Skip to main content

Nerq trust verification for CrewAI — discover trusted agents and gate tool calls with preflight checks

Project description

nerq-crewai

Trust verification for CrewAI crews

Nerq Badge

Discover trusted AI agents and gate every tool call with Nerq preflight trust checks before your CrewAI crew executes.

Install

pip install nerq-crewai

Quick start

from nerq_crewai import NerqCrewBuilder, trust_gate_crew

# 1. Discover and build a crew from trusted agents
builder = NerqCrewBuilder(api_key="your-key")
crew = builder.build_crew(
    task_description="Analyze competitor pricing",
    roles=["researcher", "analyst", "writer"],
    min_trust_score=80,
)

# 2. Gate all tool calls with Nerq trust verification
crew = trust_gate_crew(crew, min_trust=60)

# 3. Run — any untrusted tool call raises TrustError
result = crew.kickoff()

Trust gate behaviour

Before every tool invocation, trust_gate_crew checks the tool against the Nerq preflight API:

Recommendation Trust score Action
PROCEED >= 70 Silent pass-through
CAUTION 40 - 69 Logs warning, proceeds
DENY < 40 Raises TrustError
UNKNOWN n/a Logs warning, proceeds

Any tool whose trust score falls below min_trust also raises TrustError.

Discover trusted tools

from nerq_crewai import NerqCrewBuilder

builder = NerqCrewBuilder()
tools = builder.discover_trusted_tools("code-generation", min_trust=70)
for t in tools:
    print(f"{t['name']}  trust={t['trust_score']}")

Convenience functions

from nerq_crewai import discover_crewai_agents, build_crew_from_discovery

# Find agents for a capability
agents = discover_crewai_agents("web scraping", min_trust_score=75)

# One-liner crew
crew = build_crew_from_discovery(
    task="Summarize top 10 AI news stories",
    roles=["researcher", "writer"],
)

Links

Project details


Download files

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

Source Distribution

nerq_crewai-0.1.0.tar.gz (6.1 kB view details)

Uploaded Source

Built Distribution

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

nerq_crewai-0.1.0-py3-none-any.whl (7.9 kB view details)

Uploaded Python 3

File details

Details for the file nerq_crewai-0.1.0.tar.gz.

File metadata

  • Download URL: nerq_crewai-0.1.0.tar.gz
  • Upload date:
  • Size: 6.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for nerq_crewai-0.1.0.tar.gz
Algorithm Hash digest
SHA256 b5e8cbb81d52d0bc8bda86df94428b4102d205f412e0cd600c9335418adb9d4e
MD5 5517d7ca54260162cb290d2b42c4e159
BLAKE2b-256 a48aec1cf245b16fda7e9e82286fb719d4dd91e564329ba40418e7e590bc1ef9

See more details on using hashes here.

File details

Details for the file nerq_crewai-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: nerq_crewai-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 7.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for nerq_crewai-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 7c7a0444e94126e7ef97837cbd7d82ad35dd0bdf60de09897e0593e5398e9054
MD5 2aeb83491773cf9facc5ab5baa310fe2
BLAKE2b-256 c530d3bed3cbb650748b400d1889f1eb1df134daa74145e436ecc793458db5cd

See more details on using hashes here.

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