Public record
Software health reportschema 0.34.0 · metrics 2.10.0 · 2026-09-16 10:24 UTC

pydantic / pydantic-ai

How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.

PythonMIT★ 19,978 stars⑂ 2,720 forkssince Jun 2024View on GitHub ↗
KindLibraryCommand-line toolhow this is determined
#agent-framework#pydantic#python#genai#llm#harness#harness-engineering

pydantic/pydantic-ai 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 (74/100). It was last updated today. 3 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

PydanticOrganization · verified domain
3,035 followers86 public repossince Aug 2022

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

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publish
PyPIpydantic-ai2.43.015,860,5973314 days ago
PyPIclai2.43.028,5812614 days ago
PyPIpydantic-evals2.43.016,708,9462804 days ago
PyPIpydantic-graph2.43.0-3094 days ago
PyPIpydantic-ai-slim2.43.0147,324,6793254 days 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 — 1,818 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year1,818
human_commit_share0.96
days_since_last_push0
active_weeks_last_year52

Release discipline

100Exceptional
How it's scored
27/27Ships releases — 100 releases published
36/36Release recency — latest release 4 days ago
27/27Release cadence — a release every ~1.8 days
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count100
latest_release_tagv2.43.0
releases_from_tagsno
days_since_latest_release4
mean_days_between_releases1.8
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?

91Excellent · 17% of overall

Popularity & adoption

97Exceptional
How it's scored
60/60Stars — 19,978 stars
25/25Forks — 2,720 forks
11.6/15Watchers — 124 watchers
Inputs used
forks2,720
stars19,978
watchers124
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

Community health

77Good
How it's scored
22.5/22.5README
22.5/22.5License — recognized license (MIT)
18/18CONTRIBUTING guide
0/13.5Code of conduct
0/7.2Issue template
6.3/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges6
has_contributingyes
has_issue_templateno
has_code_of_conductno
readme_badge_servicesgithub.com, shields.io
has_pull_request_templateyes

Ecosystem adoption (downloads)

100Exceptional
How it's scored
80/80Monthly downloads — 179,894,222 downloads/month across pypi
0/20Registry dependents — not reported by this ecosystem
Inputs used
packagespydantic-ai, pydantic-evals, pydantic-graph, pydantic-ai-slim
dependents—
ecosystemspypi
total_downloads—
monthly_downloads179,894,222
unverified_packages_excludedclai
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?

84Excellent · 23% of overall

Maintainer resilience (bus factor)

77Good
How it's scored
36/54Bus factor — 3 contributor(s) cover half of all commits
17.2/22.5Commit distribution — top contributor authored 23% of commits
13.5/13.5Contributor breadth — 98 contributors
10/10OpenSSF Scorecard: Contributors — project has 40 contributing companies or organizations
Inputs used
bus_factor3
contributors_sampled98
top_contributor_share0.234

Issue & PR responsiveness

69Good
How it's scored
33.7/42Issue resolution — 80% of issues closed
19.5/30PR acceptance — 3,003/4,619 decided PRs merged
3.7/13Newcomer PR acceptance — 2/7 first-time contributors' PRs merged in 30d
12/15OpenSSF Scorecard: Code-Review — Found 25/30 approved changesets -- score normalized to 8
Inputs used
merged_prs3,003
open_issues634
closed_issues2,589
prs_merged_7d23
prs_decided_7d58
prs_merged_30d24
prs_decided_30d59
issue_closed_ratio0.803
closed_unmerged_prs1,616
first_time_authors_30d7
first_time_prs_merged_30d2
first_time_prs_decided_30d7

Ownership & stewardship

96Exceptional
How it's scored
30/30Ownership backing — organization-owned
20/20Verified domain
25/25Owner reach — 3,035 followers of pydantic
21.2/25Track record — 86 public repos, account ~4 yr old
Inputs used
followers3,035
owner_typeOrganization
is_verifiedyes
owner_loginpydantic
public_repos86
account_age_days1,500

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 5 package(s) on pypi
35/35Publish recency — latest publish 4 days ago
20/20Version history — 331 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagespydantic-ai, clai, pydantic-evals, pydantic-graph, pydantic-ai-slim
ecosystemspypi
any_deprecatedno
min_days_since_publish4

Engineering Quality

Are baseline engineering and documentation practices in place?

92Excellent · 19% of overall

Engineering practices

94Exceptional
How it's scored
24/24CI workflows — 32 workflow(s)
24/24Tests present
16/16Linter config — pyproject.toml ([tool.ruff])
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

90Excellent
How it's scored
30/30README
25/25Documentation directory
15/15Documentation / homepage site — https://pydantic.dev/pydantic-ai
10/10Repository description
10/10Topics — 7 topics
0/10Wiki
Inputs used
topicsagent-framework, pydantic, python, genai, llm, harness, harness-engineering
has_wikino
homepagehttps://pydantic.dev/pydantic-ai
docs_sitehttps://pydantic.dev/pydantic-ai
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

67Good
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
6/7.5Code-Review — Found 25/30 approved changesets -- score normalized to 8
2.5/2.5Contributors — project has 40 contributing companies or organizations
0/10Dangerous-Workflow — 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 1 issue activity found in the last 90 days -- score normalized to 10
5/5Packaging — packaging workflow detected
4/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 8
3/5SAST — SAST tool is not run on all commits -- score normalized to 6
5/5Security-Policy — security policy file detected
0/7.5Signed-Releases — no data
7.5/7.5Token-Permissions — GitHub workflow tokens follow principle of least privilege
0/7.5Vulnerabilities — 13 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated16
scorecard_versionv5.5.0
checks_inconclusive2
scorecard_aggregate6.7
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_packages98
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:pydantic-ai@2.43.0 runtime dependency closure — what installing the published package pulls in — 98 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.

90Excellent · 4% of overall

Agent context & guidance

96Exceptional
How it's scored
45/45Agent instructions — .github/workflows/AGENTS.md, .github/workflows/CLAUDE.md, AGENTS.md, CLAUDE.md, docs/AGENTS.md, docs/CLAUDE.md, docs/agent.md, docs/api/agent.md, docs/realtime/AGENTS.md, docs/realtime/CLAUDE.md, docs/realtime/gemini.md, pydantic_ai_slim/pydantic_ai/AGENTS.md, pydantic_ai_slim/pydantic_ai/CLAUDE.md, pydantic_ai_slim/pydantic_ai/capabilities/AGENTS.md, pydantic_ai_slim/pydantic_ai/durable_exec/AGENTS.md, pydantic_ai_slim/pydantic_ai/models/AGENTS.md, pydantic_ai_slim/pydantic_ai/models/CLAUDE.md, pydantic_ai_slim/pydantic_ai/native_tools/AGENTS.md, pydantic_ai_slim/pydantic_ai/native_tools/CLAUDE.md, pydantic_ai_slim/pydantic_ai/profiles/AGENTS.md, pydantic_ai_slim/pydantic_ai/providers/AGENTS.md, pydantic_ai_slim/pydantic_ai/realtime/AGENTS.md, pydantic_ai_slim/pydantic_ai/realtime/CLAUDE.md, pydantic_ai_slim/pydantic_ai/toolsets/AGENTS.md, pydantic_ai_slim/pydantic_ai/ui/AGENTS.md, pydantic_ai_slim/pydantic_ai/ui/CLAUDE.md, tests/AGENTS.md, tests/CLAUDE.md
15/15Machine-readable docs (llms.txt) — llms.txt served by the project website (https://pydantic.dev/llms.txt)
36.1/40Legible commit history — 65 of 96 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtyes
llms_txt_urlhttps://pydantic.dev/llms.txt
legible_history_share0.677
agent_instruction_files.github/workflows/AGENTS.md, .github/workflows/CLAUDE.md, AGENTS.md, CLAUDE.md, docs/AGENTS.md, docs/CLAUDE.md, docs/agent.md, docs/api/agent.md, docs/realtime/AGENTS.md, docs/realtime/CLAUDE.md, docs/realtime/gemini.md, pydantic_ai_slim/pydantic_ai/AGENTS.md, pydantic_ai_slim/pydantic_ai/CLAUDE.md, pydantic_ai_slim/pydantic_ai/capabilities/AGENTS.md, pydantic_ai_slim/pydantic_ai/durable_exec/AGENTS.md, pydantic_ai_slim/pydantic_ai/models/AGENTS.md, pydantic_ai_slim/pydantic_ai/models/CLAUDE.md, pydantic_ai_slim/pydantic_ai/native_tools/AGENTS.md, pydantic_ai_slim/pydantic_ai/native_tools/CLAUDE.md, pydantic_ai_slim/pydantic_ai/profiles/AGENTS.md, pydantic_ai_slim/pydantic_ai/providers/AGENTS.md, pydantic_ai_slim/pydantic_ai/realtime/AGENTS.md, pydantic_ai_slim/pydantic_ai/realtime/CLAUDE.md, pydantic_ai_slim/pydantic_ai/toolsets/AGENTS.md, pydantic_ai_slim/pydantic_ai/ui/AGENTS.md, pydantic_ai_slim/pydantic_ai/ui/CLAUDE.md, tests/AGENTS.md, tests/CLAUDE.md
agent_instruction_max_bytes108,174

Verify loop (build / test / typecheck)

87Excellent
How it's scored
18/18One-command bootstrap — Makefile
22/22Automated tests
11/11Lint / format config — pyproject.toml ([tool.ruff])
11/11Static type checking — examples/pydantic_ai_examples/py.typed, pydantic_ai_slim/pydantic_ai/py.typed, pydantic_evals/pydantic_evals/py.typed, pydantic_graph/pydantic_graph/py.typed
10/10Reproducible environment — lockfile
2/10Demonstrated agent practice — 1 of the last 100 commits agent-authored or agent-credited
5/8Automated maintenance — dependency automation configured, none observed in the sampled commits
8/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 8
Inputs used
has_nixno
has_testsyes
lockfilesuv.lock
has_dockerfileno
typed_languageno
bootstrap_filesMakefile
has_devcontainerno
has_linter_configyes
typecheck_configsexamples/pydantic_ai_examples/py.typed, pydantic_ai_slim/pydantic_ai/py.typed, pydantic_evals/pydantic_evals/py.typed, pydantic_graph/pydantic_graph/py.typed
agent_commit_share0.01
toolchain_manifests—
dependency_bot_commit_share0

Code legibility for models

76Good
How it's scored
27/45Type-checkable code — Python with type-check config (examples/pydantic_ai_examples/py.typed, pydantic_ai_slim/pydantic_ai/py.typed, pydantic_evals/pydantic_evals/py.typed, pydantic_graph/pydantic_graph/py.typed)
49.1/55Manageable file sizes — 86/801 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes854,755
source_files_sampled801
oversized_source_files86

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
Inputs used
example_dirsexamples
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

19,978GitHub stars
98contributors
1,818commits, last 12 months
0days since last push
100releases
3bus factor
634open 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 28 authors (cap 12)
  • pypi download statistics for 'pydantic-ai' unavailable this scan (stats endpoint failed after retries); adoption may be under-evidenced
  • pypi download statistics for 'pydantic-evals' unavailable this scan (stats endpoint failed after retries); adoption may be under-evidenced
  • pypi download statistics for 'pydantic-graph' unavailable this scan (stats endpoint failed after retries); adoption may be under-evidenced
  • pypi download statistics for 'pydantic-ai-slim' unavailable this scan (stats endpoint failed after retries); adoption may be under-evidenced
  • pypi download figures for pydantic-ai carried forward from the previous scan (stats endpoint unavailable this scan)
  • pypi download figures for pydantic-evals carried forward from the previous scan (stats endpoint unavailable this scan)
  • pypi download figures for pydantic-ai-slim carried forward from the previous scan (stats endpoint unavailable this scan)

More detail

Star and fork history 0 ★ / 2,720 ⇿
0Stars
2,720Forks
100Releases

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.

1,5001,7502,0002,2502,5002,7502,720122026-032026-062026-09
Major 1Minor 73Patch 19
OpenSSF Scorecard 6.7 / 10
6.7aggregate

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 10:23 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
8Code-ReviewFound 25/30 approved changesets -- score normalized to 8
10Contributorsproject has 40 contributing companies or organizations
0Dangerous-Workflowdangerous workflow patterns detected
10Dependency-Update-Toolupdate tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
10Maintained30 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 10
10Packagingpackaging workflow detected
8Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 8
6SASTSAST tool is not run on all commits -- score normalized to 6
10Security-Policysecurity policy file detected
n/aSigned-Releasesno releases found
10Token-PermissionsGitHub workflow tokens follow principle of least privilege
0Vulnerabilities13 existing vulnerabilities detected
Direct dependencies 4
RegistryPackageVersion constraintManifest
PyPIanyio>=4.7.0pydantic_graph/pyproject.toml
PyPIlogfire-api>=3.14.1pydantic_graph/pyproject.toml
PyPIpydantic>=2.12pydantic_graph/pyproject.toml
PyPItyping-inspection>=0.4.0pydantic_graph/pyproject.toml
All dependencies 350

Full resolved dependency set from the GitHub dependency graph: 8 direct and 342 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPIanyio—direct
PyPIanyio4.14.1direct
PyPIlogfire-api—direct
PyPIlogfire-api4.37.0direct
PyPIpydantic—direct
PyPIpydantic2.13.4direct
PyPItyping-inspection—direct
PyPItyping-inspection0.4.2direct
PyPIag-ui-protocol0.1.19indirect
PyPIaiofile3.9.0indirect
PyPIaiohappyeyeballs2.6.1indirect
PyPIaiohttp3.14.1indirect
PyPIaiolimiter1.2.1indirect
PyPIaiosignal1.4.0indirect
PyPIaiosqlite0.21.0indirect
PyPIalembic1.17.2indirect
PyPIamplitude-analytics1.2.3indirect
PyPIannotated-doc0.0.4indirect
PyPIannotated-types0.7.0indirect
PyPIanthropic1.3.0indirect
PyPIapprise1.9.6indirect
PyPIargcomplete3.6.3indirect
PyPIasgi-lifespan2.1.0indirect
PyPIasgiref3.11.0indirect
PyPIast-serialize0.5.0indirect
PyPIasttokens2.4.1indirect
PyPIasync-timeout5.0.1indirect
PyPIasyncpg0.31.0indirect
PyPIattrs25.4.0indirect
PyPIaudioop-lts0.2.2indirect
PyPIauthlib1.7.2indirect
PyPIbackports-tarfile1.2.0indirect
PyPIbeartype0.22.9indirect
PyPIbeautifulsoup44.14.3indirect
PyPIblack26.5.1indirect
PyPIblockbuster1.5.26indirect
PyPIboto31.42.63indirect
PyPIboto3-stubs1.42.63indirect
PyPIbotocore1.42.63indirect
PyPIbotocore-stubs1.42.41indirect
PyPIbrotli1.2.0indirect
PyPIbrotlicffi1.2.0.0indirect
PyPIburner-redis0.1.6indirect
PyPIburner-redis0.1.7indirect
PyPIcachetools6.2.4indirect
PyPIcaio0.9.25indirect
PyPIcertifi2025.11.12indirect
PyPIcffi2.0.0indirect
PyPIcharset-normalizer3.4.4indirect
PyPIclick8.1.8indirect
PyPIcloudpickle3.1.2indirect
PyPIcohere5.20.6indirect
PyPIcolorama0.4.6indirect
PyPIcoolname2.2.0indirect
PyPIcoverage7.13.0indirect
PyPIcronsim2.7indirect
PyPIcryptography49.0.0indirect
PyPIcuda-bindings13.1.1indirect
PyPIcuda-pathfinder1.3.4indirect
PyPIcuda-toolkit13.0.3.0indirect
PyPIcyclopts4.15.0indirect
PyPIdatasets4.4.2indirect
PyPIdateparser1.2.2indirect
PyPIdbos2.10.0indirect
PyPIddgs9.10.0indirect
PyPIdevtools0.12.2indirect
PyPIdill0.4.0indirect
PyPIdirty-equals0.11indirect
PyPIdistro1.9.0indirect
PyPIdnspython2.8.0indirect
PyPIdocker7.1.0indirect
PyPIdocstring-parser0.17.0indirect
PyPIdocutils0.22.4indirect
PyPIduckdb1.4.3indirect
PyPIduckduckgo-search8.1.1indirect
PyPIemail-validator2.3.0indirect
PyPIeval-type-backport0.3.1indirect
PyPIexa-py2.15.0indirect
PyPIexceptiongroup1.3.1indirect
PyPIexecnet2.1.2indirect
PyPIexecuting2.2.1indirect
PyPIfake-useragent2.2.0indirect
PyPIfastapi0.138.1indirect
PyPIfastavro1.12.1indirect
PyPIfastmcp3.4.2indirect
PyPIfastmcp-slim3.4.2indirect
PyPIfastmcp-slim4.0.0b1indirect
PyPIfastmcp-tasks4.0.0b1indirect
PyPIffmpeg-python0.2.0indirect
PyPIfilelock3.20.3indirect
PyPIforbiddenfruit0.1.4indirect
PyPIfrozenlist1.8.0indirect
PyPIfsspec2025.10.0indirect
PyPIfuture1.0.0indirect
PyPIgenai-prices0.1.6indirect
PyPIgoogle-auth2.56.3indirect
PyPIgoogle-genai2.18.0indirect
PyPIgoogleapis-common-protos1.72.0indirect
PyPIgradio6.19.0indirect
PyPIgradio-client2.5.0indirect
PyPIgraphviz0.21indirect
PyPIgreenlet3.3.0indirect
PyPIgriffe1.15.0indirect
PyPIgriffecli2.1.0indirect
PyPIgriffelib2.1.0indirect
PyPIgroovy0.1.2indirect
PyPIgroq0.25.0indirect
PyPIgrpcio1.76.0indirect
PyPIgrpclib0.4.7indirect
PyPIh110.16.0indirect
PyPIh24.3.0indirect
PyPIhatchling—indirect
PyPIhf-gradio0.4.1indirect
PyPIhf-xet1.2.0indirect
PyPIhf-xet1.4.3indirect
PyPIhpack4.1.0indirect
PyPIhttpcore1.0.9indirect
PyPIhttpcore22.9.1indirect
PyPIhttpx0.28.1indirect
PyPIhttpx-sse0.4.3indirect
PyPIhttpx22.9.1indirect
PyPIhuggingface-hub1.16.1indirect
PyPIhuggingface-hub1.3.4indirect
PyPIhumanize4.15.0indirect
PyPIhyperframe6.1.0indirect
PyPIidna3.18indirect
PyPIimportlib-metadata8.7.1indirect
PyPIiniconfig2.3.0indirect
PyPIinline-snapshot0.34.2indirect
PyPIjaraco-classes3.4.0indirect
PyPIjaraco-context6.1.0indirect
PyPIjaraco-functools4.4.0indirect
PyPIjeepney0.9.0indirect
PyPIjinja23.1.6indirect
PyPIjinja2-humanize-extension0.4.0indirect
PyPIjiter0.16.0indirect
PyPIjmespath1.0.1indirect
PyPIjoblib1.5.3indirect
PyPIjoserfc1.7.1indirect
PyPIjsonpatch1.33indirect
PyPIjsonpath-python1.1.5indirect
PyPIjsonpointer3.0.0indirect
PyPIjsonref1.1.0indirect
PyPIjsonschema4.25.1indirect
PyPIjsonschema-path0.3.4indirect
PyPIjsonschema-specifications2025.9.1indirect
PyPIkeyring25.7.0indirect
PyPIlangchain-core1.4.0indirect
PyPIlangchain-protocol0.0.15indirect
PyPIlangchain-text-splitters1.1.2indirect
PyPIlangsmith0.9.3indirect
PyPIlibrt0.11.0indirect
PyPIlistentome0.1.0indirect
PyPIlogfire—indirect
PyPIlogfire4.40.0indirect
PyPIlxml6.1.1indirect
PyPImako1.3.12indirect
PyPImarkdown3.10indirect
PyPImarkdown-it-py3.0.0indirect
PyPImarkdownify1.2.2indirect
PyPImarkupsafe2.1.5indirect
PyPImcp1.28.1indirect
PyPImcp2.0.0indirect
PyPImcp-types2.0.0indirect
PyPImdurl0.1.2indirect
PyPImistralai2.9.2indirect
PyPImodal1.0.4indirect
PyPImore-itertools10.8.0indirect
PyPImpmath1.3.0indirect
PyPImultidict6.7.0indirect
PyPImultiprocess0.70.18indirect
PyPImypy2.1.0indirect
PyPImypy-boto3-bedrock-runtime1.42.42indirect
PyPImypy-extensions1.1.0indirect
PyPInetworkx3.4.2indirect
PyPInetworkx3.6.1indirect
PyPInexus-rpc1.4.0indirect
PyPInodeenv1.10.0indirect
PyPInumpy2.2.6indirect
PyPInumpy2.5.0indirect
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
PyPIoauthlib3.3.1indirect
PyPIopenai3.8.0indirect
PyPIopenapi-pydantic0.5.1indirect
PyPIopentelemetry-api1.44.0indirect
PyPIopentelemetry-exporter-otlp-proto-common1.44.0indirect
PyPIopentelemetry-exporter-otlp-proto-http1.44.0indirect
PyPIopentelemetry-instrumentation0.65b0indirect
PyPIopentelemetry-instrumentation-asgi0.65b0indirect
PyPIopentelemetry-instrumentation-asyncpg0.65b0indirect
PyPIopentelemetry-instrumentation-dbapi0.65b0indirect
PyPIopentelemetry-instrumentation-fastapi0.65b0indirect
PyPIopentelemetry-instrumentation-httpx0.65b0indirect
PyPIopentelemetry-instrumentation-logging0.65b0indirect
PyPIopentelemetry-instrumentation-sqlite30.65b0indirect
PyPIopentelemetry-proto1.44.0indirect
PyPIopentelemetry-sdk1.44.0indirect
PyPIopentelemetry-semantic-conventions0.65b0indirect
PyPIopentelemetry-util-http0.65b0indirect
PyPIorjson3.11.8indirect
PyPIoutcome1.3.0.post0indirect
PyPIpackaging25.0indirect
PyPIpandas2.3.3indirect
PyPIpathable0.4.4indirect
PyPIpathspec1.0.4indirect
PyPIpendulum3.1.0indirect
PyPIpillow12.3.0indirect
PyPIpip26.1.2indirect
PyPIplatformdirs4.5.1indirect
PyPIpluggy1.6.0indirect
PyPIprefect3.7.7indirect
PyPIprimp0.15.0indirect
PyPIprometheus-client0.23.1indirect
PyPIprompt-toolkit3.0.52indirect
PyPIpropcache0.4.1indirect
PyPIprotobuf6.33.5indirect
PyPIpsycopg3.3.2indirect
PyPIpsycopg-binary3.3.2indirect
PyPIpy-key-value-aio0.4.4indirect
PyPIpyarrow24.0.0indirect
PyPIpyasn10.6.4indirect
PyPIpyasn1-modules0.4.2indirect
PyPIpycparser2.23indirect
PyPIpydantic-core2.46.4indirect
PyPIpydantic-extra-types2.10.6indirect
PyPIpydantic-handlebars0.1.0indirect
PyPIpydantic-settings2.14.2indirect
PyPIpydocket0.20.1indirect
PyPIpydocket0.22.0indirect
PyPIpydub0.25.1indirect
PyPIpygments2.20.0indirect
PyPIpyjwt2.13.0indirect
PyPIpyperclip1.11.0indirect
PyPIpyright1.1.411indirect
PyPIpytest9.1.1indirect
PyPIpytest-examples0.0.18indirect
PyPIpytest-mock3.15.1indirect
PyPIpytest-pretty1.3.0indirect
PyPIpytest-recording0.13.4indirect
PyPIpytest-xdist3.8.0indirect
PyPIpython-dateutil2.9.0.post0indirect
PyPIpython-dotenv1.2.2indirect
PyPIpython-json-logger4.0.0indirect
PyPIpython-multipart0.0.32indirect
PyPIpython-slugify8.0.4indirect
PyPIpytokens0.4.1indirect
PyPIpytz2025.2indirect
PyPIpywin32311indirect
PyPIpywin32-ctypes0.2.3indirect
PyPIpyyaml6.0.3indirect
PyPIreadchar4.2.1indirect
PyPIredis7.1.0indirect
PyPIreferencing0.36.2indirect
PyPIregex2025.11.3indirect
PyPIrequests2.33.1indirect
PyPIrequests-oauthlib2.0.0indirect
PyPIrequests-toolbelt1.0.0indirect
PyPIrfc3339-validator0.1.4indirect
PyPIrich14.2.0indirect
PyPIrich-rst1.3.2indirect
PyPIrpds-py0.30.0indirect
PyPIruamel-yaml0.18.17indirect
PyPIruamel-yaml-clib0.2.15indirect
PyPIruff0.15.19indirect
PyPIs3transfer0.16.0indirect
PyPIsafehttpx0.1.7indirect
PyPIsafetensors0.8.0indirect
PyPIscikit-learn1.7.2indirect
PyPIscikit-learn1.8.0indirect
PyPIscipy1.15.3indirect
PyPIscipy1.16.3indirect
PyPIsecretstorage3.5.0indirect
PyPIsemantic-version2.10.0indirect
PyPIsemver3.0.4indirect
PyPIsentence-transformers5.2.2indirect
PyPIsetuptools83.0.0indirect
PyPIshellingham1.5.4indirect
PyPIsigtools4.0.1indirect
PyPIsix1.17.0indirect
PyPIsniffio1.3.1indirect
PyPIsocksio1.0.0indirect
PyPIsortedcontainers2.4.0indirect
PyPIsoupsieve2.8.4indirect
PyPIsqlalchemy2.0.45indirect
PyPIsse-starlette3.0.4indirect
PyPIstarlette1.3.1indirect
PyPIstrict-no-cover0.1.1indirect
PyPIsympy1.14.0indirect
PyPIsynchronicity0.9.16indirect
PyPItaskgroup0.2.2indirect
PyPItavily-python0.7.26indirect
PyPItemporalio1.31.0indirect
PyPItenacity9.1.2indirect
PyPItext-unidecode1.3indirect
PyPIthreadpoolctl3.6.0indirect
PyPItiktoken0.12.0indirect
PyPItokenizers0.22.1indirect
PyPItoml0.10.2indirect
PyPItomli2.3.0indirect
PyPItomlkit0.13.3indirect
PyPItorch2.13.0indirect
PyPItqdm4.67.1indirect
PyPItransformers5.13.1indirect
PyPItrio0.34.0indirect
PyPItriton3.7.1indirect
PyPItruststore0.10.4indirect
PyPItwelvelabs1.2.8indirect
PyPItyper0.19.2indirect
PyPItyper0.26.8indirect
PyPItyper-slim0.20.1indirect
PyPItypes-awscrt0.30.0indirect
PyPItypes-certifi2021.10.8.3indirect
PyPItypes-protobuf6.32.1.20251210indirect
PyPItypes-requests2.32.4.20250913indirect
PyPItypes-s3transfer0.16.0indirect
PyPItypes-toml0.10.8.20240310indirect
PyPItyping-extensions4.15.0indirect
PyPItzdata2025.3indirect
PyPItzlocal5.3.1indirect
PyPIuncalled-for0.3.2indirect
PyPIurllib32.7.0indirect
PyPIuuid-utils0.13.0indirect
PyPIuv-dynamic-versioning—indirect
PyPIuvicorn0.40.0indirect
PyPIvcrpy8.2.1indirect
PyPIvoyageai0.3.7indirect
PyPIwatchfiles1.1.1indirect
PyPIwcwidth0.2.14indirect
PyPIwebsockets15.0.1indirect
PyPIwhenever0.8.10indirect
PyPIwrapt1.17.3indirect
PyPIxai-sdk1.18.0indirect
PyPIxxhash3.6.0indirect
PyPIyarl1.22.0indirect
PyPIzipp3.23.0indirect
PyPIzstandard0.25.0indirect
Dependency advisories 0

Installing pypi:pydantic-ai@2.43.0 pulls in 98 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 pydantic/pydantic-ai. 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.Exceptional99ag2ai/ag2AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3xExceptional97strands-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.Exceptional98openai/openai-agents-pythonA lightweight, powerful framework for multi-agent workflowsExceptional98bytedance/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.Exceptional98mem0ai/mem0The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.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.