Skip to main content

getting-started

Getting Started with IOA Core

IOA Core v2.6.1 is the current stable public release.

IOA Core is an open-source framework for governed AI orchestration: policy checks, evidence capture, immutable audit trails, memory-backed context, and quorum-style review patterns.

System Requirements​

  • Python 3.10 to 3.12
  • pip
  • optional provider API keys for live tests

Install​

pip install ioa-core

For source-based development:

git clone https://github.com/OrchIntel/ioa-core.git
cd ioa-core
pip install -e ".[dev]"

Verify the Install​

ioa --help
python examples/30_doctor/doctor_check.py

First Run​

Bootstrap a project​

python examples/00_bootstrap/boot_project.py my-ai-system

Run a governed workflow​

python examples/10_workflows/run_workflow.py

Run a quorum example​

python examples/20_roundtable/roundtable_quorum.py "Analyze this code for security issues (ok)"

Smoke-test providers​

IOA_PROVIDER=mock python examples/40_providers/provider_smoketest.py

Live Provider Mode​

Examples default to offline or mock-friendly behavior. For live provider checks, set keys explicitly and turn on live mode.

export OPENAI_API_KEY="your-openai-key"
IOA_LIVE=1 IOA_PROVIDER=openai python examples/40_providers/provider_smoketest.py

If live keys are not configured, treat outputs as local demo results rather than provider validation.

What v2.6.1 Gives You​

  • hash-chained audit logging
  • evidence bundle generation
  • policy and system-law framing
  • memory fabric primitives
  • offline and live provider smoke testing
  • local examples for governed workflow and quorum-style review

Next Docs​

Help​