Public record
Software health reportschema 0.31.0 · metrics 2.10.0 · 2026-08-05 02:27 UTC

openai / openai-agents-python

A lightweight, powerful framework for multi-agent workflows

PythonMIT★ 28,384 stars⑂ 4,442 forkssince Mar 2025View on GitHub ↗
KindLibraryMCP serverhow this is determined
#agents#ai#framework#llm#python#openai#harness

openai/openai-agents-python holds a health index of 94 out of 100, placing it in the Exceptional band. It scores highest on Vitality (100/100) and lowest on Security (63/100). It was last updated today. 2 contributors account for most of its recent work.

94
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.

94
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 81 is calibrated to 94 on the published index scale (record calibration 2026-08-02).

Ownership

OpenAIOrganization
128,598 followers268 public repossince Oct 2015

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

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publish
PyPIopenai-agents0.19.3-1140 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 — 1,310 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 15 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year1,310
human_commit_share0.94
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 0 days ago
27/27Release cadence — a release every ~4.6 days
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count100
latest_release_tagv0.19.3
releases_from_tagsno
days_since_latest_release0
mean_days_between_releases4.6
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?

76Good · 17% of overall

Popularity & adoption

98Exceptional
How it's scored
60/60Stars — 28,384 stars
25/25Forks — 4,442 forks
13.1/15Watchers — 225 watchers
Inputs used
forks4,442
stars28,384
watchers225
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

Community health

50Moderate
How it's scored
22.5/22.5README
22.5/22.5License — recognized license (MIT)
0/18CONTRIBUTING guide
0/13.5Code of conduct
0/7.2Issue template
0/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges1
has_contributingno
has_issue_templateno
has_code_of_conductno
readme_badge_servicesshields.io
has_pull_request_templateno

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)

62Moderate
How it's scored
25.2/54Bus factor — 2 contributor(s) cover half of all commits
13.6/22.5Commit distribution — top contributor authored 40% of commits
13.5/13.5Contributor breadth — 98 contributors
10/10OpenSSF Scorecard: Contributors — project has 34 contributing companies or organizations
Inputs used
bus_factor2
contributors_sampled98
top_contributor_share0.396

Issue & PR responsiveness

64Moderate
How it's scored
41.5/42Issue resolution — 99% of issues closed
17.3/30PR acceptance — 1,567/2,717 decided PRs merged
2.6/13Newcomer PR acceptance — 1/5 first-time contributors' PRs merged in 30d
3/15OpenSSF Scorecard: Code-Review — Found 6/29 approved changesets -- score normalized to 2
Inputs used
merged_prs1,567
open_issues16
closed_issues1,367
prs_merged_7d25
prs_decided_7d59
prs_merged_30d25
prs_decided_30d59
issue_closed_ratio0.988
closed_unmerged_prs1,150
first_time_authors_30d4
first_time_prs_merged_30d1
first_time_prs_decided_30d5

Ownership & stewardship

100Exceptional
How it's scored
30/30Ownership backing — organization-owned
0/20Verified domain — verified-domain status not read for this organization
25/25Owner reach — 128,598 followers of openai
25/25Track record — 268 public repos, account ~10 yr old
Inputs used
followers128,598
owner_typeOrganization
is_verified—
owner_loginopenai
public_repos268
account_age_days3,958
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 0 days ago
20/20Version history — 114 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagesopenai-agents
ecosystemspypi
any_deprecatedno
min_days_since_publish0

Engineering Quality

Are baseline engineering and documentation practices in place?

77Good · 19% of overall

Engineering practices

68Good
How it's scored
24/24CI workflows — 6 workflow(s)
24/24Tests present
0/16Linter config
0/9.6Pre-commit hooks
0/6.4.editorconfig
20/20OpenSSF Scorecard: CI-Tests — 28 out of 28 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

90Excellent
How it's scored
30/30README
25/25Documentation directory
15/15Documentation / homepage site — https://openai.github.io/openai-agents-python/
10/10Repository description
10/10Topics — 7 topics
0/10Wiki
Inputs used
topicsagents, ai, framework, llm, python, openai, harness
has_wikino
homepagehttps://openai.github.io/openai-agents-python/
docs_sitehttps://openai.github.io/openai-agents-python/
has_readmeyes
has_docs_diryes
has_descriptionyes

Security

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

63Moderate · 16% of overall

Security posture

61Moderate
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 — 28 out of 28 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
1.5/7.5Code-Review — Found 6/29 approved changesets -- score normalized to 2
2.5/2.5Contributors — project has 34 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 15 issue activity found in the last 90 days -- score normalized to 10
5/5Packaging — packaging workflow detected
3.5/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 7
0/5SAST — SAST tool is not run on all commits -- score normalized to 0
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 — 87 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated16
scorecard_versionv5.5.0
checks_inconclusive2
scorecard_aggregate6.1
Excluded from scoring (no data or not applicable): Branch-Protection, Signed-Releases. Remaining weights renormalized.

Dependency advisories

72Good
How it's scored
13.7/35Direct dependencies free of known advisories — 1 affected: mcp 1.26.0 (high 7.6)
0/25Indirect dependencies free of known advisories — transitive set not separable from development and test dependencies in this scope
40/40No advisories left outstanding — no advisory has been public longer than 90 days
Inputs used
sourceosv
advisories171
affected_packages17
assessed_packages199
unassessed_packages6
affected_by_severitycritical 3, high 5, moderate 2, low 1, unknown 6
direct_affected_packages1
Excluded from scoring (no data or not applicable): Indirect dependencies free of known advisories. Remaining weights renormalized. Matched 199 resolved dependencies against OSV. 6 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.

87Excellent · 4% of overall

Agent context & guidance

100Exceptional
How it's scored
45/45Agent instructions — AGENTS.md, CLAUDE.md, docs/agents.md, docs/ja/agents.md, docs/ko/agents.md, docs/ref/agent.md, docs/ref/realtime/agent.md, docs/zh/agents.md
15/15Machine-readable docs (llms.txt) — llms.txt present
40/40Legible commit history — 94 of 94 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtyes
llms_txt_url—
legible_history_share1
agent_instruction_filesAGENTS.md, CLAUDE.md, docs/agents.md, docs/ja/agents.md, docs/ko/agents.md, docs/ref/agent.md, docs/ref/realtime/agent.md, docs/zh/agents.md
agent_instruction_max_bytes24,753

Verify loop (build / test / typecheck)

76Good
How it's scored
18/18One-command bootstrap — Makefile, examples/sandbox/extensions/temporal/justfile
22/22Automated tests
0/11Lint / format config
11/11Static type checking — pyrightconfig.json, src/agents/py.typed, src/agents/sandbox/py.typed
10/10Reproducible environment — Dockerfile, lockfile
0/10Demonstrated agent practice — no agent-authored commits among the last 100
8/8Automated maintenance — 4 of the last 100 commits are automated dependency updates
7/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 7
Inputs used
has_nixno
has_testsyes
lockfilesuv.lock
has_dockerfileyes
typed_languageno
bootstrap_filesMakefile, examples/sandbox/extensions/temporal/justfile
has_devcontainerno
has_linter_configno
typecheck_configspyrightconfig.json, src/agents/py.typed, src/agents/sandbox/py.typed
agent_commit_share0
toolchain_manifests—
dependency_bot_commit_share0.04

Code legibility for models

79Good
How it's scored
27/45Type-checkable code — Python with type-check config (pyrightconfig.json, src/agents/py.typed, src/agents/sandbox/py.typed)
52.2/55Manageable file sizes — 43/852 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes287,207
source_files_sampled852
oversized_source_files43

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

28,384GitHub stars
98contributors
1,310commits, last 12 months
0days since last push
100releases
2bus factor
16open 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 19 authors (cap 12)
  • deps.dev does not index pypi:openai-agents@0.19.3; advisories assessed against the repository dependency graph instead
  • Advisory severity resolved for 120 of 171 advisories (lookup cap); the remainder are reported as unknown severity

More detail

Star and fork history 0 ★ / 4,442 ⇿
0Stars
4,442Forks
30Releases

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.

3,0003,5004,0004,5004,442822026-042026-062026-08
Major 0Minor 5Patch 25
OpenSSF Scorecard 6.1 / 10
6.1aggregate

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 · 2026-08-05 02:26 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-Tests28 out of 28 merged PRs checked by a CI test -- score normalized to 10
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
2Code-ReviewFound 6/29 approved changesets -- score normalized to 2
10Contributorsproject has 34 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 15 issue activity found in the last 90 days -- score normalized to 10
10Packagingpackaging workflow detected
7Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 7
0SASTSAST tool is not run on all commits -- score normalized to 0
10Security-Policysecurity policy file detected
n/aSigned-Releasesno releases found
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
0Vulnerabilities87 existing vulnerabilities detected
Direct dependencies 7
RegistryPackageVersion constraintManifest
PyPIopenai>=2.45.0,<3pyproject.toml
PyPIpydantic>=2.12.2, <3pyproject.toml
PyPIgriffelib>=2, <3pyproject.toml
PyPItyping-extensions>=4.12.2, <5pyproject.toml
PyPIrequests>=2.0, <3pyproject.toml
PyPIwebsockets>=15.0, <17pyproject.toml
PyPImcp>=1.19.0, <2pyproject.toml
All dependencies 205

Full resolved dependency set from the GitHub dependency graph: 9 direct and 196 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPIgriffelib2.0.1direct
PyPImcp1.26.0direct
PyPIopenai—direct
PyPIopenai2.45.0direct
PyPIpydantic2.12.3direct
PyPIrequests2.34.2direct
PyPItyping-extensions4.14.1direct
PyPIwebsockets—direct
PyPIwebsockets15.0.1direct
PyPIaiofiles24.1.0indirect
PyPIaiohappyeyeballs2.6.1indirect
PyPIaiohttp3.12.15indirect
PyPIaiohttp-retry2.9.1indirect
PyPIaiosignal1.4.0indirect
PyPIaiosqlite0.21.0indirect
PyPIannotated-doc0.0.4indirect
PyPIannotated-types0.7.0indirect
PyPIany-llm-sdk1.11.0indirect
PyPIanyio4.10.0indirect
PyPIasttokens3.0.0indirect
PyPIasync-timeout5.0.1indirect
PyPIasyncpg0.30.0indirect
PyPIattrs25.3.0indirect
PyPIbabel2.17.0indirect
PyPIbackports-asyncio-runner1.2.0indirect
PyPIbackports-datetime-fromisoformat2.0.3indirect
PyPIbackrefs5.9indirect
PyPIblaxel0.2.50indirect
PyPIboto31.42.75indirect
PyPIbotocore1.42.75indirect
PyPIbracex2.6indirect
PyPIcbor25.8.0indirect
PyPIcertifi2025.8.3indirect
PyPIcffi1.17.1indirect
PyPIcharset-normalizer3.4.3indirect
PyPIclick8.2.1indirect
PyPIcolorama0.4.6indirect
PyPIcoverage7.10.3indirect
PyPIcryptography45.0.7indirect
PyPIdapr1.16.0indirect
PyPIdaytona0.155.0indirect
PyPIdaytona-api-client0.155.0indirect
PyPIdaytona-api-client-async0.155.0indirect
PyPIdaytona-toolbox-api-client0.155.0indirect
PyPIdaytona-toolbox-api-client-async0.155.0indirect
PyPIdeprecated1.3.1indirect
PyPIdistro1.9.0indirect
PyPIdnspython2.8.0indirect
PyPIdocker7.1.0indirect
PyPIdockerfile-parse2.0.1indirect
PyPIe2b2.31.0indirect
PyPIe2b-code-interpreter2.8.1indirect
PyPIenvirons14.6.0indirect
PyPIeval-type-backport0.2.2indirect
PyPIevdev1.9.2indirect
PyPIexceptiongroup1.3.1indirect
PyPIexecnet2.1.2indirect
PyPIexecuting2.2.0indirect
PyPIfakeredis2.31.3indirect
PyPIfastapi—indirect
PyPIfastapi0.139.2indirect
PyPIfastuuid0.14.0indirect
PyPIfilelock3.18.0indirect
PyPIfrozenlist1.7.0indirect
PyPIfsspec2025.7.0indirect
PyPIghp-import2.1.0indirect
PyPIgoogleapis-common-protos1.70.0indirect
PyPIgraphviz0.21indirect
PyPIgreenlet3.2.4indirect
PyPIgrpcio1.76.0indirect
PyPIgrpcio-status1.67.1indirect
PyPIgrpclib0.4.9indirect
PyPIh110.16.0indirect
PyPIh24.3.0indirect
PyPIhf-xet1.1.7indirect
PyPIhpack4.1.0indirect
PyPIhttpcore1.0.9indirect
PyPIhttpx0.28.1indirect
PyPIhttpx-sse0.4.1indirect
PyPIhuggingface-hub0.34.4indirect
PyPIhyperframe6.1.0indirect
PyPIidna3.10indirect
PyPIimportlib-metadata8.7.0indirect
PyPIiniconfig2.1.0indirect
PyPIinline-snapshot0.27.2indirect
PyPIjinja23.1.6indirect
PyPIjiter0.10.0indirect
PyPIjmespath1.1.0indirect
PyPIjsonschema4.25.0indirect
PyPIjsonschema-specifications2025.4.1indirect
PyPIlinkify-it-py2.0.3indirect
PyPIlitellm1.83.0indirect
PyPImarkdown3.8.2indirect
PyPImarkdown-it-py4.0.0indirect
PyPImarkupsafe3.0.2indirect
PyPImarshmallow4.2.2indirect
PyPImdit-py-plugins0.5.0indirect
PyPImdurl0.1.2indirect
PyPImergedeep1.3.4indirect
PyPImkdocs1.6.1indirect
PyPImkdocs-autorefs1.4.2indirect
PyPImkdocs-get-deps0.2.0indirect
PyPImkdocs-material9.6.16indirect
PyPImkdocs-material-extensions1.3.1indirect
PyPImkdocs-static-i18n1.3.0indirect
PyPImkdocstrings1.0.3indirect
PyPImkdocstrings-python2.0.3indirect
PyPImodal1.4.3indirect
PyPImultidict6.6.4indirect
PyPImypy1.17.1indirect
PyPImypy-extensions1.1.0indirect
PyPInexus-rpc1.4.0indirect
PyPInodeenv1.10.0indirect
PyPInumpy2.2.6indirect
PyPInumpy2.3.2indirect
PyPIobstore0.8.2indirect
PyPIopenai-agents—indirect
PyPIopenai-agents0.19.3indirect
PyPIopenresponses-types2.3.0.post1indirect
PyPIopentelemetry-api1.40.0indirect
PyPIopentelemetry-exporter-otlp-proto-common1.40.0indirect
PyPIopentelemetry-exporter-otlp-proto-http1.40.0indirect
PyPIopentelemetry-instrumentation0.61b0indirect
PyPIopentelemetry-instrumentation-aiohttp-client0.61b0indirect
PyPIopentelemetry-proto1.40.0indirect
PyPIopentelemetry-sdk1.40.0indirect
PyPIopentelemetry-semantic-conventions0.61b0indirect
PyPIopentelemetry-util-http0.61b0indirect
PyPIpackaging25.0indirect
PyPIpaginate0.5.7indirect
PyPIpathspec0.12.1indirect
PyPIplatformdirs4.3.8indirect
PyPIplaywright1.50.0indirect
PyPIpluggy1.6.0indirect
PyPIpropcache0.3.2indirect
PyPIprotobuf5.29.5indirect
PyPIpycparser2.22indirect
PyPIpydantic-core2.41.4indirect
PyPIpydantic-settings2.10.1indirect
PyPIpyee12.1.1indirect
PyPIpygments2.19.2indirect
PyPIpyjwt2.10.1indirect
PyPIpymdown-extensions10.16.1indirect
PyPIpymongo4.16.0indirect
PyPIpynput1.8.1indirect
PyPIpyobjc-core11.1indirect
PyPIpyobjc-framework-applicationservices11.1indirect
PyPIpyobjc-framework-cocoa11.1indirect
PyPIpyobjc-framework-coretext11.1indirect
PyPIpyobjc-framework-quartz11.1indirect
PyPIpyright1.1.408indirect
PyPIpytest8.4.1indirect
PyPIpytest-asyncio1.1.0indirect
PyPIpytest-mock3.14.1indirect
PyPIpytest-xdist3.8.0indirect
PyPIpython-dateutil2.9.0.post0indirect
PyPIpython-dotenv—indirect
PyPIpython-dotenv1.1.1indirect
PyPIpython-multipart0.0.20indirect
PyPIpython-xlib0.33indirect
PyPIpywin32311indirect
PyPIpyyaml6.0.2indirect
PyPIpyyaml-env-tag1.1indirect
PyPIredis7.0.1indirect
PyPIreferencing0.36.2indirect
PyPIregex2025.7.34indirect
PyPIrich14.3.3indirect
PyPIrpds-py0.27.0indirect
PyPIruff0.9.2indirect
PyPIrunloop-api-client1.16.0indirect
PyPIs3transfer0.16.0indirect
PyPIsix1.17.0indirect
PyPIsniffio1.3.1indirect
PyPIsortedcontainers2.4.0indirect
PyPIsounddevice0.5.2indirect
PyPIsqlalchemy2.0.43indirect
PyPIsse-starlette3.0.2indirect
PyPIstarlette0.47.2indirect
PyPIsynchronicity0.12.2indirect
PyPItemporalio1.26.0indirect
PyPItestcontainers4.12.0indirect
PyPItextual8.2.3indirect
PyPItiktoken0.12.0indirect
PyPItokenizers0.21.4indirect
PyPItoml0.10.2indirect
PyPItomli2.2.1indirect
PyPItqdm4.67.1indirect
PyPItypes-certifi2021.10.8.3indirect
PyPItypes-protobuf6.32.1.20260221indirect
PyPItypes-pynput1.8.1.20250809indirect
PyPItypes-toml0.10.8.20240310indirect
PyPItyping-inspection0.4.2indirect
PyPIuc-micro-py1.0.3indirect
PyPIurllib32.5.0indirect
PyPIuuid-utils0.14.1indirect
PyPIuvicorn—indirect
PyPIuvicorn0.35.0indirect
PyPIvercel0.5.6indirect
PyPIvercel-workers0.0.16indirect
PyPIwatchdog6.0.0indirect
PyPIwatchfiles1.1.1indirect
PyPIwcmatch10.1indirect
PyPIwrapt1.17.3indirect
PyPIyarl1.20.1indirect
PyPIzipp3.23.0indirect
Dependency advisories 17

This repository publishes no package the index resolves, so its own dependency graph was assessed — 199 packages, which also include development and test pins that never ship: 17 carry known advisories, of which 1 are direct. 6 could not be assessed — no resolved version, an unsupported ecosystem, or beyond the reported package list.

PackageVersionRelationSeverityAdvisoriesFixed in
aiohttp3.12.15indirectcritical643.14.3
cryptography45.0.7indirectcritical1350.0.0
litellm1.83.0indirectcritical201.84.0
mcp1.26.0directhigh61.28.1
cbor25.8.0indirecthigh25.9.0
click8.2.1indirecthigh18.3.3
protobuf5.29.5indirecthigh26.33.5
pyjwt2.10.1indirecthigh132.13.0
filelock3.18.0indirectmoderate43.20.3
idna3.10indirectmoderate23.15
pygments2.19.2indirectlow22.20.0
pymdown-extensions10.16.1indirectunknown4—
pytest8.4.1indirectunknown2—
python-dotenv1.1.1indirectunknown2—
python-multipart0.0.20indirectunknown14—
starlette0.47.2indirectunknown12—
urllib32.5.0indirectunknown8—

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 openai/openai-agents-python. Read them side by side →

99langchain-ai/langgraphBuild resilient agents.Exceptional98langchain-ai/langchainThe agent engineering platform.Exceptional100deepset-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.Exceptional98Significant-Gravitas/AutoGPTAutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.Exceptional98ModelEngine-Group/nexentNexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.Exceptional98mem0ai/mem0Universal memory layer for AI AgentsExceptional

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.