Public record
Software health reportschema 0.34.0 · metrics 2.10.0 · 2026-09-16 20:28 UTC

google / adk-python

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

PythonApache-2.0★ 21,553 stars⑂ 4,013 forkssince Apr 2025View on GitHub ↗
KindCommand-line toolLibraryNetwork servicehow this is determined
#agent#agents#agents-sdk#ai#ai-agents#multi-agent-systems#multi-agents#multi-agents-collaboration#aiagentframework#genai#genai-chatbot#llms#agentic#agentic-ai#llm#multi-agent

google/adk-python holds a health index of 99 out of 100, placing it in the Exceptional band. It scores highest on Vitality (100/100) and lowest on Security (70/100). It was last updated today. 4 contributors account for most of its recent work.

99
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.

99
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 89 is calibrated to 99 on the published index scale (record calibration 2026-08-02).

Ownership

GoogleOrganization · verified domain
78,660 followers2,904 public repossince Jan 2012

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

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publish
PyPIgoogle-adk2.9.118,710,896931 day ago

Metrics by category

Vitality

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

100Exceptional · 21% of overall

Development activity

100Exceptional
How it's scored
36/36Push recency — last push 0 days ago
36/36Commit cadence — 52/52 weeks with commits
18/18Commit volume — 3,049 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 16 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year3,049
human_commit_share1
days_since_last_push0
active_weeks_last_year52

Release discipline

100Exceptional
How it's scored
27/27Ships releases — 86 releases published
36/36Release recency — latest release 1 days ago
27/27Release cadence — a release every ~4.7 days
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count86
latest_release_tagv2.9.1
releases_from_tagsno
days_since_latest_release1
mean_days_between_releases4.7
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?

96Exceptional · 17% of overall

Popularity & adoption

97Exceptional
How it's scored
60/60Stars — 21,553 stars
25/25Forks — 4,013 forks
12.1/15Watchers — 152 watchers
Inputs used
forks4,013
stars21,553
watchers152
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 (Apache-2.0)
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_badges7
has_contributingyes
has_issue_templateno
has_code_of_conductyes
readme_badge_servicesgithub.com, shields.io
has_pull_request_templateyes

Ecosystem adoption (downloads)

100Exceptional
How it's scored
80/80Monthly downloads — 18,710,896 downloads/month across pypi
0/20Registry dependents — not reported by this ecosystem
Inputs used
packagesgoogle-adk
dependents—
ecosystemspypi
total_downloads—
monthly_downloads18,710,896
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?

86Excellent · 23% of overall

Maintainer resilience (bus factor)

85Excellent
How it's scored
43.2/54Bus factor — 4 contributor(s) cover half of all commits
18.1/22.5Commit distribution — top contributor authored 20% of commits
13.5/13.5Contributor breadth — 99 contributors
10/10OpenSSF Scorecard: Contributors — project has 13 contributing companies or organizations
Inputs used
bus_factor4
contributors_sampled99
top_contributor_share0.197

Issue & PR responsiveness

60Moderate
How it's scored
38.3/42Issue resolution — 91% of issues closed
7.2/30PR acceptance — 664/2,771 decided PRs merged
0/13Newcomer PR acceptance — 0/11 first-time contributors' PRs merged in 30d
15/15OpenSSF Scorecard: Code-Review — all changesets reviewed
Inputs used
merged_prs664
open_issues271
closed_issues2,860
prs_merged_7d2
prs_decided_7d55
prs_merged_30d2
prs_decided_30d59
issue_closed_ratio0.913
closed_unmerged_prs2,107
first_time_authors_30d11
first_time_prs_merged_30d0
first_time_prs_decided_30d11

Ownership & stewardship

100Exceptional
How it's scored
30/30Ownership backing — organization-owned
20/20Verified domain
25/25Owner reach — 78,660 followers of google
25/25Track record — 2,904 public repos, account ~14 yr old
Inputs used
followers78,660
owner_typeOrganization
is_verifiedyes
owner_logingoogle
public_repos2,904
account_age_days5,355

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 1 package(s) on pypi
35/35Publish recency — latest publish 1 days ago
20/20Version history — 93 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagesgoogle-adk
ecosystemspypi
any_deprecatedno
min_days_since_publish1

Engineering Quality

Are baseline engineering and documentation practices in place?

91Excellent · 19% of overall

Engineering practices

92Excellent
How it's scored
24/24CI workflows — 14 workflow(s)
24/24Tests present
16/16Linter config — pyproject.toml ([tool.ruff], [tool.isort]), tox.ini
9.6/9.6Pre-commit hooks
0/6.4.editorconfig
0/20OpenSSF Scorecard: CI-Tests — no data
Inputs used
has_ciyes
has_testsyes
has_editorconfigno
has_linter_configyes
has_precommit_configyes
Excluded from scoring (no data or not applicable): OpenSSF Scorecard: CI-Tests. Remaining weights renormalized.

Documentation

90Excellent
How it's scored
30/30README
25/25Documentation directory
15/15Documentation / homepage site — https://google.github.io/adk-docs/
10/10Repository description
10/10Topics — 16 topics
0/10Wiki
Inputs used
topicsagent, agents, agents-sdk, ai, ai-agents, multi-agent-systems, multi-agents, multi-agents-collaboration, aiagentframework, genai, genai-chatbot, llms, agentic, agentic-ai, llm, multi-agent
has_wikino
homepagehttps://google.github.io/adk-docs/
docs_sitehttps://google.github.io/adk-docs/
has_readmeyes
has_docs_diryes
has_descriptionyes

Security

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

70Good · 16% of overall

Security posture

63Moderate
How it's scored
7.5/7.5Binary-Artifacts — no binaries found in the repo
0.8/7.5Branch-Protection — branch protection is not maximal on development and all release branches
0/2.5CI-Tests — no data
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
7.5/7.5Code-Review — all changesets reviewed
2.5/2.5Contributors — project has 13 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 16 issue activity found in the last 90 days -- score normalized to 10
0/5Packaging — no data
2.5/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 5
0/5SAST — no SAST tool detected
5/5Security-Policy — security policy file detected
0/7.5Signed-Releases — no data
0/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
3/7.5Vulnerabilities — 6 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated15
scorecard_versionv5.5.0
checks_inconclusive3
scorecard_aggregate6.2
Excluded from scoring (no data or not applicable): CI-Tests, Packaging, 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
0/25Indirect dependencies free of known advisories — transitive set not separable from development and test dependencies in this scope
0/40No advisories left outstanding — no advisory carries a publication date
Inputs used
sourceosv
advisories0
affected_packages0
assessed_packages15
unassessed_packages110
affected_by_severitynone
direct_affected_packages0
Excluded from scoring (no data or not applicable): Indirect dependencies free of known advisories, No advisories left outstanding. Remaining weights renormalized. Matched 15 resolved dependencies against OSV. 110 could not be assessed — no resolved version, an unsupported ecosystem, or beyond the reported package list. This repository publishes no package the index resolves, so the repository dependency graph was assessed instead. That graph mixes development and test pins with shipped dependencies, so only the declared runtime dependencies are scored; transitive findings are reported as context and excluded from the score. 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.

81Excellent · 4% of overall

Agent context & guidance

100Exceptional
How it's scored
45/45Agent instructions — AGENTS.md
15/15Machine-readable docs (llms.txt) — llms.txt present
40/40Legible commit history — 99 of 100 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtyes
llms_txt_url—
legible_history_share0.99
agent_instruction_filesAGENTS.md
agent_instruction_max_bytes1,420

Verify loop (build / test / typecheck)

59Moderate
How it's scored
0/18One-command bootstrap
22/22Automated tests
11/11Lint / format config — pyproject.toml ([tool.ruff], [tool.isort]), tox.ini
11/11Static type checking — src/google/adk/py.typed
10/10Reproducible environment — Dockerfile
0/10Demonstrated agent practice — no agent-authored commits among the last 100
0/8Automated maintenance — no automated dependency updates observed
5/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 5
Inputs used
has_nixno
has_testsyes
lockfiles—
has_dockerfileyes
typed_languageno
bootstrap_files—
has_devcontainerno
has_linter_configyes
typecheck_configssrc/google/adk/py.typed
agent_commit_share0
toolchain_manifests—
dependency_bot_commit_share0

Code legibility for models

81Excellent
How it's scored
27/45Type-checkable code — Python with type-check config (src/google/adk/py.typed)
53.7/55Manageable file sizes — 50/2,055 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes4,742,976
source_files_sampled2,055
oversized_source_files50

Machine-readable interfaces

100Exceptional
How it's scored
40/40API schema (OpenAPI/GraphQL/proto) — contributing/samples/integrations/authn-adk-all-in-one/adk_agents/agent_openapi_tools/openapi.yaml, contributing/samples/integrations/authn-adk-all-in-one/hotel_booker_app/openapi.yaml
20/20MCP server
40/40Runnable examples — example, examples, notebooks, samples
Inputs used
example_dirsexample, examples, notebooks, samples
has_mcp_signalyes
api_schema_filescontributing/samples/integrations/authn-adk-all-in-one/adk_agents/agent_openapi_tools/openapi.yaml, contributing/samples/integrations/authn-adk-all-in-one/hotel_booker_app/openapi.yaml
interfaces_expected_ofnetwork-service

Key facts

21,553GitHub stars
99contributors
3,049commits, last 12 months
0days since last push
86releases
4bus factor
271open issues
PyPIpackage ecosystems

Data collection warnings

  • Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
  • First-time contributor figures cover 12 of 47 authors (cap 12)
  • pypi download statistics for 'google-adk' unavailable this scan (stats endpoint failed after retries); adoption may be under-evidenced
  • pypi download figures for google-adk carried forward from the previous scan (stats endpoint unavailable this scan)
  • deps.dev does not index pypi:google-adk@2.9.1; advisories assessed against the repository dependency graph instead

More detail

Star and fork history 0 ★ / 4,013 ⇿
0Stars
4,013Forks
42Releases

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.

Only the most recent history is shown — this repository exceeds the collection window, so the earliest history is not captured.

3,0003,2003,4003,6003,8004,0004,2004,013162026-032026-062026-09
Major 1Minor 21Patch 17
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 · 2026-09-16 20:27 UTC

10Binary-Artifactsno binaries found in the repo
1Branch-Protectionbranch protection is not maximal on development and all release branches
n/aCI-Testsno pull request found
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
10Code-Reviewall changesets reviewed
10Contributorsproject has 13 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 16 issue activity found in the last 90 days -- score normalized to 10
n/aPackagingpackaging workflow not detected
5Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 5
0SASTno SAST tool detected
10Security-Policysecurity policy file detected
n/aSigned-Releasesno releases found
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
4Vulnerabilities6 existing vulnerabilities detected
Direct dependencies 23
RegistryPackageVersion constraintManifest
PyPIaiosqlite>=0.21pyproject.toml
PyPIauthlib>=1.6.6,<2pyproject.toml
PyPIclick>=8.1.8,<9pyproject.toml
PyPIfastapi>=0.133,<1pyproject.toml
PyPIgoogle-auth>=2.47pyproject.toml
PyPIgoogle-genai>=2.19,<3pyproject.toml
PyPIgraphviz>=0.20.2,<1pyproject.toml
PyPIhttpx>=0.27,<1pyproject.toml
PyPIjsonschema>=4.23,<5pyproject.toml
PyPIopentelemetry-api>=1.39,<=1.42.1pyproject.toml
PyPIopentelemetry-sdk>=1.39,<=1.42.1pyproject.toml
PyPIpackaging>=21pyproject.toml
PyPIpydantic>=2.12,<3pyproject.toml
PyPIpython-dotenv>=1,<2pyproject.toml
PyPIpython-multipart>=0.0.9,<1pyproject.toml
PyPIpyyaml>=6.0.2,<7pyproject.toml
PyPIrequests>=2.32.4,<3pyproject.toml
PyPIstarlette>=1.3.1,<2pyproject.toml
PyPItenacity>=9,<10pyproject.toml
PyPItyping-extensions>=4.5,<5pyproject.toml
PyPIuvicorn>=0.34,<1pyproject.toml
PyPIwatchdog>=6,<7pyproject.toml
PyPIwebsockets>=15.0.1,<16pyproject.toml
All dependencies 125

Full resolved dependency set from the GitHub dependency graph: 25 direct and 100 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPIaiosqlite—direct
PyPIauthlib—direct
PyPIclick—direct
PyPIfastapi—direct
PyPIgoogle-auth—direct
PyPIgoogle-genai—direct
PyPIgraphviz—direct
PyPIhttpx—direct
PyPIjsonschema—direct
PyPIopentelemetry-api—direct
PyPIopentelemetry-sdk—direct
PyPIpackaging—direct
PyPIpydantic—direct
PyPIpython-dotenv—direct
PyPIpython-dotenv1.2.2direct
PyPIpython-multipart—direct
PyPIpyyaml—direct
PyPIrequests—direct
PyPIrequests2.33.0direct
PyPIstarlette—direct
PyPItenacity—direct
PyPItyping-extensions—direct
PyPIuvicorn—direct
PyPIwatchdog—direct
PyPIwebsockets—direct
PyPIa2a-sdk—indirect
PyPIaiohttp—indirect
PyPIanthropic—indirect
PyPIanyio—indirect
PyPIbeautifulsoup4—indirect
PyPIbrowserbase1.3.0indirect
PyPIcodespell2.4.2indirect
PyPIdaytona—indirect
PyPIdocker—indirect
PyPIe2b—indirect
PyPIflask3.1.3indirect
PyPIflask-cors6.0.1indirect
PyPIflit—indirect
PyPIflit-core—indirect
PyPIgepa—indirect
PyPIgoogle-adk—indirect
PyPIgoogle-antigravity—indirect
PyPIgoogle-api-python-client—indirect
PyPIgoogle-benchmark—indirect
PyPIgoogle-cloud-agentidentitycredentials—indirect
PyPIgoogle-cloud-aiplatform—indirect
PyPIgoogle-cloud-bigquery—indirect
PyPIgoogle-cloud-bigquery-storage—indirect
PyPIgoogle-cloud-bigtable—indirect
PyPIgoogle-cloud-dataplex—indirect
PyPIgoogle-cloud-discoveryengine—indirect
PyPIgoogle-cloud-eventarc-publishing—indirect
PyPIgoogle-cloud-firestore—indirect
PyPIgoogle-cloud-iamconnectorcredentials—indirect
PyPIgoogle-cloud-modelarmor—indirect
PyPIgoogle-cloud-parametermanager—indirect
PyPIgoogle-cloud-pubsub—indirect
PyPIgoogle-cloud-resource-manager—indirect
PyPIgoogle-cloud-secret-manager—indirect
PyPIgoogle-cloud-spanner—indirect
PyPIgoogle-cloud-speech—indirect
PyPIgoogle-cloud-storage—indirect
PyPIgoogle-cloud-texttospeech—indirect
PyPIhypothesis—indirect
PyPIisort8.0.1indirect
PyPIjinja2—indirect
PyPIk8s-agent-sandbox—indirect
PyPIkubernetes—indirect
PyPIlangchain-community—indirect
PyPIlanggraph—indirect
PyPIlanggraph-checkpoint—indirect
PyPIlitellm—indirect
PyPIlivekit—indirect
PyPIlivekit-api—indirect
PyPIllama-index-embeddings-google-genai—indirect
PyPIllama-index-readers-file—indirect
PyPIlxml—indirect
PyPImcp—indirect
PyPImdformat0.7.22indirect
PyPImypy—indirect
PyPInltk—indirect
PyPIoci—indirect
PyPIopenai—indirect
PyPIopenpyxl—indirect
PyPIopentelemetry-exporter-gcp-logging—indirect
PyPIopentelemetry-exporter-gcp-monitoring—indirect
PyPIopentelemetry-exporter-gcp-trace—indirect
PyPIopentelemetry-exporter-otlp-proto-http—indirect
PyPIopentelemetry-instrumentation-google-genai—indirect
PyPIopentelemetry-instrumentation-grpc—indirect
PyPIopentelemetry-instrumentation-httpx—indirect
PyPIopentelemetry-resourcedetector-gcp—indirect
PyPIpandas—indirect
PyPIpillow—indirect
PyPIplaywright1.52.0indirect
PyPIpre-commit—indirect
PyPIpre-commit-hooks4.6indirect
PyPIprotobuf—indirect
PyPIpyarrow—indirect
PyPIpyink25.12indirect
PyPIpyjwt2.13.0indirect
PyPIpylint—indirect
PyPIpymongo—indirect
PyPIpypika—indirect
PyPIpyproject-fmt2.24indirect
PyPIpytest—indirect
PyPIpytest-asyncio—indirect
PyPIpytest-mock—indirect
PyPIpytest-xdist—indirect
PyPIpython-dateutil—indirect
PyPIredis—indirect
PyPIrich—indirect
PyPIrouge-score—indirect
PyPIruff0.15.17indirect
PyPIslack-bolt—indirect
PyPIsphinx—indirect
PyPIsqlalchemy—indirect
PyPIsqlalchemy-spanner—indirect
PyPItabulate—indirect
PyPItermcolor3.1.0indirect
PyPItoolbox-adk—indirect
PyPItox—indirect
PyPItox-uv—indirect
PyPIxlrd—indirect
PyPIyoutube-search—indirect
Dependency advisories 0

This repository publishes no package the index resolves, so its own dependency graph was assessed — 15 packages, which also include development and test pins that never ship: 0 carry known advisories, of which 0 are direct. 110 could not be assessed — no resolved version, an unsupported ecosystem, or beyond the reported package list.

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 google/adk-python. Read them side by side →

96google/adk-jsAn open-source, code-first Typescript toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.Exceptional99ag2ai/ag2AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3xExceptional100deepset-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.Exceptional98strands-agents/toolsA set of tools that gives agents powerful capabilities.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.Exceptional98google/adk-goAn open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.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 v0.34.0 — full methodology · metrics wiki.

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