vaara 0.12.0

Adaptive AI Agent Execution Layer for risk scoring, audit trails, and regulatory compliance

Vaara intercepts agent tool calls, scores each one with a conformal risk interval, and writes a hash-chained audit record. Online learning across five expert signals via Multiplicative Weight Update. Distribution-free conformal coverage on the score.

For broader agent governance (zero-trust identity, capability-based access control, multi-language SDKs) see Microsoft's Agent Governance Toolkit.

Numbers

• 5,955-entry adversarial corpus (3,422 attack across 8 categories, 2,533 benign)
• 97.1% attack recall on held-out distribution-shift split, threshold 0.55
• PAIR adaptive-attacker calibration: ASR 0/25 against Qwen2.5-32B
• vaara-bench-v1: 77-trace synthetic-corpus benchmark with frozen methodology, 100% soft TPR, 0% hard FPR
• 140 µs / 210 µs p99 inference latency, commodity CPU
• Distribution-free conformal coverage on the score
• MWU regret bound O(sqrt(T log N))

Install

pip install vaara

Python 3.10+. Zero runtime deps. Optional XGBoost classifier: pip install vaara[ml].

Quick start

from vaara.pipeline import InterceptionPipeline

pipeline = InterceptionPipeline()
result = pipeline.intercept(
    agent_id="agent-007",
    tool_name="fs.write_file",
    parameters={"path": "/etc/service.yaml", "content": "..."},
    agent_confidence=0.8,
)
if result.allowed:
    pipeline.report_outcome(result.action_id, outcome_severity=0.0)
else:
    print(result.reason)

report_outcome closes the loop. MWU reweights signals based on which ones predicted the outcome.

HTTP API

The same scorer and audit trail are available over HTTP for non-Python agents and for control planes that prefer a network boundary. Install with the server extra:

pip install 'vaara[server]'
vaara serve --host 0.0.0.0 --port 8000

curl -sX POST http://localhost:8000/v1/score \
  -H 'content-type: application/json' \
  -d '{"tool_name":"tx.transfer","agent_id":"agent-007","base_risk_score":0.5}'

The contract is in docs/openapi.yaml. Vaara defines the interface; control-plane and orchestration vendors call it. Integration recipes for adopters live under examples/recipes/.

OVERT 1.0 attestation

Vaara is the first OSS Python reference implementation of the OVERT 1.0 (overt.is, Glacis Technologies, March 2026) Protocol Profile 1.0 Base Envelope at AAL-3 Phase 2 (Provisional Receipt). Closed-schema 9-field structure, canonical CBOR encoding, Ed25519 signatures, HMAC-SHA256 keyed commitments, IEEE-754 float rejection. External Independent Attestation Providers can promote AAL-3 emission to AAL-4 by attaching Phase 3 notary signatures and transparency-log inclusion proofs.

pip install 'vaara[attestation]'

from vaara.attestation.overt import emit_base_envelope, make_request_commitment, encoder_binary_identity

envelope = emit_base_envelope(
    signing_key=key,
    request_commitment=make_request_commitment(payload, operator_key=op_key),
    encoder_binary_identity=encoder_binary_identity(arbiter_version="vaara/0.12.0", policy_hash=ph),
    non_content_metadata={"action_class": "tx.transfer", "decision": "escalate"},
    monotonic_counter=42,
    arbiter_instance_identifier=uuid_bytes,
)

Vaara operates as the Arbiter in OVERT terms. See COMPLIANCE.md "Position relative to open runtime-attestation standards" for the architectural framing.

v0.12.0 adds an OVERT S3P (MEA-2) emitter with exact Clopper-Pearson confidence intervals (pure Python, no scipy), plus a proposed Protocol Profile extension that reports aggregate statistics over Vaara's per-action conformal prediction intervals alongside the standard binomial CI. The agentic-controls mapping in COMPLIANCE.md "OVERT 1.0 Part 3 (Agentic AI Controls) mapping" walks Vaara's coverage of TOOL-, MCP-, MULTI-, CAP-, DISC-, HITL-, and DRIFT-* control by control.

from vaara.attestation.s3p import emit_s3p_attestation, ConformalExtension, make_epoch_nonce_commitment

Where things live

• docs/formal_specification.md: math. MWU regret bound O(sqrt(T log N)), conformal coverage guarantees, security properties.
• COMPLIANCE.md: Article-level evidence mapping for EU AI Act (Articles 9, 11 to 15, 61) and DORA (Articles 10, 12, 13). Eval numbers, threshold sweeps, PAIR adversarial calibration.
• Article 14 runtime: why oversight of agentic AI has to be evidenced as action, not model: why this exists. Posted on the EU Apply AI Alliance Futurium.
• src/vaara/integrations/: LangChain, OpenAI Agents SDK, CrewAI, MCP server.
• src/vaara/audit/: hash-chain trail, SQLite backend, append-only WAL.
• src/vaara/policy/: declarative YAML / JSON policy schema with vaara policy validate (semantic checks) and vaara policy test (Conftest-style cases-file runner) for reviewing the policy artifact in CI independently from agent code.
• src/vaara/sandbox/: synthetic-trace cold-start calibration.

Vaara helps deployers assemble evidence for their own conformity work. It does not certify compliance or constitute legal advice. Deployers own their obligations under the EU AI Act and other applicable law.

License

LICENSE