vaara 0.7.0

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
• 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.

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/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