Skip to main content

Testing and Observability SDK for AI Agents

Project description

Cekura Python SDK

Testing and Observability for AI Voice Agents. Launch in minutes not weeks by ensuring your agents deliver a seamless experience in every conversational scenario.

Installation

pip install cekura

Integrations

LiveKit

  • One-line integration for simulation and observability
  • Automatic metrics collection (STT, LLM, TTS, EOU)
  • Session logs capture
  • Mock tool injection for testing
  • Dual-channel audio recording

→ LiveKit Integration Guide

Pipecat

  • Automatic transcript capture with timestamps
  • Audio recording with S3 upload
  • Minimal 3-line integration
  • Automatic cleanup

→ Pipecat Integration Guide

Requirements

  • Python 3.9+
  • aiohttp>=3.9.0

License

MIT License - see LICENSE file for details.

Links

Support

For support, email support@cekura.ai

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

cekura-1.2.0rc3.tar.gz (23.2 kB view details)

Uploaded Source

Built Distribution

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

cekura-1.2.0rc3-py3-none-any.whl (24.4 kB view details)

Uploaded Python 3

File details

Details for the file cekura-1.2.0rc3.tar.gz.

File metadata

  • Download URL: cekura-1.2.0rc3.tar.gz
  • Upload date:
  • Size: 23.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for cekura-1.2.0rc3.tar.gz
Algorithm Hash digest
SHA256 2ef8785b983a644f239b76729b514f2029ad5c48aefeff688b149746b1ff266d
MD5 a06b289555a5bde89f9c0d085ac3f65f
BLAKE2b-256 9fe4d49ac7c3f39f50d1b375ac19d106fcd65829ed59e6519cba08c9869036bc

See more details on using hashes here.

File details

Details for the file cekura-1.2.0rc3-py3-none-any.whl.

File metadata

  • Download URL: cekura-1.2.0rc3-py3-none-any.whl
  • Upload date:
  • Size: 24.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for cekura-1.2.0rc3-py3-none-any.whl
Algorithm Hash digest
SHA256 d18d09716468adcc66d182198ec0cacd94e950c358d3ad0aee413b49ad07eac5
MD5 f3ef0110a983be88a73adc31ad4195ee
BLAKE2b-256 816d03a56f504edecc796f26aee72ad212c7b2800d60aab9c5d60348db392c42

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