Skip to main content

pipecat-guardrails

Output guardrails for Pipecat voice agents. It checks what your bot is about to say, and stops it before it is spoken.

Status: early development. Version 0.0.1 contains the package structure only, with no guardrails yet. Follow the repo for the first usable release (0.1.0).

The problem

Pipecat has no built-in output guardrail, so every team writes its own processor between the LLM and the TTS. These homemade processors tend to break on user interruptions, keep speaking after a violation, let blocked text into the LLM history, and miss paraphrases and Hindi/Hinglish text.

This package will provide one processor you add to your pipeline:

pipeline = Pipeline([
    transport.input(), stt, context_aggregator.user(), llm,
    OutputGuardProcessor(guard),   # checks each sentence before it is spoken
    tts, transport.output(), context_aggregator.assistant(),
])

There will also be a plain await guard.check(text) for apps that run their own LLM loop.

See BEFORE_AFTER.md for a side-by-side comparison and PLAN.md for the design and roadmap.

Install

pip install pipecat-guardrails          # includes Pipecat
pip install "pipecat-guardrails[jev]"   # also installs the TypeSafe Jev classifier client

Requires Python 3.11+ and Pipecat 1.12 or later (installed automatically).

How checking works

Each sentence goes through up to three layers, and stops at the first one that is sure:

  1. Banned words, PII, regex: local and instant.
  2. Classifier model (optional), such as TypeSafe Jev: a fast yes/no model with an API key. A confident answer decides; an unsure one moves to layer 3.
  3. LLM judge (optional): any OpenAI-compatible LLM gives the final answer.

Layers 2 and 3 use Pipecat's own classifiers (pipecat.classifiers), so any classifier Pipecat supports works here.

Development

uv sync                      # create .venv with dev tools
uv run pytest                # tests
uv run ruff check .          # lint
uv run ruff format .         # format
uv run pyright               # type check
uv run pre-commit install    # run the checks on every commit

License

BSD-2-Clause, the same as Pipecat.

Metadata

Release files for pipecat-guardrails 0.0.1

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

Source distribution (sdist)

Source distribution for pipecat-guardrails 0.0.1
File Size Uploaded Provenance Actions
pipecat_guardrails-0.0.1.tar.gz 4.2 kB With provenance Details for pipecat_guardrails-0.0.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for pipecat-guardrails 0.0.1
File Interpreter ABI Platform Actions
pipecat_guardrails-0.0.1-py3-none-any.whl Python 3 none any Details for pipecat_guardrails-0.0.1-py3-none-any.whl

Total release size: 8.2 kB

Release files / pipecat_guardrails-0.0.1.tar.gz

Download URL pipecat_guardrails-0.0.1.tar.gz
Size 4.2 kB
Tags Source
SHA-256 checksum
How to use checksums
f472fca6e90553a1fd346e6e06daad9c8b74defb5626b9f1d56fce6ab416b98c
BLAKE2b-256 checksum
How to use checksums
d67f29ee8941f62cc8a606437bb69afce6462bcb2c0b1c3124768121ae6243e3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Oct 30, 2026.

Transparency log

Release files / pipecat_guardrails-0.0.1-py3-none-any.whl

Download URL pipecat_guardrails-0.0.1-py3-none-any.whl
Size 3.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
342317a5131d9a9606683b59f40060fb61613b1b1576b89b572b056691086a01
BLAKE2b-256 checksum
How to use checksums
50c2593ba7188c071605524d651eb5450d56e2490e8c6085e59c23d093289d78
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Oct 30, 2026.

Transparency log

Security for pipecat-guardrails 0.0.1

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 pipecat_guardrails-0.0.1.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 Oct 30, 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.

Release history Release notifications | RSS feed

This release

0.0.1 This release

2 release files Full 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