Public record
Software health reportschema 0.34.0 · metrics 2.10.0 · 2026-08-25 17:39 UTC

anthropics / anthropic-sdk-csharp

Access to Anthropic's safety-first language model APIs in C#

C#MIT★ 317 stars⑂ 101 forkssince Aug 2025View on GitHub ↗

anthropics/anthropic-sdk-csharp holds a health index of 91 out of 100, placing it in the Excellent band. It scores highest on Vitality (97/100) and lowest on Engineering Quality (50/100). It was last updated today. 4 contributors account for most of its recent work.

91
overall / 100
Excellent

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.

91
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 77 is calibrated to 91 on the published index scale (record calibration 2026-08-02).

Ownership

AnthropicOrganization · verified domain
83,354 followers102 public repossince Dec 2020

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

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publishTags
NuGetAnthropic12.42.1-650 days agosdkapihttplibrary
NuGetAnthropic.Aws0.5.2-76 days agosdkapihttplibrary
NuGetAnthropic.Mcp0.1.0-1103 days agosdkapihttplibrary
NuGetAnthropic.Vertex0.5.3-96 days agosdkapihttplibrary
NuGetAnthropic.Bedrock0.12.0-166 days agosdkapihttplibrary
NuGetAnthropic.Foundry0.7.1-1061 days agosdkapihttplibrary
NuGetAnthropic.GoogleCloud0.1.0-139 days agosdkapihttplibrary

Metrics by category

Vitality

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

97Exceptional · 21% of overall
How it's scored
36/36Push recencylast push 0 days ago
31.2/36Commit cadence45/52 weeks with commits
18/18Commit volume398 commits in the last year
10/10OpenSSF Scorecard: Maintained30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year398
human_commit_share0.21
days_since_last_push0
active_weeks_last_year45

Release discipline

100Exceptional
How it's scored
27/27Ships releases100 releases published
36/36Release recencylatest release 0 days ago
27/27Release cadencea release every ~3.6 days
0/10OpenSSF Scorecard: Signed-Releasesno data
Inputs used
releases_count100
latest_release_tagAnthropic-v12.42.1
releases_from_tagsno
days_since_latest_release0
mean_days_between_releases3.6
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?

71Good · 17% of overall
How it's scored
40.5/60Stars317 stars
16.7/25Forks101 forks
4.3/15Watchers7 watchers
Inputs used
forks101
stars317
watchers7
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history
How it's scored
22.5/22.5README
22.5/22.5Licenserecognized license (MIT)
18/18CONTRIBUTING guide
0/13.5Code of conduct
0/7.2Issue template
0/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges1
has_contributingyes
has_issue_templateno
has_code_of_conductno
readme_badge_servicesshields.io
has_pull_request_templateno
How it's scored
68.7/80Total downloads4,112,880 downloads all-time across nuget
0/20Registry dependentsnot reported by this ecosystem
Inputs used
packagesAnthropic, Anthropic.Aws, Anthropic.Mcp, Anthropic.Vertex, Anthropic.Bedrock, Anthropic.Foundry, Anthropic.GoogleCloud
dependents
ecosystemsnuget
total_downloads4,112,880
monthly_downloads
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?

91Excellent · 23% of overall
How it's scored
43.2/54Bus factor4 contributor(s) cover half of all commits
17.2/22.5Commit distributiontop contributor authored 24% of commits
13.5/13.5Contributor breadth28 contributors
10/10OpenSSF Scorecard: Contributorsproject has 7 contributing companies or organizations
Inputs used
bus_factor4
contributors_sampled28
top_contributor_share0.236
How it's scored
38.4/42Issue resolution92% of issues closed
23.5/30PR acceptance126/161 decided PRs merged
0/13Newcomer PR acceptanceno first-time contributor's PR decided in 30d
0/15OpenSSF Scorecard: Code-Reviewno data
Inputs used
merged_prs126
open_issues7
closed_issues75
prs_merged_7d0
prs_decided_7d0
prs_merged_30d2
prs_decided_30d2
issue_closed_ratio0.915
closed_unmerged_prs35
first_time_authors_30d0
first_time_prs_merged_30d0
first_time_prs_decided_30d0
Excluded from scoring (no data or not applicable): Newcomer PR acceptance, OpenSSF Scorecard: Code-Review. Remaining weights renormalized.
How it's scored
30/30Ownership backingorganization-owned
20/20Verified domain
25/25Owner reach83,354 followers of anthropics
24.4/25Track record102 public repos, account ~5 yr old
Inputs used
followers83,354
owner_typeOrganization
is_verifiedyes
owner_loginanthropics
public_repos102
account_age_days2,074

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable7 package(s) on nuget
35/35Publish recencylatest publish 0 days ago
20/20Version history65 published versions
20/20Not deprecatedactive, not deprecated or yanked
Inputs used
packagesAnthropic, Anthropic.Aws, Anthropic.Mcp, Anthropic.Vertex, Anthropic.Bedrock, Anthropic.Foundry, Anthropic.GoogleCloud
ecosystemsnuget
any_deprecatedno
min_days_since_publish0

Engineering Quality

Are baseline engineering and documentation practices in place?

50Moderate · 19% of overall
How it's scored
24/24CI workflows4 workflow(s)
0/24Tests present
0/16Linter config
0/9.6Pre-commit hooks
6.4/6.4.editorconfig
20/20OpenSSF Scorecard: CI-Tests3 out of 3 merged PRs checked by a CI test -- score normalized to 10
Inputs used
has_ciyes
has_testsno
has_editorconfigyes
has_linter_configno
has_precommit_configno

Documentation

50Moderate
How it's scored
30/30README
0/25Documentation directory
0/15Documentation / homepage site
10/10Repository description
0/10Topics
10/10Wiki
Inputs used
topics
has_wikiyes
homepage
docs_site
has_readmeyes
has_docs_dirno
has_descriptionyes

Security

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

71Good · 16% of overall
How it's scored
7.5/7.5Binary-Artifactsno binaries found in the repo
4.5/7.5Branch-Protectionbranch protection is not maximal on development and all release branches
2.5/2.5CI-Tests3 out of 3 merged PRs checked by a CI test -- score normalized to 10
0/2.5CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
0/7.5Code-Reviewno data
2.5/2.5Contributorsproject has 7 contributing companies or organizations
10/10Dangerous-Workflowno dangerous workflow patterns detected
0/7.5Dependency-Update-Toolno update tool detected
0/5Fuzzingproject is not fuzzed
2.5/2.5Licenselicense file detected
7.5/7.5Maintained30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10
5/5Packagingpackaging workflow detected
3.5/5Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 7
0/5SASTSAST tool is not run on all commits -- score normalized to 0
5/5Security-Policysecurity policy file detected
0/7.5Signed-Releasesno data
0/7.5Token-Permissionsdetected GitHub workflow tokens with excessive permissions
7.5/7.5Vulnerabilities0 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated16
scorecard_versionv5.5.0
checks_inconclusive2
scorecard_aggregate6.4
Excluded from scoring (no data or not applicable): Code-Review, Signed-Releases. Remaining weights renormalized.

Dependency advisories

100Exceptional
How it's scored
35/35Direct dependencies free of known advisoriesno direct dependency carries a known advisory
0/25Indirect dependencies free of known advisoriestransitive set not separable from development and test dependencies in this scope
0/40No advisories left outstandingno advisory carries a publication date
Inputs used
sourceosv
advisories0
affected_packages0
assessed_packages24
unassessed_packages0
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 24 resolved dependencies against OSV. 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.

80Excellent · 4% of overall
How it's scored
45/45Agent instructionsCLAUDE.md
15/15Machine-readable docs (llms.txt)llms.txt served by the project website (https://docs.anthropic.com/llms.txt)
40/40Legible commit history21 of 21 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtyes
llms_txt_urlhttps://docs.anthropic.com/llms.txt
legible_history_share1
agent_instruction_filesCLAUDE.md
agent_instruction_max_bytes19,761
How it's scored
12.6/18One-command bootstrapexamples/ChatClientExample/ChatClientExample.csproj, examples/CredentialsExample/CredentialsExample.csproj, examples/FallbacksExample/FallbacksExample.csproj (toolchain convention, no task runner)
0/22Automated tests
0/11Lint / format config
11/11Static type checkingC# (statically typed)
10/10Reproducible environmentdevcontainer, lockfile
10/10Demonstrated agent practice10 of the last 100 commits agent-authored or agent-credited
0/8Automated maintenanceno automated dependency updates observed
7/10OpenSSF Scorecard: Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 7
Inputs used
has_nixno
has_testsno
lockfilespackages.lock.json
has_dockerfileno
typed_languageyes
bootstrap_files
has_devcontaineryes
has_linter_configno
typecheck_configs
agent_commit_share0.1
toolchain_manifestsexamples/ChatClientExample/ChatClientExample.csproj, examples/CredentialsExample/CredentialsExample.csproj, examples/FallbacksExample/FallbacksExample.csproj, examples/ManagedAgentsComprehensiveExample/ManagedAgentsComprehensiveExample.csproj, examples/ManagedAgentsExample/ManagedAgentsExample.csproj, examples/ManagedAgentsStreamingDeltasExample/ManagedAgentsStreamingDeltasExample.csproj, examples/ManagedAgentsWithFilesExample/ManagedAgentsWithFilesExample.csproj, examples/McpToolRunnerExample/McpToolRunnerExample.csproj, examples/MemoryToolExample/MemoryToolExample.csproj, examples/MessagesExample.Bedrock/MessagesExample.Bedrock.csproj, examples/MessagesExample.Foundry/MessagesExample.Foundry.csproj, examples/MessagesExample.Vertex/MessagesExample.Vertex.csproj, examples/MessagesExample/MessagesExample.csproj, examples/MessagesStreamingExample/MessagesStreamingExample.csproj, examples/StreamingAggregationBetaExample/StreamingAggregationBetaExample.csproj, examples/StreamingAggregationExample/StreamingAggregationExample.csproj, examples/StructuredOutputExample/StructuredOutputExample.csproj, examples/ThinkingExample/ThinkingExample.csproj, examples/ThinkingStreamingExample/ThinkingStreamingExample.csproj, examples/ToolRunnerExample/ToolRunnerExample.csproj, src/Anthropic.Aws/Anthropic.Aws.csproj, src/Anthropic.Bedrock/Anthropic.Bedrock.csproj, src/Anthropic.Foundry/Anthropic.Foundry.csproj, src/Anthropic.GoogleCloud/Anthropic.GoogleCloud.csproj, src/Anthropic.Mcp/Anthropic.Mcp.csproj, src/Anthropic.Tests/Anthropic.Tests.csproj, src/Anthropic.Vertex/Anthropic.Vertex.csproj, src/Anthropic/Anthropic.csproj
dependency_bot_commit_share0
How it's scored
45/45Type-checkable codeC# (statically typed)
54.5/55Manageable file sizes24/2,659 source files over 60KB
Inputs used
primary_languageC#
largest_source_bytes343,306
source_files_sampled2,659
oversized_source_files24
How it's scored
0/40API schema (OpenAPI/GraphQL/proto)not applicable to this kind of software
20/20MCP server
40/40Runnable examplesexamples
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

317GitHub stars
28contributors
398commits, last 12 months
0days since last push
100releases
4bus factor
7open issues
package ecosystems

Data collection warnings

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

More detail

Star and fork history 0 ★ / 101 ⇿
0Stars
101Forks
94Releases

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.

0204060801009932025-102026-032026-08
Major 1Minor 2Patch 0
OpenSSF Scorecard 6.4 / 10
6.4aggregate

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 · 2026-08-25 17:38 UTC

10Binary-Artifactsno binaries found in the repo
6Branch-Protectionbranch protection is not maximal on development and all release branches
10CI-Tests3 out of 3 merged PRs checked by a CI test -- score normalized to 10
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
n/aCode-ReviewFound no human activity in the last 3 changesets
10Contributorsproject has 7 contributing companies or organizations
10Dangerous-Workflowno dangerous workflow patterns detected
0Dependency-Update-Toolno update tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
10Maintained30 commit(s) and 0 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
10Vulnerabilities0 existing vulnerabilities detected
Direct dependencies 38
RegistryPackageVersion constraintManifest
NuGetAWSSDK.Core4.0.3.3src/Anthropic.Aws/Anthropic.Aws.csproj
NuGetAWSSDK.SSO4.0.2.5src/Anthropic.Aws/Anthropic.Aws.csproj
NuGetAWSSDK.SSOOIDC4.0.3.6src/Anthropic.Aws/Anthropic.Aws.csproj
NuGetMicrosoft.Bcl.Memory10.0.4src/Anthropic.Aws/Anthropic.Aws.csproj
NuGetSystem.Collections.Immutable8.0.0src/Anthropic.Aws/Anthropic.Aws.csproj
NuGetSystem.Threading.Tasks.Extensions4.6.3src/Anthropic.Aws/Anthropic.Aws.csproj
NuGetMicrosoft.Bcl.Memory10.0.4src/Anthropic.Bedrock/Anthropic.Bedrock.csproj
NuGetAWSSDK.Core4.0.3.3src/Anthropic.Bedrock/Anthropic.Bedrock.csproj
NuGetAWSSDK.SSO4.0.2.5src/Anthropic.Bedrock/Anthropic.Bedrock.csproj
NuGetAWSSDK.SSOOIDC4.0.3.6src/Anthropic.Bedrock/Anthropic.Bedrock.csproj
NuGetSystem.Collections.Immutable8.0.0src/Anthropic.Bedrock/Anthropic.Bedrock.csproj
NuGetSystem.Threading.Tasks.Extensions4.6.3src/Anthropic.Bedrock/Anthropic.Bedrock.csproj
NuGetAzure.Identity1.17.0src/Anthropic.Foundry/Anthropic.Foundry.csproj
NuGetSystem.Collections.Immutable8.0.0src/Anthropic.Foundry/Anthropic.Foundry.csproj
NuGetSystem.Threading.Tasks.Extensions4.6.3src/Anthropic.Foundry/Anthropic.Foundry.csproj
NuGetSystem.Collections.Immutable8.0.0src/Anthropic.GoogleCloud/Anthropic.GoogleCloud.csproj
NuGetSystem.Threading.Tasks.Extensions4.6.3src/Anthropic.GoogleCloud/Anthropic.GoogleCloud.csproj
NuGetGoogle.Apis.Oauth2.v21.68.0.1869src/Anthropic.GoogleCloud/Anthropic.GoogleCloud.csproj
NuGetModelContextProtocol.Core1.2.0src/Anthropic.Mcp/Anthropic.Mcp.csproj
NuGetSystem.Memory4.6.3src/Anthropic.Mcp/Anthropic.Mcp.csproj
NuGetSystem.Threading.Tasks.Extensions4.6.3src/Anthropic.Mcp/Anthropic.Mcp.csproj
NuGetcoverlet.collector6.0.4src/Anthropic.Tests/Anthropic.Tests.csproj
NuGetMicrosoft.NET.Test.Sdk18.0.1src/Anthropic.Tests/Anthropic.Tests.csproj
NuGetMoq4.20.72src/Anthropic.Tests/Anthropic.Tests.csproj
NuGetSystem.Net.Http4.3.4src/Anthropic.Tests/Anthropic.Tests.csproj
NuGetSystem.Text.RegularExpressions4.3.1src/Anthropic.Tests/Anthropic.Tests.csproj
NuGetxunit.v33.2.1src/Anthropic.Tests/Anthropic.Tests.csproj
NuGetxunit.analyzers1.26.0src/Anthropic.Tests/Anthropic.Tests.csproj
NuGetxunit.runner.visualstudio3.1.5src/Anthropic.Tests/Anthropic.Tests.csproj
NuGetSystem.Collections.Immutable8.0.0src/Anthropic.Vertex/Anthropic.Vertex.csproj
NuGetSystem.Threading.Tasks.Extensions4.6.3src/Anthropic.Vertex/Anthropic.Vertex.csproj
NuGetGoogle.Apis.Oauth2.v21.68.0.1869src/Anthropic.Vertex/Anthropic.Vertex.csproj
NuGetSystem.Text.Json10.0.6src/Anthropic/Anthropic.csproj
NuGetSystem.Net.ServerSentEvents10.0.1src/Anthropic/Anthropic.csproj
NuGetMicrosoft.Extensions.AI.Abstractions10.5.1src/Anthropic/Anthropic.csproj
NuGetMicrosoft.SourceLink.GitHub8.0.0src/Anthropic/Anthropic.csproj
NuGetSystem.Collections.Immutable8.0.0src/Anthropic/Anthropic.csproj
NuGetSystem.Threading.Tasks.Extensions4.6.3src/Anthropic/Anthropic.csproj
All dependencies 24

Full resolved dependency set from the GitHub dependency graph: 22 direct and 2 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
NuGetAWSSDK.Core4.0.3.3direct
NuGetAWSSDK.SSO4.0.2.5direct
NuGetAWSSDK.SSOOIDC4.0.3.6direct
NuGetAzure.Identity1.17.0direct
NuGetcoverlet.collector6.0.4direct
NuGetGoogle.Apis.Oauth2.v21.68.0.1869direct
NuGetMicrosoft.Bcl.Memory10.0.4direct
NuGetMicrosoft.Extensions.AI.Abstractions10.5.1direct
NuGetMicrosoft.NET.Test.Sdk18.0.1direct
NuGetMicrosoft.SourceLink.GitHub8.0.0direct
NuGetModelContextProtocol.Core1.2.0direct
NuGetMoq4.20.72direct
NuGetSystem.Collections.Immutable8.0.0direct
NuGetSystem.Memory4.6.3direct
NuGetSystem.Net.Http4.3.4direct
NuGetSystem.Net.ServerSentEvents10.0.1direct
NuGetSystem.Text.Json10.0.6direct
NuGetSystem.Text.RegularExpressions4.3.1direct
NuGetSystem.Threading.Tasks.Extensions4.6.3direct
NuGetxunit.analyzers1.26.0direct
NuGetxunit.runner.visualstudio3.1.5direct
NuGetxunit.v33.2.1direct
NuGetMicrosoft.Extensions.AI10.0.0indirect
NuGetModelContextProtocol1.2.0indirect
Dependency advisories 0

This repository publishes no package the index resolves, so its own dependency graph was assessed — 24 packages, which also include development and test pins that never ship: 0 carry known advisories, of which 0 are direct.

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.

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 statisticsNuGet.