Skip to main content

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

SDK

The Python SDK provides a sync and async API client for the Cekura platform.

pip install cekura[sdk]
from cekura import Cekura

client = Cekura(api_key="your-api-key")

# List agents
agents = client.agents.list()

# Get a specific agent
agent = client.agents.get(agent_id=123)

# List scenarios for a project
scenarios = client.scenarios.list(project_id=42)

# Run test cases from a checked-in JSON spec, without creating evaluators.
# dry_run validates and prices the spec without running or charging anything.
import json
spec = json.load(open("tests/agent-suite.json"))
plan = client.scenarios.run_json(spec, agent_id=123, dry_run=True)
result = client.scenarios.run_json(spec, agent_id=123, channel="voice")

For async usage:

from cekura import AsyncCekura

async with AsyncCekura(api_key="your-api-key") as client:
    agents = await client.agents.list()

See the API documentation for the full resource reference.

CLI

The CLI lets you manage agents, scenarios, metrics, and test runs from the terminal.

pip install cekura[cli]
# Authenticate
cekura auth login

# List your agents
cekura agents list

# Start a test run
cekura run start --agent-id 123 --scenario-id 456

# Stream run progress
cekura run watch <run-id>

→ CLI Reference Guide

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
  • Built-in OpenTelemetry export for LiveKit agent traces

→ LiveKit Integration Guide

Pipecat

  • Automatic transcript capture with timestamps
  • Audio recording with S3 upload
  • Built-in OpenTelemetry tracing (conversation, turn, STT/LLM/TTS spans)
  • Session logs capture
  • Minimal 3-line integration

→ 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

Metadata

Release files for cekura 1.6.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for cekura 1.6.3
File Size Uploaded Provenance Actions
cekura-1.6.3.tar.gz 90.5 kB Without provenance Details for cekura-1.6.3.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for cekura 1.6.3
File Interpreter ABI Platform Actions
cekura-1.6.3-py3-none-any.whl Python 3 none any Details for cekura-1.6.3-py3-none-any.whl

Total release size: 216.5 kB

Release files / cekura-1.6.3.tar.gz

Download URL cekura-1.6.3.tar.gz
Size 90.5 kB
Tags Source
SHA-256 checksum
How to use checksums
c4a9b33bdff0e74e2f07f2d201147cdfba5a0822d0e23f5c167dafa5c3b78e0b
BLAKE2b-256 checksum
How to use checksums
819d70b8d21d02aa455584cb407edf6add31b4aa1537bc9bb1e7789044fd745b
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.5

Release files / cekura-1.6.3-py3-none-any.whl

Download URL cekura-1.6.3-py3-none-any.whl
Size 125.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
e65389da45bd0be4100ccd45fe2dd8ab134caa4ed2d2e622fd96557c0e4934a2
BLAKE2b-256 checksum
How to use checksums
ef3d3aa3983d9fc435efdf7ba91341fbc89c5c30633742ab4de79a12427c914e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.5

Security for cekura 1.6.3

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

1.6.3 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page