intro
IOA Core — Developer Documentation
Welcome to the IOA (Intelligent Orchestration Architecture) Core developer documentation. IOA Core v2.6.1 is the current stable public release on PyPI.
IOA Core is an open-source governance kernel for AI workflows. It focuses on policy enforcement, evidence capture, immutable audit trails, memory-backed orchestration, and multi-model review patterns.
What Is Included
- Immutable audit chains with hash continuity and tamper detection
- Evidence bundles for governed decisions and validations
- Memory Fabric with hot and persistent storage backends
- Vendor-neutral quorum patterns for multi-model review
- Provider support for OpenAI, Anthropic, Gemini, DeepSeek, XAI, and Ollama
- Runnable examples for bootstrap, workflows, roundtable, doctor, providers, and Ollama turbo
- CLI entrypoints for local development and diagnostics
Quick Start
- Install the package:
pip install ioa-core - Clone the repository if you want the examples locally
- Run the bootstrap, workflow, and doctor examples
pip install ioa-core
git clone https://github.com/OrchIntel/ioa-core.git
cd ioa-core
ioa --help
python examples/00_bootstrap/boot_project.py /tmp/ioa-core-demo-project
python examples/10_workflows/run_workflow.py
python examples/30_doctor/doctor_check.py
Examples run offline by default unless you explicitly enable live mode and provide API keys.
Public Release Posture
The current public release has been validated through:
- green repository CI on
main - successful PyPI publication for
v2.6.1 - fresh-install smoke verification from PyPI
- downstream compatibility checks across dependent repos
- bounded perf and durability profiles in CI-safe mode