EIO-Agents

The framework-agnostic semantic layer for AI-agent evaluation. EIO-Agents uses the Evaluation Intelligence Ontology (EIO) to turn an evaluator's observations into evidence-linked claims and a versioned Portable Evaluation Record (PER). It also validates, verifies, and explains that record.

Explore EIO and its schemas · See a PER example · Read the quick start

From evaluation to evidence

ProofAgent Harness is one possible evaluation producer; EIO-Agents does not require it. The raw bundle remains local. Review a PER before sharing it, because permitted redacted excerpts and metadata can still be sensitive.

Try the synthetic example

From this repository root, with Python 3.10 or newer:

python3 -m venv .venv
.venv/bin/pip install -e .
.venv/bin/eio-agents project tests/data/native/v0_6/source-complete.bundle.json \
  -o native.per.json --jcs native.per.jcs
.venv/bin/eio-agents validate native.per.json
.venv/bin/eio-agents verify native.per.json \
  --bundle tests/data/native/v0_6/source-complete.bundle.json
.venv/bin/eio-agents explain native.per.json --list
.venv/bin/eio-agents explain native.per.json readiness

The last command prints this explanation from the included synthetic bundle:

Readiness: 42.0448/100 (recorded). Raw weighted score: 42.0448/100.

Use a target from explain --list to inspect one finding or score, then eio-agents evidence native.per.json <finding-id> to locate its cited evidence. verify --bundle re-derives the PER and checks its digest against the local source; it does not prove the original evaluation or an agent is safe. The sample's score is not a production sign-off.

Versions and limits

• Package: 0.6.0rc1 · ontology: EIO 0.6.0 · source-complete record: PER 2.0.0. The reference scoring profile is 0.3.1-draft.1; missing inputs leave affected values WITHHELD, never guessed. Older partial records retain their own historical versions.
• Open format: PER 2.0.0 uses JSON Schema Draft 2020-12 and EIO publishes a JSON-LD context. It is a versioned ProofAgent specification, not a W3C- or ISO-ratified standard or a compliance certification.
• Framework mappings: provisional evidence-relevance links, not legal or regulatory compliance determinations. Historical ProofAgent report conversion requires the matching adapter and pinned EIO release.

For local-text privacy boundaries, CLI targets, and your own bundle, see the quick start. For the complete record structure and dashboard-style example, see the PER guide.

Develop and contribute

.venv/bin/pip install -e '.[test]'
.venv/bin/python -m pytest -q tests
.venv/bin/python tools/eio_gates.py

Maintained by ProofAI LLC under the ProofAgent brand. Code, ontology data, and schemas are Apache-2.0 licensed; see NOTICE, contribution guidelines, and security policy. Support and private security reports: support@proofagent.ai.