NeMo Guardrails

license

Apache-2.0(OSI)

source

public(full Python implementation)

self-host

yes(library/CLI/Docker/server)

service

none

core-gated

ungated

Fully open source: Apache-2.0, complete source, self-hostable with no proprietary tier. Two details are worth recording. The repo now lives at NVIDIA-NeMo/Guardrails, and GitHub's own metadata reports the license as NOASSERTION rather than Apache-2.0 - a quirk of how the LICENSE file is detected rather than a relicense, since the README states in as many words that 'the NeMo Guardrails library is licensed under the Apache License, Version 2.0'.

• https://github.com/NVIDIA/NeMo-Guardrails recorded 2026-08-13

  Redirects to NVIDIA-NeMo/Guardrails. README states 'The NeMo Guardrails library is licensed under the Apache License, Version 2.0' and describes it as 'an open-source toolkit for easily adding programmable guardrails to LLM-based conversational applications', installable and runnable yourself. Repo metadata reports spdxId NOASSERTION, which is GitHub failing to classify the file rather than a different license. No enterprise directory, commercial edition or license key on the page.

401,369 downloads in the trailing 30 days for the PyPI package `nemoguardrails`, which bands at 100K-1M, level 3. The package is the product's own rather than a same-named stranger - its PyPI project URLs point at https://github.com/NVIDIA-NeMo/Guardrails - and for a Python library PyPI is the primary distribution channel rather than a minority one, so downloads rather than GitHub stars are what the level rests on.

• https://pypistats.org/api/packages/nemoguardrails/recent recorded 2026-08-13

  last_month 401,369

One of the most feature-complete open guardrail orchestration layers; the Colang policy language adds flexibility beyond simple scanners, and two bands in this category are recorded relative to it.

• https://github.com/NVIDIA/NeMo-Guardrails recorded 2026-08-13

  README describes programmable guardrails for LLM applications, with dialog rails operating on canonical-form messages via the Colang Guide, fact-checking and output moderation over retrieval pipelines, keeping an assistant on topic, and deciding whether an action should be executed - that is I/O moderation, dialog control, retrieval filtering and tool-use control.