Public record
Software health reportschema 0.31.0 · metrics 2.10.0 · 2026-08-12 22:24 UTC

NVIDIA-NeMo / Guardrails

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

PythonCustom license★ 6,930 stars⑂ 804 forkssince Apr 2023View on GitHub ↗
KindCommand-line toolLibraryhow this is determined
#agents#guardrails#python#safety#generative-ai#llms#nvidia#llm-safety#llm-security

NVIDIA-NeMo/Guardrails holds a health index of 98 out of 100, placing it in the Exceptional band. It scores highest on Vitality (99/100) and lowest on Security (74/100). It was last updated today. 2 contributors account for most of its recent work.

98
overall / 100
Exceptional

Software health index

Metrics are grouped into weighted categories on one standardized 1–100 scale. Overall starts as their weighted mean, calibrated against the distribution of the public record so bands carry percentile meaning; when public evidence triggers the High-Risk Jurisdiction Policy, the rating is adjusted and receives an At Risk ceiling of 34.

98
Exceptional93-100The record's top tier (≈ top 5%); essentially all checked criteria met
Excellent80-92Strong across the board; minor gaps
Good65-79Healthy; gaps are limited and manageable
Moderate50-64Acceptable with notable gaps; review recommended
Weak35-49Material weaknesses across several areas
At Risk20-34Significant weaknesses; adoption warrants caution
Critical1-19Severe problems (abandoned, single-maintainer, no hygiene)
VitalityCommunity &AdoptionSustainability &GovernanceEngineeringQualitySecurityAI Readiness

Score profile

Each axis is a category. The shape matters more than the average — a healthy subject fills the whole shape, while a spike-and-crater profile means strength in one dimension is masking risk in another.

The weighted overall 86 is calibrated to 98 on the published index scale (record calibration 2026-08-02).

Ownership

NVIDIA-NeMoOrganization
1,592 followers28 public repossince May 2025

This repository is backed by an organization — shared, accountable stewardship that can outlive any single maintainer.

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publish
PyPInemoguardrails0.23.0394,7903342 days ago

Metrics by category

Vitality

Is the project alive — is code being written and are releases shipping?

99Exceptional · 21% of overall

Development activity

99Exceptional
How it's scored
36/36Push recency — last push 0 days ago
34.6/36Commit cadence — 50/52 weeks with commits
18/18Commit volume — 512 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 10 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year512
human_commit_share0.95
days_since_last_push0
active_weeks_last_year50

Release discipline

100Exceptional
How it's scored
27/27Ships releases — 32 releases published
36/36Release recency — latest release 42 days ago
27/27Release cadence — a release every ~39.8 days
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count32
latest_release_tagv0.23.0
releases_from_tagsno
days_since_latest_release42
mean_days_between_releases39.8
Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.

Community & Adoption

Does the project have users, downloads, attention, and a welcoming setup for contributors?

85Excellent · 17% of overall

Popularity & adoption

93Exceptional
How it's scored
60/60Stars — 6,930 stars
24.2/25Forks — 804 forks
9/15Watchers — 42 watchers
Inputs used
forks804
stars6,930
watchers42
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

Community health

71Good
How it's scored
22.5/22.5README
16.9/22.5License — license file present, not a recognized license
18/18CONTRIBUTING guide
0/13.5Code of conduct
0/7.2Issue template
6.3/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges10
has_contributingyes
has_issue_templateno
has_code_of_conductno
readme_badge_servicesshields.io
has_pull_request_templateyes

Ecosystem adoption (downloads)

93Exceptional
How it's scored
74.6/80Monthly downloads — 394,790 downloads/month across pypi
0/20Registry dependents — not reported by this ecosystem
Inputs used
packagesnemoguardrails
dependents—
ecosystemspypi
total_downloads—
monthly_downloads394,790
unverified_packages_excluded—
Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.

Sustainability & Governance

Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?

76Good · 23% of overall

Maintainer resilience (bus factor)

64Moderate
How it's scored
25.2/54Bus factor — 2 contributor(s) cover half of all commits
15.6/22.5Commit distribution — top contributor authored 31% of commits
13.5/13.5Contributor breadth — 98 contributors
10/10OpenSSF Scorecard: Contributors — project has 17 contributing companies or organizations
Inputs used
bus_factor2
contributors_sampled98
top_contributor_share0.308

Issue & PR responsiveness

66Good
How it's scored
32.6/42Issue resolution — 78% of issues closed
22/30PR acceptance — 1,022/1,391 decided PRs merged
1.1/13Newcomer PR acceptance — 1/12 first-time contributors' PRs merged in 30d
10.5/15OpenSSF Scorecard: Code-Review — Found 23/30 approved changesets -- score normalized to 7
Inputs used
merged_prs1,022
open_issues134
closed_issues462
prs_merged_7d5
prs_decided_7d6
prs_merged_30d43
prs_decided_30d59
issue_closed_ratio0.775
closed_unmerged_prs369
first_time_authors_30d4
first_time_prs_merged_30d1
first_time_prs_decided_30d12

Ownership & stewardship

83Excellent
How it's scored
30/30Ownership backing — organization-owned
0/20Verified domain — verified-domain status not read for this organization
23/25Owner reach — 1,592 followers of NVIDIA-NeMo
13.1/25Track record — 28 public repos, account ~1 yr old
Inputs used
followers1,592
owner_typeOrganization
is_verified—
owner_loginNVIDIA-NeMo
public_repos28
account_age_days442
Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 1 package(s) on pypi
35/35Publish recency — latest publish 42 days ago
20/20Version history — 33 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagesnemoguardrails
ecosystemspypi
any_deprecatedno
min_days_since_publish42

Engineering Quality

Are baseline engineering and documentation practices in place?

96Exceptional · 19% of overall

Engineering practices

94Exceptional
How it's scored
24/24CI workflows — 30 workflow(s)
24/24Tests present
16/16Linter config — ruff.toml
9.6/9.6Pre-commit hooks
0/6.4.editorconfig
20/20OpenSSF Scorecard: CI-Tests — 30 out of 30 merged PRs checked by a CI test -- score normalized to 10
Inputs used
has_ciyes
has_testsyes
has_editorconfigno
has_linter_configyes
has_precommit_configyes

Documentation

100Exceptional
How it's scored
30/30README
25/25Documentation directory
15/15Documentation / homepage site — https://docs.nvidia.com/nemo/guardrails/latest/index.html
10/10Repository description
10/10Topics — 9 topics
10/10Wiki
Inputs used
topicsagents, guardrails, python, safety, generative-ai, llms, nvidia, llm-safety, llm-security
has_wikiyes
homepagehttps://docs.nvidia.com/nemo/guardrails/latest/index.html
docs_sitehttps://docs.nvidia.com/nemo/guardrails/latest/index.html
has_readmeyes
has_docs_diryes
has_descriptionyes

Security

Are visible security and supply-chain practices strong, without unresolved high-risk jurisdiction exposure?

74Good · 16% of overall

Security posture

68Good
How it's scored
7.5/7.5Binary-Artifacts — no binaries found in the repo
0/7.5Branch-Protection — no data
2.5/2.5CI-Tests — 30 out of 30 merged PRs checked by a CI test -- score normalized to 10
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
5.2/7.5Code-Review — Found 23/30 approved changesets -- score normalized to 7
2.5/2.5Contributors — project has 17 contributing companies or organizations
10/10Dangerous-Workflow — no dangerous workflow patterns detected
7.5/7.5Dependency-Update-Tool — update tool detected
0/5Fuzzing — project is not fuzzed
2.2/2.5License — license file detected
7.5/7.5Maintained — 30 commit(s) and 10 issue activity found in the last 90 days -- score normalized to 10
5/5Packaging — packaging workflow detected
1/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 2
5/5SAST — SAST tool is run on all commits
5/5Security-Policy — security policy file detected
0/7.5Signed-Releases — no data
0/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
0/7.5Vulnerabilities — 41 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated16
scorecard_versionv5.5.0
checks_inconclusive2
scorecard_aggregate6.8
Excluded from scoring (no data or not applicable): Branch-Protection, Signed-Releases. Remaining weights renormalized.

Dependency advisories

100Exceptional
How it's scored
35/35Direct dependencies free of known advisories — no direct dependency carries a known advisory
25/25Indirect dependencies free of known advisories — no indirect dependency carries a known advisory
0/40No advisories left outstanding — no advisory carries a publication date
Inputs used
sourceosv
advisories0
affected_packages0
assessed_packages53
unassessed_packages0
affected_by_severitynone
direct_affected_packages0
Excluded from scoring (no data or not applicable): No advisories left outstanding. Remaining weights renormalized. Matched the pypi:nemoguardrails@0.23.0 runtime dependency closure — what installing the published package pulls in — 53 packages. Reachability is not analyzed.

AI Readiness

How well is the repo equipped to be developed and maintained with AI coding agents? Carries a deliberately small weight (4%): agent tooling is a real maintenance signal, but a repository with none can still reach 100/100.

78Good · 4% of overall

Agent context & guidance

85Excellent
How it's scored
45/45Agent instructions — AGENTS.md, CLAUDE.md, docs/AGENTS.md, nemoguardrails/AGENTS.md, nemoguardrails/CLAUDE.md
0/15Machine-readable docs (llms.txt)
40/40Legible commit history — 95 of 95 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtno
llms_txt_url—
legible_history_share1
agent_instruction_filesAGENTS.md, CLAUDE.md, docs/AGENTS.md, nemoguardrails/AGENTS.md, nemoguardrails/CLAUDE.md
agent_instruction_max_bytes10,507

Verify loop (build / test / typecheck)

73Good
How it's scored
18/18One-command bootstrap — Makefile
22/22Automated tests
11/11Lint / format config — ruff.toml
0/11Static type checking
10/10Reproducible environment — devcontainer, Dockerfile, lockfile
2/10Demonstrated agent practice — 1 of the last 100 commits agent-authored or agent-credited
8/8Automated maintenance — 4 of the last 100 commits are automated dependency updates
2/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 2
Inputs used
has_nixno
has_testsyes
lockfilespackage-lock.json, uv.lock
has_dockerfileyes
typed_languageno
bootstrap_filesMakefile
has_devcontaineryes
has_linter_configyes
typecheck_configs—
agent_commit_share0.01
toolchain_manifests—
dependency_bot_commit_share0.04

Code legibility for models

54Moderate
How it's scored
0/45Type-checkable code — Python without a type-check config
54.3/55Manageable file sizes — 12/937 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes122,529
source_files_sampled937
oversized_source_files12

Machine-readable interfaces

100Exceptional
How it's scored
40/40API schema (OpenAPI/GraphQL/proto) — fern/openapi.yml
0/20MCP server — not applicable to this kind of software
40/40Runnable examples — examples, notebooks, sample
Inputs used
example_dirsexamples, notebooks, sample
has_mcp_signalno
api_schema_filesfern/openapi.yml
interfaces_expected_of—
Excluded from scoring (no data or not applicable): MCP server. Remaining weights renormalized.

Key facts

6,930GitHub stars
98contributors
512commits, last 12 months
0days since last push
32releases
2bus factor
134open issues
npm, PyPIpackage ecosystems

Data collection warnings

  • Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token

More detail

Star and fork history 0 ★ / 804 ⇿
0Stars
804Forks
32Releases

When each star and fork was added, collected from GitHub and bucketed by day. Cumulative growth sits directly above the daily additions it is made of, so the two read against each other: steady organic accretion looks nothing like an abrupt, short-lived burst. Where that difference is measurable, it is reported as growth authenticity.

0200400600800778352023-042024-122026-08
Major 0Minor 22Patch 9

Each point covers 4 days.

OpenSSF Scorecard 6.8 / 10
6.8aggregate

Independent, tool-agnostic security assessment from the open-source OpenSSF Scorecard. Each check rewards a security practice, not a specific vendor's tool. Checks Scorecard could not determine are marked n/a and excluded from the security score (never counted as zero).Scorecard v5.5.0 · 2026-08-12 22:24 UTC

10Binary-Artifactsno binaries found in the repo
n/aBranch-Protectioninternal error: error during branchesHandler.setup: internal error: some github tokens can't read classic branch protection rules: https://github.com/ossf/scorecard-action/blob/main/docs/authentication/fine-grained-auth-token.md
10CI-Tests30 out of 30 merged PRs checked by a CI test -- score normalized to 10
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
7Code-ReviewFound 23/30 approved changesets -- score normalized to 7
10Contributorsproject has 17 contributing companies or organizations
10Dangerous-Workflowno dangerous workflow patterns detected
10Dependency-Update-Toolupdate tool detected
0Fuzzingproject is not fuzzed
9Licenselicense file detected
10Maintained30 commit(s) and 10 issue activity found in the last 90 days -- score normalized to 10
10Packagingpackaging workflow detected
2Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 2
10SASTSAST tool is run on all commits
10Security-Policysecurity policy file detected
n/aSigned-Releasesno releases found
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
0Vulnerabilities41 existing vulnerabilities detected
Direct dependencies 22
RegistryPackageVersion constraintManifest
npmyaml^2.9.0package.json
PyPIaiohttp(>=3.10.11)pyproject.toml
PyPIaiohttp-retry(>=2.9.0)pyproject.toml
PyPIdataclasses-json(>=0.6.7,<0.7.0)pyproject.toml
PyPIfastembed(>=0.2.2)pyproject.toml
PyPIonnxruntime(>=1.17.0,<1.24)pyproject.toml
PyPIonnxruntime(>=1.17.0)pyproject.toml
PyPIhttpx(>=0.24.1)pyproject.toml
PyPIjinja2(>=3.1.6)pyproject.toml
PyPIjsonschema(>=4.26.0,<5.0.0)pyproject.toml
PyPIlark(>=1.1.7)pyproject.toml
PyPInest-asyncio(>=1.5.6)pyproject.toml
PyPInumpy(>=1.21)pyproject.toml
PyPInumpy(>=1.26)pyproject.toml
PyPInumpy(>=2.1.0)pyproject.toml
PyPIprompt-toolkit(>=3.0)pyproject.toml
PyPIprotobuf(>=5.29.5)pyproject.toml
PyPIpydantic(>=2.5,<3.0)pyproject.toml
PyPIpyyaml(>=6.0)pyproject.toml
PyPIrich(>=13.5.2)pyproject.toml
PyPIsimpleeval(>=0.9.13)pyproject.toml
PyPItyper(>=0.8)pyproject.toml
All dependencies 333

Full resolved dependency set from the GitHub dependency graph: 27 direct and 306 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
npmyaml2.9.0direct
PyPIaiohttp3.14.1direct
PyPIaiohttp-retry2.9.1direct
PyPIdataclasses-json0.6.7direct
PyPIfastembed0.8.0direct
PyPIhttpx—direct
PyPIhttpx0.28.1direct
PyPIjinja23.1.6direct
PyPIjsonschema4.26.0direct
PyPIlark1.3.1direct
PyPInest-asyncio1.6.0direct
PyPInumpy1.26.4direct
PyPInumpy2.2.6direct
PyPInumpy2.4.6direct
PyPInumpy2.5.0direct
PyPIonnxruntime—direct
PyPIonnxruntime1.23.2direct
PyPIonnxruntime1.27.0direct
PyPIprompt-toolkit3.0.52direct
PyPIprotobuf7.35.1direct
PyPIpydantic—direct
PyPIpydantic2.13.4direct
PyPIpyyaml6.0.3direct
PyPIrich15.0.0direct
PyPIsimpleeval1.0.7direct
PyPItyper—direct
PyPItyper0.26.8direct
PyPIaiofiles25.1.0indirect
PyPIaiohappyeyeballs2.6.2indirect
PyPIaioresponses0.7.9indirect
PyPIaiosignal1.4.0indirect
PyPIaltair6.2.2indirect
PyPIannotated-doc0.0.4indirect
PyPIannotated-types0.7.0indirect
PyPIanyio4.14.1indirect
PyPIasttokens3.0.1indirect
PyPIasync-timeout4.0.3indirect
PyPIasync-timeout5.0.1indirect
PyPIasyncer0.0.18indirect
PyPIattrs26.1.0indirect
PyPIaudioop-lts0.2.2indirect
PyPIbackports-asyncio-runner1.2.0indirect
PyPIbidict0.23.1indirect
PyPIblinker1.9.0indirect
PyPIblis1.3.3indirect
PyPIcachetools7.1.4indirect
PyPIcatalogue2.0.10indirect
PyPIcertifi2026.6.17indirect
PyPIcffi2.0.0indirect
PyPIcfgv3.5.0indirect
PyPIchainlit2.11.1indirect
PyPIcharset-normalizer3.4.7indirect
PyPIchevron0.14.0indirect
PyPIclick8.4.2indirect
PyPIcloudpathlib0.24.0indirect
PyPIcolorama0.4.6indirect
PyPIcoloredlogs15.0.1indirect
PyPIcolorlog6.10.1indirect
PyPIconfection1.3.3indirect
PyPIcoverage7.14.3indirect
PyPIcryptography46.0.7indirect
PyPIcryptography49.0.0indirect
PyPIcuda-bindings13.3.1indirect
PyPIcuda-pathfinder1.5.5indirect
PyPIcuda-toolkit13.0.2indirect
PyPIcuid0.4indirect
PyPIcymem2.0.13indirect
PyPIdeprecated1.3.1indirect
PyPIdistlib0.4.3indirect
PyPIdistro1.9.0indirect
PyPIeinops—indirect
PyPIexceptiongroup1.3.1indirect
PyPIexecnet2.1.2indirect
PyPIexecuting2.2.1indirect
PyPIfast-langdetect1.0.1indirect
PyPIfastapi—indirect
PyPIfastapi0.138.1indirect
PyPIfastapi0.138.2indirect
PyPIfasttext-predict0.9.2.4indirect
PyPIfilelock3.29.4indirect
PyPIfiletype1.2.0indirect
PyPIflatbuffers25.12.19indirect
PyPIfrozenlist1.8.0indirect
PyPIfsspec2026.6.0indirect
PyPIgitdb4.0.12indirect
PyPIgitpython3.1.50indirect
PyPIgliner—indirect
PyPIgoogle-api-core2.31.0indirect
PyPIgoogle-auth2.55.1indirect
PyPIgoogle-cloud-language2.21.0indirect
PyPIgoogleapis-common-protos1.75.0indirect
PyPIgprof2dot2025.4.14indirect
PyPIgreenlet3.5.3indirect
PyPIgrpcio1.81.1indirect
PyPIgrpcio-status1.81.1indirect
PyPIh110.16.0indirect
PyPIhf-xet1.5.1indirect
PyPIhttpcore1.0.9indirect
PyPIhttptools0.8.0indirect
PyPIhttpx-sse0.4.3indirect
PyPIhuggingface-hub—indirect
PyPIhuggingface-hub1.16.1indirect
PyPIhumanfriendly10.0indirect
PyPIidentify2.6.19indirect
PyPIidna3.18indirect
PyPIinflection0.5.1indirect
PyPIiniconfig2.3.0indirect
PyPIinline-snapshot0.33.0indirect
PyPIitsdangerous2.2.0indirect
PyPIjiter0.15.0indirect
PyPIjiter0.16.0indirect
PyPIjsonpatch1.33indirect
PyPIjsonpointer3.1.1indirect
PyPIjsonschema-specifications2025.9.1indirect
PyPIlangchain1.3.11indirect
PyPIlangchain-classic1.0.8indirect
PyPIlangchain-community0.3.31indirect
PyPIlangchain-community0.4.2indirect
PyPIlangchain-core1.4.8indirect
PyPIlangchain-nvidia-ai-endpoints1.4.1indirect
PyPIlangchain-openai1.3.3indirect
PyPIlangchain-protocol0.0.18indirect
PyPIlangchain-text-splitters1.1.2indirect
PyPIlanggraph1.2.6indirect
PyPIlanggraph1.2.7indirect
PyPIlanggraph-checkpoint4.1.1indirect
PyPIlanggraph-prebuilt1.1.0indirect
PyPIlanggraph-sdk0.4.2indirect
PyPIlangsmith0.9.3indirect
PyPIlangsmith0.9.4indirect
PyPIlazify0.4.0indirect
PyPIliteralai0.1.201indirect
PyPIloguru0.7.3indirect
PyPImarkdown-it-py3.0.0indirect
PyPImarkupsafe3.0.3indirect
PyPImarshmallow3.26.2indirect
PyPImcp1.28.1indirect
PyPImdurl0.1.2indirect
PyPImmh35.2.1indirect
PyPImpmath1.3.0indirect
PyPImultidict6.7.1indirect
PyPImurmurhash1.0.15indirect
PyPImypy-extensions1.1.0indirect
PyPInarwhals2.22.1indirect
PyPInarwhals2.23.0indirect
PyPInemoguardrails0.24.0.dev0indirect
PyPInetworkx3.4.2indirect
PyPInodeenv1.10.0indirect
PyPInvidia-cublas13.1.1.3indirect
PyPInvidia-cuda-cupti13.0.85indirect
PyPInvidia-cuda-nvrtc13.0.88indirect
PyPInvidia-cuda-runtime13.0.96indirect
PyPInvidia-cudnn-cu139.20.0.48indirect
PyPInvidia-cufft12.0.0.61indirect
PyPInvidia-cufile1.15.1.6indirect
PyPInvidia-curand10.4.0.35indirect
PyPInvidia-cusolver12.0.4.66indirect
PyPInvidia-cusparse12.6.3.3indirect
PyPInvidia-cusparselt-cu130.8.1indirect
PyPInvidia-nccl-cu132.29.7indirect
PyPInvidia-nvjitlink13.0.88indirect
PyPInvidia-nvshmem-cu133.4.5indirect
PyPInvidia-nvtx13.0.85indirect
PyPIopenai2.44.0indirect
PyPIopentelemetry-api1.43.0indirect
PyPIopentelemetry-exporter-otlp-proto-common1.43.0indirect
PyPIopentelemetry-exporter-otlp-proto-grpc1.43.0indirect
PyPIopentelemetry-exporter-otlp-proto-http1.43.0indirect
PyPIopentelemetry-instrumentation0.64b0indirect
PyPIopentelemetry-instrumentation-agno0.62.1indirect
PyPIopentelemetry-instrumentation-alephalpha0.62.1indirect
PyPIopentelemetry-instrumentation-anthropic0.62.1indirect
PyPIopentelemetry-instrumentation-bedrock0.62.1indirect
PyPIopentelemetry-instrumentation-chromadb0.62.1indirect
PyPIopentelemetry-instrumentation-cohere0.62.1indirect
PyPIopentelemetry-instrumentation-crewai0.62.1indirect
PyPIopentelemetry-instrumentation-google-generativeai0.62.1indirect
PyPIopentelemetry-instrumentation-groq0.62.1indirect
PyPIopentelemetry-instrumentation-haystack0.62.1indirect
PyPIopentelemetry-instrumentation-lancedb0.62.1indirect
PyPIopentelemetry-instrumentation-langchain0.62.1indirect
PyPIopentelemetry-instrumentation-litellm0.1.0indirect
PyPIopentelemetry-instrumentation-llamaindex0.62.1indirect
PyPIopentelemetry-instrumentation-logging0.64b0indirect
PyPIopentelemetry-instrumentation-marqo0.62.1indirect
PyPIopentelemetry-instrumentation-mcp0.62.1indirect
PyPIopentelemetry-instrumentation-milvus0.60.0indirect
PyPIopentelemetry-instrumentation-mistralai0.62.1indirect
PyPIopentelemetry-instrumentation-ollama0.62.1indirect
PyPIopentelemetry-instrumentation-openai0.62.1indirect
PyPIopentelemetry-instrumentation-openai-agents0.62.1indirect
PyPIopentelemetry-instrumentation-pinecone0.60.0indirect
PyPIopentelemetry-instrumentation-qdrant0.62.1indirect
PyPIopentelemetry-instrumentation-redis0.64b0indirect
PyPIopentelemetry-instrumentation-replicate0.62.1indirect
PyPIopentelemetry-instrumentation-requests0.64b0indirect
PyPIopentelemetry-instrumentation-sagemaker0.62.1indirect
PyPIopentelemetry-instrumentation-sqlalchemy0.64b0indirect
PyPIopentelemetry-instrumentation-threading0.64b0indirect
PyPIopentelemetry-instrumentation-together0.62.1indirect
PyPIopentelemetry-instrumentation-transformers0.62.1indirect
PyPIopentelemetry-instrumentation-urllib30.64b0indirect
PyPIopentelemetry-instrumentation-vertexai0.62.1indirect
PyPIopentelemetry-instrumentation-voyageai0.62.1indirect
PyPIopentelemetry-instrumentation-watsonx0.62.1indirect
PyPIopentelemetry-instrumentation-weaviate0.62.1indirect
PyPIopentelemetry-instrumentation-writer0.62.1indirect
PyPIopentelemetry-proto1.43.0indirect
PyPIopentelemetry-sdk1.43.0indirect
PyPIopentelemetry-semantic-conventions0.64b0indirect
PyPIopentelemetry-semantic-conventions-ai0.5.1indirect
PyPIopentelemetry-util-http0.64b0indirect
PyPIorjson3.11.9indirect
PyPIormsgpack1.12.2indirect
PyPIpackaging26.2indirect
PyPIpandas2.3.3indirect
PyPIphonenumbers9.0.33indirect
PyPIpillow12.2.0indirect
PyPIpillow12.3.0indirect
PyPIplatformdirs4.10.0indirect
PyPIpluggy1.6.0indirect
PyPIpre-commit4.6.0indirect
PyPIpreshed3.0.13indirect
PyPIpresidio-analyzer2.2.362indirect
PyPIpresidio-analyzer2.2.363indirect
PyPIpresidio-anonymizer2.2.362indirect
PyPIpresidio-anonymizer2.2.363indirect
PyPIpropcache0.5.2indirect
PyPIproto-plus1.28.0indirect
PyPIpy-rust-stemmers0.1.8indirect
PyPIpyarrow24.0.0indirect
PyPIpyasn10.6.3indirect
PyPIpyasn1-modules0.4.2indirect
PyPIpycparser3.0indirect
PyPIpydantic-core2.46.4indirect
PyPIpydantic-settings2.14.2indirect
PyPIpydeck0.9.2indirect
PyPIpygments2.20.0indirect
PyPIpyjwt2.13.0indirect
PyPIpyproject-api1.10.1indirect
PyPIpyreadline33.5.6indirect
PyPIpyright1.1.411indirect
PyPIpytest—indirect
PyPIpytest8.4.2indirect
PyPIpytest9.1.1indirect
PyPIpytest-asyncio0.26.0indirect
PyPIpytest-asyncio1.4.0indirect
PyPIpytest-cov7.1.0indirect
PyPIpytest-httpx0.35.0indirect
PyPIpytest-httpx0.36.2indirect
PyPIpytest-profiling1.8.1indirect
PyPIpytest-recording0.13.4indirect
PyPIpytest-xdist3.8.0indirect
PyPIpython-dateutil2.9.0.post0indirect
PyPIpython-discovery1.4.2indirect
PyPIpython-dotenv1.2.2indirect
PyPIpython-engineio4.13.3indirect
PyPIpython-multipart0.0.32indirect
PyPIpython-socketio5.16.3indirect
PyPIpytz2026.2indirect
PyPIpywin32312indirect
PyPIreferencing0.37.0indirect
PyPIregex2026.6.28indirect
PyPIrequests2.34.2indirect
PyPIrequests-file3.0.1indirect
PyPIrequests-toolbelt1.0.0indirect
PyPIrobust-downloader0.0.2indirect
PyPIrpds-py0.30.0indirect
PyPIrpds-py2026.6.3indirect
PyPIruff0.14.6indirect
PyPIsafetensors0.8.0indirect
PyPIsetuptools81.0.0indirect
PyPIshellingham1.5.4indirect
PyPIsimple-websocket1.1.0indirect
PyPIsix1.17.0indirect
PyPIsmart-open8.0.0indirect
PyPIsmmap5.0.3indirect
PyPIsniffio1.3.1indirect
PyPIspacy3.8.13indirect
PyPIspacy3.8.14indirect
PyPIspacy-legacy3.0.12indirect
PyPIspacy-loggers1.0.5indirect
PyPIsqlalchemy2.0.51indirect
PyPIsrsly2.5.3indirect
PyPIsse-starlette3.4.5indirect
PyPIstarlette—indirect
PyPIstarlette1.3.1indirect
PyPIstreamlit1.58.0indirect
PyPIsympy1.14.0indirect
PyPIsyncer2.0.3indirect
PyPItenacity9.1.4indirect
PyPIthinc8.3.13indirect
PyPItiktoken0.13.0indirect
PyPItldextract5.3.1indirect
PyPItokenizers0.22.2indirect
PyPItoml0.10.2indirect
PyPItomli2.4.1indirect
PyPItomli-w1.2.0indirect
PyPItorch—indirect
PyPItorch2.12.1indirect
PyPItorchvision—indirect
PyPItornado6.5.7indirect
PyPItox4.56.1indirect
PyPItqdm4.68.3indirect
PyPItraceloop-sdk0.62.1indirect
PyPItransformers—indirect
PyPItransformers5.12.1indirect
PyPItriton3.7.1indirect
PyPIty0.0.56indirect
PyPItyping-extensions4.15.0indirect
PyPItyping-inspect0.9.0indirect
PyPItyping-inspection0.4.2indirect
PyPItzdata2026.2indirect
PyPIurllib32.7.0indirect
PyPIuuid-utils0.16.2indirect
PyPIuvicorn—indirect
PyPIuvicorn0.49.0indirect
PyPIvcrpy8.2.1indirect
PyPIvirtualenv21.5.1indirect
PyPIwasabi1.1.3indirect
PyPIwatchdog6.0.0indirect
PyPIwatchfiles1.2.0indirect
PyPIwcwidth0.8.1indirect
PyPIwcwidth0.8.2indirect
PyPIweasel1.0.0indirect
PyPIwebsockets15.0.1indirect
PyPIwin32-setctime1.2.0indirect
PyPIwrapt2.2.2indirect
PyPIwsproto1.3.2indirect
PyPIxxhash3.8.0indirect
PyPIyara-python4.5.4indirect
PyPIyarl1.24.2indirect
PyPIzstandard0.25.0indirect
Dependency advisories 0

Installing pypi:nemoguardrails@0.23.0 pulls in 53 packages, direct and transitive: 0 carry known advisories, of which 0 are direct dependencies.

No known advisories affect the assessed dependencies.

An advisory means the version recorded in the dependency graph falls inside an advisory’s affected range. Reachability is not analysed, and the graph includes development and test pins — a finding may concern tooling rather than shipped software.

Raw JSON report machine-readable

Feedback

Spotted something off in this report, or have thoughts to share? Wrong measurements, missed tooling, ideas, questions — anything is welcome. Every message is read and gets a response.

The message is kept through sign-in.

Related records

Inspected repositories sharing catalogue tags or ecosystems with NVIDIA-NeMo/Guardrails. Read them side by side →

100deepset-ai/haystackOpen-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.Exceptional99IBM/mcp-context-forgeAn AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.Exceptional97strands-agents/harness-sdkBuild an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.Exceptional99langchain-ai/langgraphBuild resilient agents.Exceptional98Netflix/metaflowBuild, Manage and Deploy AI/ML SystemsExceptional98langchain-ai/langchainThe agent engineering platform.Exceptional

Scores are signals, not warranties. They reflect publicly visible practices on GitHub — not a code audit, and not a security guarantee.

Missing data is excluded and weights renormalized, never scored as zero. Methodology is versioned and open: metrics v2.10.0, schema v0.31.0 — full methodology · metrics wiki.

How one result sits in the wider record: aggregate statistics — PyPI.