Skip to main content

Entropy Labs' Sentinel is an agent control plane that enables efficient oversight of thousands of parallel-running agents.

Project description

Entropy Labs Python Package

Sentinel

Sentinel is an agent control plane developed by Entropy Labs that allows you to efficiently oversee thousands of agents running in parallel. This is the Python package for Sentinel, which implements various types of approvers that can be integrated into the AISI Inspect platform or used separately.

Features

  • Efficient oversight of parallel-running agents
  • Various types of approvers including human, bash, python or LLM-powered approvers
  • Integration with AISI's Inspect platform
  • Standalone usage capability

More Information

For more detailed information, documentation, and usage examples, please visit the main GitHub repository:

https://github.com/EntropyLabsAI/sentinel

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

entropy_labs-0.1.8.tar.gz (56.2 kB view details)

Uploaded Source

Built Distribution

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

entropy_labs-0.1.8-py3-none-any.whl (118.7 kB view details)

Uploaded Python 3

File details

Details for the file entropy_labs-0.1.8.tar.gz.

File metadata

  • Download URL: entropy_labs-0.1.8.tar.gz
  • Upload date:
  • Size: 56.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.10

File hashes

Hashes for entropy_labs-0.1.8.tar.gz
Algorithm Hash digest
SHA256 8db4180563b9756ffeaf028b32c17e2bb19fd87929947caf026ec1ea56633cc7
MD5 68adca49fd217ede0bd4cde9cb65381c
BLAKE2b-256 18c245a5723c5449b7dc2ea73f3b7ab5aff90f4b4f421dbb40f5c156b2b932c0

See more details on using hashes here.

File details

Details for the file entropy_labs-0.1.8-py3-none-any.whl.

File metadata

  • Download URL: entropy_labs-0.1.8-py3-none-any.whl
  • Upload date:
  • Size: 118.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.10

File hashes

Hashes for entropy_labs-0.1.8-py3-none-any.whl
Algorithm Hash digest
SHA256 50d66edd2e5356a28e6fbfbd7d4d40c802dd2d3f762214472137e0f8611ec9e2
MD5 ac035230e6d8e73242491a46b969943c
BLAKE2b-256 6a63182569a52512bcbdab9b5c6fec3c8f44f7a5aa7d2d2a395a6cbec3add862

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