Public record
Software health reportschema 0.11.0 · metrics 2.10.0 · 2026-07-17 00:55 UTC

langchain-ai / langchain-google

🦜🔗 LangChain interfaces to Google's suite of AI products (e.g. Gemini & Vertex AI)

Python · Jupyter NotebookMIT★ 392 stars⑂ 458 forkssince Feb 2024View on GitHub ↗
#ai#gemini#gemini-api#langchain#langchain-python#llm#vertex-ai

langchain-ai/langchain-google holds a health index of 93 out of 100, placing it in the Exceptional band. It scores highest on Vitality (99/100) and lowest on Security (62/100). It was last updated today. 3 contributors account for most of its recent work.

93
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.

93
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 79 is calibrated to 93 on the published index scale (record calibration 2026-08-02).

Ownership

LangChainOrganization
20,912 followers251 public repossince Mar 2023

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

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
35.3/36Commit cadence — 51/52 weeks with commits
18/18Commit volume — 460 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 2 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year460
human_commit_share—
days_since_last_push0
active_weeks_last_year51

Release discipline

100Exceptional
How it's scored
27/27Ships releases — 100 releases published
36/36Release recency — latest release 10 days ago
27/27Release cadence — a release every ~9.1 days
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count100
latest_release_taglibs/genai/v4.2.7
releases_from_tagsno
days_since_latest_release10
mean_days_between_releases9.1
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?

80Excellent · 17% of overall

Popularity & adoption

69Good
How it's scored
42/60Stars — 392 stars
22.2/25Forks — 458 forks
4.7/15Watchers — 8 watchers
Inputs used
forks458
stars392
watchers8
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

Community health

92Excellent
How it's scored
22.5/22.5README
22.5/22.5License — recognized license (MIT)
18/18CONTRIBUTING guide
13.5/13.5Code of conduct
0/7.2Issue template
6.3/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges—
has_contributingyes
has_issue_templateno
has_code_of_conductyes
readme_badge_services—
has_pull_request_templateyes

Sustainability & Governance

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

80Excellent · 23% of overall

Maintainer resilience (bus factor)

77Good
How it's scored
36/54Bus factor — 3 contributor(s) cover half of all commits
17.8/22.5Commit distribution — top contributor authored 21% of commits
13.5/13.5Contributor breadth — 100 contributors
10/10OpenSSF Scorecard: Contributors — project has 11 contributing companies or organizations
Inputs used
bus_factor3
contributors_sampled100
top_contributor_share0.209

Issue & PR responsiveness

71Good
How it's scored
36.2/42Issue resolution — 86% of issues closed
25.7/30PR acceptance — 1,072/1,249 decided PRs merged
0/13Newcomer PR acceptance — no first-time contributor's PR decided in 30d
0/15OpenSSF Scorecard: Code-Review — Found 1/11 approved changesets -- score normalized to 0
Inputs used
merged_prs1,072
open_issues77
closed_issues476
prs_merged_7d—
prs_decided_7d—
prs_merged_30d—
prs_decided_30d—
issue_closed_ratio0.861
closed_unmerged_prs177
first_time_authors_30d—
first_time_prs_merged_30d—
first_time_prs_decided_30d—
Excluded from scoring (no data or not applicable): Newcomer PR acceptance. Remaining weights renormalized.

Ownership & stewardship

94Exceptional
How it's scored
30/30Ownership backing — organization-owned
0/20Verified domain — verified-domain status not read for this organization
25/25Owner reach — 20,912 followers of langchain-ai
19.8/25Track record — 251 public repos, account ~3 yr old
Inputs used
followers20,912
owner_typeOrganization
is_verified—
owner_loginlangchain-ai
public_repos251
account_age_days1,233
Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.

Engineering Quality

Are baseline engineering and documentation practices in place?

67Good · 19% of overall

Engineering practices

68Good
How it's scored
24/24CI workflows — 10 workflow(s)
24/24Tests present
0/16Linter config
0/9.6Pre-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_configno
has_precommit_configno

Documentation

65Good
How it's scored
30/30README
0/25Documentation directory
15/15Documentation / homepage site — https://docs.langchain.com/oss/python/integrations/providers/google
10/10Repository description
10/10Topics — 7 topics
0/10Wiki
Inputs used
topicsai, gemini, gemini-api, langchain, langchain-python, llm, vertex-ai
has_wikino
homepagehttps://docs.langchain.com/oss/python/integrations/providers/google
docs_sitehttps://docs.langchain.com/oss/python/integrations/providers/google
has_readmeyes
has_docs_dirno
has_descriptionyes

Security

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

62Moderate · 16% of overall

Security posture

62Moderate
How it's scored
7.5/7.5Binary-Artifacts — no binaries found in the repo
3.8/7.5Branch-Protection — branch protection is not maximal on development and all release branches
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
0/7.5Code-Review — Found 1/11 approved changesets -- score normalized to 0
2.5/2.5Contributors — project has 11 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
2.5/2.5License — license file detected
7.5/7.5Maintained — 30 commit(s) and 2 issue activity found in the last 90 days -- score normalized to 10
5/5Packaging — packaging workflow detected
2.5/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 5
4.5/5SAST — SAST tool is not run on all commits -- score normalized to 9
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 — 10 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated17
scorecard_versionv5.5.0
checks_inconclusive1
scorecard_aggregate6.2
Excluded from scoring (no data or not applicable): Signed-Releases. Remaining weights renormalized.

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.

81Excellent · 4% of overall

Agent context & guidance

75Good
How it's scored
45/45Agent instructions — AGENTS.md, CLAUDE.md
0/15Machine-readable docs (llms.txt)
0/40Legible commit history — no data
Inputs used
has_llms_txtno
llms_txt_url—
legible_history_share—
agent_instruction_filesAGENTS.md, CLAUDE.md
agent_instruction_max_bytes22,238
Excluded from scoring (no data or not applicable): Legible commit history. Remaining weights renormalized.

Verify loop (build / test / typecheck)

79Good
How it's scored
18/18One-command bootstrap — libs/community/Makefile, libs/genai/Makefile, libs/vertexai/Makefile
22/22Automated tests
0/11Lint / format config
11/11Static type checking — libs/genai/langchain_google_genai/py.typed, libs/vertexai/langchain_google_vertexai/py.typed
10/10Reproducible environment — lockfile
0/10Demonstrated agent practice — no data
5/8Automated maintenance — dependency automation configured, none observed in the sampled commits
5/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 5
Inputs used
has_nixno
has_testsyes
lockfilesuv.lock
has_dockerfileno
typed_languageno
bootstrap_fileslibs/community/Makefile, libs/genai/Makefile, libs/vertexai/Makefile
has_devcontainerno
has_linter_configno
typecheck_configslibs/genai/langchain_google_genai/py.typed, libs/vertexai/langchain_google_vertexai/py.typed
agent_commit_share—
toolchain_manifests—
dependency_bot_commit_share0
Excluded from scoring (no data or not applicable): Demonstrated agent practice. Remaining weights renormalized.

Code legibility for models

80Excellent
How it's scored
27/45Type-checkable code — Python with type-check config (libs/genai/langchain_google_genai/py.typed, libs/vertexai/langchain_google_vertexai/py.typed)
53.3/55Manageable file sizes — 7/231 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes214,397
source_files_sampled231
oversized_source_files7

Machine-readable interfaces

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

Key facts

392GitHub stars
100contributors
460commits, last 12 months
0days since last push
100releases
3bus factor
77open issues
—package ecosystems

More detail

OpenSSF Scorecard 6.2 / 10
6.2aggregate

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 · 2026-07-17 00:54 UTC

10Binary-Artifactsno binaries found in the repo
5Branch-Protectionbranch protection is not maximal on development and all release branches
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
0Code-ReviewFound 1/11 approved changesets -- score normalized to 0
10Contributorsproject has 11 contributing companies or organizations
10Dangerous-Workflowno dangerous workflow patterns detected
10Dependency-Update-Toolupdate tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
10Maintained30 commit(s) and 2 issue activity found in the last 90 days -- score normalized to 10
10Packagingpackaging workflow detected
5Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 5
9SASTSAST tool is not run on all commits -- score normalized to 9
10Security-Policysecurity policy file detected
n/aSigned-Releasesno releases found
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
0Vulnerabilities10 existing vulnerabilities detected
All dependencies 227

Full resolved dependency set from the GitHub dependency graph: 0 direct and 227 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPIaiohappyeyeballs2.6.1indirect
PyPIaiohttp3.14.1indirect
PyPIaiosignal1.4.0indirect
PyPIannotated-types0.7.0indirect
PyPIanthropic0.75.0indirect
PyPIanyio4.11.0indirect
PyPIanyio4.12.0indirect
PyPIanyio4.12.1indirect
PyPIast-serialize0.5.0indirect
PyPIasync-timeout4.0.3indirect
PyPIattrs25.4.0indirect
PyPIbackports-asyncio-runner1.2.0indirect
PyPIbeautifulsoup44.15.0indirect
PyPIbottleneck1.6.0indirect
PyPIcertifi2025.11.12indirect
PyPIcertifi2026.2.25indirect
PyPIcffi2.0.0indirect
PyPIcharset-normalizer3.4.4indirect
PyPIclick8.3.1indirect
PyPIcloudpickle3.1.2indirect
PyPIcolorama0.4.6indirect
PyPIcryptography48.0.1indirect
PyPIdb-dtypes1.7.0indirect
PyPIdistro1.9.0indirect
PyPIdocstring-parser0.17.0indirect
PyPIexceptiongroup1.3.0indirect
PyPIexceptiongroup1.3.1indirect
PyPIexecnet2.1.2indirect
PyPIfastapi—indirect
PyPIfilelock3.20.3indirect
PyPIfiletype1.2.0indirect
PyPIfreezegun1.5.5indirect
PyPIfrozenlist1.8.0indirect
PyPIfsspec2025.12.0indirect
PyPIfuture1.0.0indirect
PyPIgapic-google-longrunning0.11.2indirect
PyPIgoogle-api-core2.28.1indirect
PyPIgoogle-api-core2.31.0indirect
PyPIgoogle-api-python-client2.187.0indirect
PyPIgoogle-api-python-client2.198.0indirect
PyPIgoogle-auth2.48.0indirect
PyPIgoogle-auth2.52.0indirect
PyPIgoogle-auth2.55.1indirect
PyPIgoogle-auth-httplib20.2.1indirect
PyPIgoogle-auth-httplib20.4.0indirect
PyPIgoogle-auth-oauthlib1.4.0indirect
PyPIgoogle-cloud-aiplatform1.139.0indirect
PyPIgoogle-cloud-aiplatform1.159.0indirect
PyPIgoogle-cloud-bigquery—indirect
PyPIgoogle-cloud-bigquery3.38.0indirect
PyPIgoogle-cloud-bigquery3.42.1indirect
PyPIgoogle-cloud-bigquery-storage2.39.0indirect
PyPIgoogle-cloud-contentwarehouse0.11.0indirect
PyPIgoogle-cloud-core2.5.0indirect
PyPIgoogle-cloud-core2.6.0indirect
PyPIgoogle-cloud-datastore2.21.0indirect
PyPIgoogle-cloud-discoveryengine0.20.1indirect
PyPIgoogle-cloud-documentai3.15.0indirect
PyPIgoogle-cloud-modelarmor0.7.0indirect
PyPIgoogle-cloud-resource-manager1.15.0indirect
PyPIgoogle-cloud-speech2.40.0indirect
PyPIgoogle-cloud-storage3.12.0indirect
PyPIgoogle-cloud-storage3.6.0indirect
PyPIgoogle-cloud-texttospeech2.37.0indirect
PyPIgoogle-cloud-translate3.27.0indirect
PyPIgoogle-cloud-vectorsearch0.2.0indirect
PyPIgoogle-cloud-vision3.15.0indirect
PyPIgoogle-crc32c1.7.1indirect
PyPIgoogle-gax0.14.1indirect
PyPIgoogle-genai1.65.0indirect
PyPIgoogle-genai1.70.0indirect
PyPIgoogle-genai2.10.0indirect
PyPIgoogle-resumable-media2.7.2indirect
PyPIgoogle-resumable-media2.8.0indirect
PyPIgoogleapis-common-protos1.72.0indirect
PyPIgooglemaps4.10.0indirect
PyPIgrpc-google-iam-v10.14.3indirect
PyPIgrpcio1.76.0indirect
PyPIgrpcio1.81.1indirect
PyPIgrpcio-status1.76.0indirect
PyPIh110.16.0indirect
PyPIhf-xet1.2.0indirect
PyPIhttpcore1.0.9indirect
PyPIhttplib20.31.0indirect
PyPIhttpx0.28.1indirect
PyPIhttpx-sse0.4.3indirect
PyPIhuggingface-hub1.2.1indirect
PyPIidna3.15indirect
PyPIiniconfig2.3.0indirect
PyPIjinja2—indirect
PyPIjiter0.12.0indirect
PyPIjsonpatch1.33indirect
PyPIjsonpointer3.0.0indirect
PyPIlangchain1.3.11indirect
PyPIlangchain1.3.9indirect
PyPIlangchain-core1.4.7indirect
PyPIlangchain-google-community5.0.0indirect
PyPIlangchain-google-genai4.2.7indirect
PyPIlangchain-google-vertexai3.2.4indirect
PyPIlangchain-mistralai1.1.0indirect
PyPIlangchain-protocol0.0.15indirect
PyPIlangchain-protocol0.0.16indirect
PyPIlangchain-protocol0.0.18indirect
PyPIlangchain-tests1.1.5indirect
PyPIlangchain-tests1.1.6indirect
PyPIlanggraph1.2.7indirect
PyPIlanggraph1.2.9indirect
PyPIlanggraph-checkpoint4.1.1indirect
PyPIlanggraph-prebuilt1.1.0indirect
PyPIlanggraph-sdk0.4.2indirect
PyPIlangsmith0.8.18indirect
PyPIlibrt0.11.0indirect
PyPIlibrt0.8.1indirect
PyPImarkdown-it-py4.0.0indirect
PyPImdurl0.1.2indirect
PyPImultidict6.7.0indirect
PyPImypy1.18.2indirect
PyPImypy1.20.0indirect
PyPImypy2.1.0indirect
PyPImypy-extensions1.1.0indirect
PyPInumexpr2.14.1indirect
PyPInumpy2.2.6indirect
PyPInumpy2.3.4indirect
PyPInumpy2.3.5indirect
PyPInumpy2.4.2indirect
PyPIoauth2client3.0.0indirect
PyPIoauthlib3.3.1indirect
PyPIorjson3.11.7indirect
PyPIormsgpack1.12.0indirect
PyPIpackaging25.0indirect
PyPIpackaging26.0indirect
PyPIpandas2.3.3indirect
PyPIpathspec0.12.1indirect
PyPIpathspec1.0.4indirect
PyPIpillow12.2.0indirect
PyPIpluggy1.6.0indirect
PyPIply3.8indirect
PyPIpropcache0.4.1indirect
PyPIproto-plus1.26.1indirect
PyPIprotobuf6.33.5indirect
PyPIprotobuf7.35.1indirect
PyPIpy-cpuinfo9.0.0indirect
PyPIpyarrow23.0.1indirect
PyPIpyasn10.6.3indirect
PyPIpyasn1-modules0.4.2indirect
PyPIpycparser2.23indirect
PyPIpycparser3.0indirect
PyPIpydantic2.12.5indirect
PyPIpydantic2.13.4indirect
PyPIpydantic-core2.41.5indirect
PyPIpydantic-core2.46.4indirect
PyPIpygments2.20.0indirect
PyPIpyopenssl26.2.0indirect
PyPIpyparsing3.2.5indirect
PyPIpytest9.0.3indirect
PyPIpytest9.1.1indirect
PyPIpytest-asyncio1.3.0indirect
PyPIpytest-asyncio1.4.0indirect
PyPIpytest-benchmark5.2.3indirect
PyPIpytest-codspeed4.2.0indirect
PyPIpytest-codspeed4.3.0indirect
PyPIpytest-mock3.15.1indirect
PyPIpytest-order1.3.0indirect
PyPIpytest-recording0.13.4indirect
PyPIpytest-retry1.7.0indirect
PyPIpytest-socket0.7.0indirect
PyPIpytest-socket0.8.0indirect
PyPIpytest-timeout2.4.0indirect
PyPIpytest-watcher0.4.3indirect
PyPIpytest-watcher0.6.3indirect
PyPIpytest-xdist3.8.0indirect
PyPIpython-dateutil2.9.0.post0indirect
PyPIpytz2025.2indirect
PyPIpyyaml6.0.3indirect
PyPIrequests2.33.0indirect
PyPIrequests2.34.2indirect
PyPIrequests-oauthlib2.0.0indirect
PyPIrequests-toolbelt1.0.0indirect
PyPIrich14.2.0indirect
PyPIrich14.3.3indirect
PyPIrsa4.9.1indirect
PyPIruff0.13.3indirect
PyPIruff0.15.20indirect
PyPIshellingham1.5.4indirect
PyPIsix1.17.0indirect
PyPIsniffio1.3.1indirect
PyPIsoupsieve2.8.4indirect
PyPIsse-starlette—indirect
PyPIsyrupy5.1.0indirect
PyPIsyrupy5.3.4indirect
PyPIsyrupy5.4.0indirect
PyPItenacity9.1.2indirect
PyPItenacity9.1.4indirect
PyPItokenizers0.22.1indirect
PyPItomli2.3.0indirect
PyPItomli2.4.0indirect
PyPItqdm4.67.1indirect
PyPItyper-slim0.20.0indirect
PyPItypes-beautifulsoup44.12.0.20250516indirect
PyPItypes-google-cloud-ndb2.3.0.20251121indirect
PyPItypes-google-cloud-ndb2.4.0.20260518indirect
PyPItypes-html5lib1.1.11.20251014indirect
PyPItypes-pillow10.2.0.20240822indirect
PyPItypes-protobuf4.25.0.20240417indirect
PyPItypes-protobuf7.34.1.20260518indirect
PyPItypes-requests2.31.0.6indirect
PyPItypes-requests2.32.4.20250913indirect
PyPItypes-requests2.33.0.20260518indirect
PyPItypes-urllib31.26.25.14indirect
PyPItyping-extensions4.15.0indirect
PyPItyping-inspection0.4.2indirect
PyPItzdata2025.2indirect
PyPIuritemplate4.2.0indirect
PyPIurllib32.7.0indirect
PyPIuuid-utils0.12.0indirect
PyPIuuid-utils0.14.1indirect
PyPIuvicorn—indirect
PyPIvalidators0.35.0indirect
PyPIvcrpy8.2.1indirect
PyPIwatchdog6.0.0indirect
PyPIwebsockets15.0.1indirect
PyPIwebsockets16.0indirect
PyPIwrapt2.0.1indirect
PyPIwrapt2.1.1indirect
PyPIxxhash3.6.0indirect
PyPIyarl1.22.0indirect
PyPIzstandard0.25.0indirect
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 langchain-ai/langchain-google. Read them side by side →

99langchain-ai/langgraphBuild resilient agents.Exceptional98langchain-ai/langchainThe agent engineering platform.Exceptional98google/adk-goAn open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.Exceptional98bytedance/deer-flowAn open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.Exceptional98google-gemini/gemini-cliAn open-source AI agent that brings the power of Gemini directly into your terminal.Exceptional98novuhq/novuThe open-source communication infrastructure for agents and productsExceptional

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 v0.11.0 — full methodology · metrics wiki.

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