reserved.

If you have questions about your rights to use or distribute this software, please contact Berkeley Lab's Intellectual Property Office at IPO@lbl.gov.

NOTICE. This Software was developed under funding from the U.S. Department of Energy and the U.S. Government consequently retains certain rights. As such, the U.S. Government has been granted for itself and others acting on its behalf a paid-up, nonexclusive, irrevocable, worldwide license in the Software to reproduce, distribute copies to the public, prepare derivative works, and perform publicly and display publicly, and to permit others to do so.


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

alpha_berkeley_framework-0.7.4.tar.gz (1.3 MB view details)

Uploaded Source

Built Distribution

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

alpha_berkeley_framework-0.7.4-py3-none-any.whl (1.4 MB view details)

Uploaded Python 3

File details

Details for the file alpha_berkeley_framework-0.7.4.tar.gz.

File metadata

File hashes

Hashes for alpha_berkeley_framework-0.7.4.tar.gz
Algorithm Hash digest
SHA256 133265d03297b93a0f470ae8e86b7c9a835d5296ae420767c54fd522dae249b0
MD5 ddbe0b7e591726b0ab52f6c2c7dac549
BLAKE2b-256 053345121a82961a3d5b7c8e710064fc34bc35b40ff7125a57e1966942703333

See more details on using hashes here.

File details

Details for the file alpha_berkeley_framework-0.7.4-py3-none-any.whl.

File metadata

File hashes

Hashes for alpha_berkeley_framework-0.7.4-py3-none-any.whl
Algorithm Hash digest
SHA256 7fd6e4a10feb1106984563c2a28e0ec9b3e060a6c64274b8f8ef8f7e21c84000
MD5 2879e906a6d29a8036f1eb6574fc816c
BLAKE2b-256 b7dfa9af5cd71b50b271bef6e88fa0f4e67d0a2eb9f519e45cef098a365cdd65

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