Skip to main content

An operational monitoring library for Crew AI applications.

Project description

Agent Watch

Agent Watch is an operational monitoring library for Crew AI applications. It captures essential metrics such as token counts, costs, execution time, resource utilization, carbon emissions, and detailed logs. Additionally, it offers both textual and visual representations of the collected data via a Command-Line Interface (CLI) or a Streamlit dashboard.

Features

  1. Token Counting

    • Total tokens
    • Input tokens
    • Output tokens
  2. Cost Calculation

    • Based on the token usage and model pricing
  3. Performance Metrics

    • Time taken for each call
    • CPU and memory consumption
  4. Environmental Impact

    • Estimated CO₂ emissions
  5. Logging

    • Comprehensive logs of all operations
  6. Visualization

    • CLI summaries
    • Streamlit dashboard for detailed insights

Installation

You can install Agent Watch via pip. If not published to PyPI, install it locally:

pip install .

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

agent_watch-0.1.1.tar.gz (5.6 kB view details)

Uploaded Source

Built Distribution

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

agent_watch-0.1.1-py3-none-any.whl (7.0 kB view details)

Uploaded Python 3

File details

Details for the file agent_watch-0.1.1.tar.gz.

File metadata

  • Download URL: agent_watch-0.1.1.tar.gz
  • Upload date:
  • Size: 5.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.3

File hashes

Hashes for agent_watch-0.1.1.tar.gz
Algorithm Hash digest
SHA256 bf272a75b30ff7a7f9c09470c68dbd1234164a4ad230fdba915d094b07074005
MD5 7e538028cf7b336d144d699f499f302e
BLAKE2b-256 f9514426cc4d61d75d32a0746fe5df302f0ab2a56cbf6891220da3137840469c

See more details on using hashes here.

File details

Details for the file agent_watch-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: agent_watch-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 7.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.3

File hashes

Hashes for agent_watch-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 cad733b9188666cd67715c7de25fe892876b10d375f0efec997f3b26520b8bbc
MD5 9246c7fde7a582917676222530a038c2
BLAKE2b-256 e549f74c4e97e9eb667f0d45b0724e5e41029ae8d0585617ba65073a7537a2dd

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