Norviq

Runtime policy enforcement for LLM agent tool calls.

License Docs

Norviq is a policy enforcement point (PEP) that sits between an agent's reasoning loop and the tools it can call. Every tool call is evaluated against OPA/Rego policy and then allowed, blocked, escalated, or audited — before the tool function runs. It turns "the model decided to call execute_sql" from implicit trust into an enforced, auditable decision.

This package is the Python SDK: it wraps your existing tools so enforcement happens in-process. The full platform (control plane, console, Kubernetes admission webhook, sidecar injection) is installed with the Helm chart — see the documentation.

Install

pip install "norviq[langchain]"      # LangChain / LangGraph
pip install "norviq[crewai]"         # CrewAI
pip install "norviq[autogen]"        # AutoGen
pip install "norviq[semantic-kernel]" # Semantic Kernel
pip install "norviq[frameworks]"     # all of the above

Use

from norviq.sdk import PolicyEngineClient, ToolInterceptor
from norviq.sdk.langchain.adapter import protect

engine = PolicyEngineClient()                      # NRVQ_POLICY_ENGINE_URL + NRVQ_API_TOKEN
interceptor = ToolInterceptor(evaluator=engine)

# Every tool is wrapped: policy runs before the tool body, on every call the model makes.
tools = protect([search_kb, execute_sql, delete_record], interceptor, session_id="session-1")

A blocked call raises NorviqBlockError, which carries the full PolicyDecision — including the rule_id that fired and a human-readable reason — so you can surface a refusal instead of performing the action:

from norviq.sdk import NorviqBlockError

try:
    result = agent.invoke({"messages": [("user", "delete all customer records")]})
except NorviqBlockError as exc:
    print(f"blocked by {exc.decision.rule_id}: {exc.decision.reason}")

Two things to know before your first run, because either one makes a correct setup look broken:

  • Norviq is deny-by-default. With no policy loaded for the scope you evaluate against, the decision is deny. Load a policy for your namespace/agent-class first.
  • POST /api/v1/evaluate requires a bearer token. Without one the client fails closed.

Links

Apache 2.0 licensed.

Project links

Data verified by PyPI on Jul 29, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.2.3)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for spuppala from gravatar.com spuppala

Credits

Author: Norviq

GitHub Statistics

Data verified by PyPI on Jul 29, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License

Apache Software License (Apache-2.0)

Requires

Python >=3.11

Provides Extra

dev spiffe langchain langgraph crewai autogen semantic-kernel frameworks

Tags

llm agents security policy-enforcement opa kubernetes ai-safety

Classifiers

Report project as malware

Download files

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

Source Distribution

norviq-0.1.6.tar.gz (369.1 kB view details)

Uploaded Source

Built Distribution

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

norviq-0.1.6-py3-none-any.whl (430.4 kB view details)

Uploaded Python 3

File details

Details for the file norviq-0.1.6.tar.gz.

File metadata

  • Download URL: norviq-0.1.6.tar.gz
  • Upload date:
  • Size: 369.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.13

File hashes

Hashes for norviq-0.1.6.tar.gz
Algorithm Hash digest
SHA256 d1d38c7fb3ee3b989833459af4b2846ef70c843942bf1ca90e8c8cf548916cc7
MD5 d0798b8b9420b0936913200e6a396cc5
BLAKE2b-256 32db208f368b16bb96220e24d194b357e98090f2a44058e7c0893f9f5b3255e8

See more details on using hashes here.

Provenance

The following attestation bundles were made for norviq-0.1.6.tar.gz:

Publisher: release.yml on norviq-dev/norviq

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

File details

Details for the file norviq-0.1.6-py3-none-any.whl.

File metadata

  • Download URL: norviq-0.1.6-py3-none-any.whl
  • Upload date:
  • Size: 430.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.13

File hashes

Hashes for norviq-0.1.6-py3-none-any.whl
Algorithm Hash digest
SHA256 4f2d7aa7b5e0aa3e3e057012e23f18d6de7064b2c32cc83bf7a773ad44e35030
MD5 f5f6e7170c77085bd9bb6e101213e5b9
BLAKE2b-256 f3726a21bd4459b9c814bca8781fe8ffcbb151a523495b811e628cba551aef30

See more details on using hashes here.

Provenance

The following attestation bundles were made for norviq-0.1.6-py3-none-any.whl:

Publisher: release.yml on norviq-dev/norviq

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 Sentry Error logging StatusPage Status page