Skip to main content

Parlot

Production voice AI observability — MIT OpenTelemetry instrumentation for LiveKit Agents (and LangGraph when you already run voice).

Know if your voice agent is actually working. Install the sidecar, call parlotize() once, and Parlot models each call as turns: timeline, multi-agent handoff graph, pipeline waterfall, and goal completion with an evidence trail to the proving turns and audio.

Works with LiveKit Cloud, self-hosted media, and LiveKit on Telnyx.

Install

# LiveKit Agents (recommended)
pip install "parlot[livekit]"

# LangGraph / LangChain (same debugger for text agents alongside voice)
pip install "parlot[langgraph]"

# Both
pip install "parlot[all]"

Or install an instrumentation package directly:

pip install parlot-instrumentation-livekit
# or
pip install parlot-instrumentation-langgraph

Instrument (LiveKit)

from parlot.instrumentation.livekit import parlotize

parlotize("my-agent")

Call parlotize("…") before constructing AgentSession, then await ctx.connect() before session.start(). Set PARLOT_ENDPOINT and PARLOT_API_KEY (mint in Settings → API Keys).

Full checklist: LiveKit guide · Quick Start

Documentation

parlot.ai/docs · parlot.ai · GitHub

Metadata

Release files for parlot 0.3.1

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

Source distribution (sdist)

Source distribution for parlot 0.3.1
File Size Uploaded Provenance
parlot-0.3.1.tar.gz 2.8 kB With provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for parlot 0.3.1
File Interpreter ABI Platform
parlot-0.3.1-py3-none-any.whl Python 3 none any Details

Total release size: 5.6 kB

Release files / parlot-0.3.1.tar.gz

Download URL parlot-0.3.1.tar.gz
Size 2.8 kB
Tags Source
SHA-256 checksum
How to use checksums
178d874b035e0994a9618298b27363fbff6a3b52ec7a9cd8d43e5e4eae48e80f
BLAKE2b-256 checksum
How to use checksums
09a05ddd735bb7dae9de4f6d598aa6f4371cb8e724449fc8dac562ee93b6831f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 20, 2026.

Transparency log

Release files / parlot-0.3.1-py3-none-any.whl

Download URL parlot-0.3.1-py3-none-any.whl
Size 2.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
568f9e6e15ecade84220da46df406c165f743e4a43ad3bd8a4e2fe330a6e5d7c
BLAKE2b-256 checksum
How to use checksums
4d5c2c13eca32e777fee4269eac307b383522e98f19730ba4ab1325619b73a5a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 20, 2026.

Transparency log

Security for parlot 0.3.1

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.

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for parlot-0.3.1.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 20, 2026.

Transparency log

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.

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