🌟 Azcore
azcore - A professional multi-agent framework built on Python
To help you ship azcore-powered apps to production faster, check out our comprehensive agent orchestration and workflow management capabilities.
Quick Install
pip install azcore
🤔 What is this?
azcore is the easiest way to start building hierarchical multi-agent systems and autonomous applications powered by LLMs. With under 10 lines of code, you can create sophisticated agent teams that collaborate, reason, and solve complex problems. azcore provides pre-built agent architectures, orchestration patterns, and workflow management to help you get started quickly and seamlessly incorporate intelligent agents into your applications.
We recommend you use azcore if you want to:
- Quickly build multi-agent systems with hierarchical coordination
- Implement advanced reasoning patterns like ReAct, Reflexion, and Self-Consistency
- Create autonomous agent teams with built-in collaboration and routing
- Build production-ready agent applications with persistence, caching, and monitoring
azcore supports multiple agent patterns and workflows including:
- 🎯 Agent Patterns: ReAct, Reflexion, Reasoning Duo, Self-Consistency
- 🌲 Workflow Types: Sequential, Concurrent, Hierarchical, Forest Swarm, Graph-based
- 🤝 Team Coordination: Agent routing, pattern matching, group chat, mixture of agents
- 🔄 Advanced Features: Reinforcement learning, state management, agent persistence
🚀 Features
- Multiple Agent Architectures: Choose from ReAct, Reflexion, and custom agent patterns
- Hierarchical Organization: Build complex agent hierarchies with supervisors and coordinators
- Flexible Workflows: Sequential, concurrent, graph-based, and swarm workflows
- Agent Routing: Intelligent routing based on patterns, capabilities, and context
- State Management: Robust state tracking and persistence across agent interactions
- MCP Integration: Support for Model Context Protocol team building
- Reinforcement Learning: Built-in RL manager for agent optimization with synthetic data training
- Synthetic Data Generation: Train RL models without real user data for faster bootstrapping
- Caching & Performance: Smart caching for LLM calls and conversation history
- Production Ready: Comprehensive logging, error handling, and monitoring
� Documentation
For full documentation, see the API reference.
Installation
pip install azcore
📄 License
azcore is released under the MIT License.
🔗 Links
- GitHub: https://github.com/Azrienlabs/Az-Core
- Issues: https://github.com/Azrienlabs/Az-Core/issues
- PyPI: https://pypi.org/project/azcore/
🙏 Acknowledgments
Built with ❤️ by the Azrienlabs team.
Ready to build the next generation of AI agents? Start with azcore today!
2 maintainers
Metadata
2 maintainers
Release files for azcore 0.0.11
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| azcore-0.0.11.tar.gz | 246.5 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| azcore-0.0.11-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 562.5 kB
Release files / azcore-0.0.11.tar.gz
| Download URL | azcore-0.0.11.tar.gz |
|---|---|
| Size | 246.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
8638dc3bc753ed37d1b6ec27d71077c557bb2bd8aaaec232758320642edfdbfb
|
|
BLAKE2b-256 checksum How to use checksums |
3865ceb1fdb11de907fa1b7c036d5ba92961a343a0bd4977c4206e1c870ef0aa
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Dec 9, 2025.
Transparency logRelease files / azcore-0.0.11-py3-none-any.whl
| Download URL | azcore-0.0.11-py3-none-any.whl |
|---|---|
| Size | 315.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
de6ff8e33601742eafd71b15c1299c6213366115edbc95be83fa7ad84dc31948
|
|
BLAKE2b-256 checksum How to use checksums |
41ce64e033e7a1cfe360f4f1f611a3f563fd17604acd7697843dc69984610223
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Dec 9, 2025.
Transparency logSecurity for azcore 0.0.11
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.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for azcore-0.0.11.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Dec 9, 2025.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
