---
id: pipecat-ai-whisker
version: "2.0.0"
license: BSD-2-Clause
license_treatment: permissive
maintenance: active
---

# pipecat-ai-whisker — A real-time debugger for Pipecat

License: permissive · Maintenance: active · Downloads: 112.0K/mo

## What it is and what it does

Whisker is a low-level debugger built specifically for the Pipecat framework, which orchestrates multi-agent voice and multimodal AI systems. It attaches observers to your Pipecat workers to capture and stream frame events, job flows, and bus messages to a graphical interface where you can browse the entire system topology, inspect individual pipelines, filter and trace frames through processors, and save sessions for later replay. The debugger runs as a WebSocket server (default localhost:9090) that the UI connects to—either a hosted version via ngrok tunneling or a local Node.js development server.

You integrate Whisker by adding a WhiskerServer instance and per-worker WhiskerObserver objects to your Pipecat runner, or by using environment-variable-driven setup files to avoid modifying application code. For CI and headless recording, you can use WhiskerFile instead to write events directly to disk without opening a port. The package is designed as a trace-logging tool with a UI layer, letting you see exactly what every part of a distributed Pipecat system is doing at any moment.

Use it for:

- Debug message flow and frame routing through complex multi-worker Pipecat pipelines during development
- Inspect job queues and worker state to diagnose deadlocks or unexpected behavior in live systems
- Record and replay Pipecat sessions for post-mortem analysis or sharing debugging context with teammates
- Monitor frame processing in real-time to identify bottlenecks or processors consuming unexpected input
- Capture headless Pipecat runs in CI/testing environments by writing events to disk without UI overhead

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Whisker is a real-time debugger for Pipecat voice and multimodal AI applications that lets you inspect workers, pipelines, jobs, and message flow across a multi-agent system through a graphical UI.

Yes, if you are actively developing or debugging Pipecat applications. The package is actively maintained, has no known vulnerabilities, installs with low friction, and provides a purpose-built debugging interface for a framework that otherwise lacks built-in introspection. The permissive BSD-2-Clause license poses no restrictions. Install it as a development dependency; the overhead of observers is negligible for debugging but can be disabled in production.

## Install

pip install pipecat-ai-whisker
uv add pipecat-ai-whisker
poetry add pipecat-ai-whisker

## Installing pipecat-ai-whisker

Before you install: Low friction install with a pure-Python wheel. Requires Python 3.11+ and an active Pipecat installation; the package itself has only six runtime dependencies (aiofiles, idna, loguru, msgpack, pipecat-ai, websockets). Actively maintained with recent releases.

License in practice: BSD-2-Clause is permissive and imposes minimal restrictions on use or redistribution; you can incorporate this into commercial or proprietary projects without licensing concerns.

Quickstart:

pip install pipecat-ai-whisker

from pipecat_ai_whisker import WhiskerServer
from pipecat import PipelineWorker, WorkerRunner

whisker = WhiskerServer()
worker.add_observer(whisker.create_observer(worker))
await runner.add_workers(whisker, worker)
await runner.run()

Requires Python 3.11+, an installed Pipecat framework, and Node.js 20+ if running the UI locally. The hosted UI also requires ngrok for local tunneling.

Verify before relying:

- Whether the package works with Pipecat versions other than the latest, or version constraints on pipecat-ai dependency
- Performance overhead of Whisker observers on frame throughput in production-scale pipelines
- Whether saved .whisk session files are forward/backward compatible across Whisker versions

## Package facts

- License: BSD-2-Clause (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 112.0K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

pipecat debugger, ai pipeline debugging, multimodal conversational ai debug, worker inspection tool, message bus tracing, frame flow visualization, pipecat monitoring, pipecat-ecosystem, debugging-ui, multi-agent-systems

[View on SkillFed](https://skillfed.io/packages/pipecat-ai-whisker) · [View on PyPI](https://pypi.org/project/pipecat-ai-whisker/)