Skip to main content

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

Project description

Vaara

PyPI Python License CI OpenSSF Scorecard OpenSSF Best Practices

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.
  • 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

Project details


Release history Release notifications | RSS feed

This version

0.6.2

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vaara-0.6.2.tar.gz (363.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

vaara-0.6.2-py3-none-any.whl (335.5 kB view details)

Uploaded Python 3

File details

Details for the file vaara-0.6.2.tar.gz.

File metadata

  • Download URL: vaara-0.6.2.tar.gz
  • Upload date:
  • Size: 363.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.13

File hashes

Hashes for vaara-0.6.2.tar.gz
Algorithm Hash digest
SHA256 aaad72e442b01dbbaf733eb05f8f577e502451a579c5ffd7b4fc8890b17deb13
MD5 5d6d05d36c8fce7ea8538e860f1d54ef
BLAKE2b-256 59e819aa805109ff74ecfd5d01a53c34747f4b27eb9cf27eae8e483dbe5aed57

See more details on using hashes here.

Provenance

The following attestation bundles were made for vaara-0.6.2.tar.gz:

Publisher: release.yml on vaaraio/vaara

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file vaara-0.6.2-py3-none-any.whl.

File metadata

  • Download URL: vaara-0.6.2-py3-none-any.whl
  • Upload date:
  • Size: 335.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.13

File hashes

Hashes for vaara-0.6.2-py3-none-any.whl
Algorithm Hash digest
SHA256 29f3d54c19a9d3aa02e60684291dbbd386081e190bae177287e67ed17a2fb302
MD5 31856ec66f2e7068eb9c42e28bf985a8
BLAKE2b-256 db572cee12aa92c0014b42f3ec4c61615b87eec74f278482ac2b437308858604

See more details on using hashes here.

Provenance

The following attestation bundles were made for vaara-0.6.2-py3-none-any.whl:

Publisher: release.yml on vaaraio/vaara

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page