Public record
Software health reportschema 0.34.0 · metrics 2.10.0 · 2026-09-18 09:28 UTC

ypollak2 / llm-router

Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.

PythonMIT★ 81 stars⑂ 11 forkssince Mar 2026View on GitHub ↗
KindCommand-line toolLibraryMCP serverNetwork servicehow this is determined
#ai-routing#anthropic#claude#claude-code#cost-optimization#gemini#litellm#llm#llm-router#mcp-server#model-router#ollama#openai

ypollak2/llm-router holds a health index of 77 out of 100, placing it in the Good band. It scores highest on Vitality (83/100) and lowest on Sustainability & Governance (50/100). It was last updated today. A single contributor accounts for most of its recent work.

77
overall / 100
Good

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.

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

Ownership

Yali PollakPersonal account
7 followers21 public repossince Dec 2021

This repository is owned by a personal account. A single-owner project carries more continuity risk than an organization-backed one.

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publishTags
PyPIllm-routing13.3.23,033731 day agoaiclaudeclaude-codeclaude-desktopcost-optimizationgeminilitellmllmllm-routermcpmcp-servermodel-routingopenairouter
npmllm-routing13.3.21,10781 day agollmrouterclaudeclaude-codecodexcursormcpcost-optimizationquotaollama

Metrics by category

Vitality

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

83Excellent · 21% of overall

Development activity

78Good
How it's scored
36/36Push recency — last push 0 days ago
13.8/36Commit cadence — 20/52 weeks with commits
18/18Commit volume — 880 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 30 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year880
human_commit_share0.98
days_since_last_push0
active_weeks_last_year20

Release discipline

90Excellent
How it's scored
27/27Ships releases — 100 releases published
36/36Release recency — latest release 1 days ago
27/27Release cadence — a release every ~1.7 days
0/10OpenSSF Scorecard: Signed-Releases — Project has not signed or included provenance with any releases.
Inputs used
releases_count100
latest_release_tagv13.3.2
releases_from_tagsno
days_since_latest_release1
mean_days_between_releases1.7

Community & Adoption

Does the project have users, downloads, attention, and a welcoming setup for contributors?

55Moderate · 17% of overall

Popularity & adoption

39Weak
How it's scored
30.9/60Stars — 81 stars
8.3/25Forks — 11 forks
0/15Watchers — 2 watchers
Inputs used
forks11
stars81
watchers2
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

Community health

70Good
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
0/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges7
has_contributingyes
has_issue_templateno
has_code_of_conductno
readme_badge_servicesshields.io
has_pull_request_templateno

Ecosystem adoption (downloads)

60Moderate
How it's scored
48.2/80Monthly downloads — 4,140 downloads/month across npm, pypi
0/20Registry dependents — not reported by this ecosystem
Inputs used
packagesllm-routing, llm-routing
dependents—
ecosystemsnpm, pypi
total_downloads—
monthly_downloads4,140
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?

50Moderate · 23% of overall

Maintainer resilience (bus factor)

10Critical
How it's scored
9/54Bus factor — 1 contributor(s) cover half of all commits
0/22.5Commit distribution — top contributor authored 100% of commits
1.4/13.5Contributor breadth — 1 contributors
0/10OpenSSF Scorecard: Contributors — project has 0 contributing companies or organizations -- score normalized to 0
Inputs used
bus_factor1
contributors_sampled1
top_contributor_share1

Issue & PR responsiveness

63Moderate
How it's scored
39.5/42Issue resolution — 94% of issues closed
23.1/30PR acceptance — 64/83 decided PRs merged
0/13Newcomer PR acceptance — 0/1 first-time contributors' PRs merged in 30d
0/15OpenSSF Scorecard: Code-Review — Found 0/10 approved changesets -- score normalized to 0
Inputs used
merged_prs64
open_issues3
closed_issues47
prs_merged_7d4
prs_decided_7d4
prs_merged_30d52
prs_decided_30d53
issue_closed_ratio0.94
closed_unmerged_prs19
first_time_authors_30d1
first_time_prs_merged_30d0
first_time_prs_decided_30d1

Ownership & stewardship

45Weak
How it's scored
10/30Ownership backing — personal (user) account
0/20Verified domain — not applicable to user accounts
6.5/25Owner reach — 7 followers of ypollak2
19.3/25Track record — 21 public repos, account ~4 yr old
Inputs used
followers7
owner_typeUser
is_verified—
owner_loginypollak2
public_repos21
account_age_days1,743
Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 2 package(s) on npm, pypi
35/35Publish recency — latest publish 1 days ago
20/20Version history — 73 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagesllm-routing, llm-routing
ecosystemsnpm, pypi
any_deprecatedno
min_days_since_publish1

Engineering Quality

Are baseline engineering and documentation practices in place?

80Excellent · 19% of overall

Engineering practices

84Excellent
How it's scored
24/24CI workflows — 7 workflow(s)
24/24Tests present
16/16Linter config — pyproject.toml ([tool.ruff])
0/9.6Pre-commit hooks
0/6.4.editorconfig
20/20OpenSSF Scorecard: CI-Tests — 4 out of 4 merged PRs checked by a CI test -- score normalized to 10
Inputs used
has_ciyes
has_testsyes
has_editorconfigno
has_linter_configyes
has_precommit_configno

Documentation

75Good
How it's scored
30/30README
25/25Documentation directory
0/15Documentation / homepage site
10/10Repository description
10/10Topics — 13 topics
0/10Wiki
Inputs used
topicsai-routing, anthropic, claude, claude-code, cost-optimization, gemini, litellm, llm, llm-router, mcp-server, model-router, ollama, openai
has_wikino
homepage—
docs_site—
has_readmeyes
has_docs_diryes
has_descriptionyes

Security

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

60Moderate · 16% of overall

Security posture

50Moderate
How it's scored
7.5/7.5Binary-Artifacts — no binaries found in the repo
2.2/7.5Branch-Protection — branch protection is not maximal on development and all release branches
2.5/2.5CI-Tests — 4 out of 4 merged PRs checked by a CI test -- score normalized to 10
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
0/7.5Code-Review — Found 0/10 approved changesets -- score normalized to 0
0/2.5Contributors — project has 0 contributing companies or organizations -- score normalized to 0
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 30 issue activity found in the last 90 days -- score normalized to 10
5/5Packaging — packaging workflow detected
3/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 6
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 — Project has not signed or included provenance with any releases.
0/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
0/7.5Vulnerabilities — 90 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated18
scorecard_versionv5.5.0
checks_inconclusive0
scorecard_aggregate5

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_packages73
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:llm-routing@13.3.2 runtime dependency closure — what installing the published package pulls in — 73 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.

63Moderate · 4% of overall

Agent context & guidance

85Excellent
How it's scored
45/45Agent instructions — .github/copilot-instructions.md
0/15Machine-readable docs (llms.txt)
40/40Legible commit history — 98 of 98 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtno
llms_txt_url—
legible_history_share1
agent_instruction_files.github/copilot-instructions.md
agent_instruction_max_bytes3,334

Verify loop (build / test / typecheck)

67Good
How it's scored
0/18One-command bootstrap
22/22Automated tests
11/11Lint / format config — pyproject.toml ([tool.ruff])
0/11Static type checking
10/10Reproducible environment — lockfile
10/10Demonstrated agent practice — 83 of the last 100 commits agent-authored or agent-credited
8/8Automated maintenance — 2 of the last 100 commits are automated dependency updates
6/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 6
Inputs used
has_nixno
has_testsyes
lockfilesuv.lock
has_dockerfileno
typed_languageno
bootstrap_files—
has_devcontainerno
has_linter_configyes
typecheck_configs—
agent_commit_share0.83
toolchain_manifests—
dependency_bot_commit_share0.02

Code legibility for models

54Moderate
How it's scored
0/45Type-checkable code — Python without a type-check config
54.3/55Manageable file sizes — 16/1,239 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes255,816
source_files_sampled1,239
oversized_source_files16

Machine-readable interfaces

20At Risk
How it's scored
0/40API schema (OpenAPI/GraphQL/proto)
20/20MCP server
0/40Runnable examples
Inputs used
example_dirs—
has_mcp_signalyes
api_schema_files—
interfaces_expected_ofnetwork-service

Key facts

81GitHub stars
1contributors
880commits, last 12 months
0days since last push
100releases
1bus factor
3open issues
npm, PyPIpackage ecosystems

Data collection warnings

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

More detail

Star and fork history 0 ★ / 11 ⇿
0Stars
11Forks
84Releases

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.

0246810121112026-042026-062026-08
Major 8Minor 31Patch 45
OpenSSF Scorecard 5.0 / 10
5.0aggregate

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 · 2026-09-18 09:28 UTC

10Binary-Artifactsno binaries found in the repo
3Branch-Protectionbranch protection is not maximal on development and all release branches
10CI-Tests4 out of 4 merged PRs checked by a CI test -- score normalized to 10
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
0Code-ReviewFound 0/10 approved changesets -- score normalized to 0
0Contributorsproject has 0 contributing companies or organizations -- score normalized to 0
10Dangerous-Workflowno dangerous workflow patterns detected
10Dependency-Update-Toolupdate tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
10Maintained30 commit(s) and 30 issue activity found in the last 90 days -- score normalized to 10
10Packagingpackaging workflow detected
6Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 6
0SASTSAST tool is not run on all commits -- score normalized to 0
10Security-Policysecurity policy file detected
0Signed-ReleasesProject has not signed or included provenance with any releases.
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
0Vulnerabilities90 existing vulnerabilities detected
Direct dependencies 9
RegistryPackageVersion constraintManifest
PyPImcp>=2.0.0,<3.0.0pyproject.toml
PyPIlitellm>=1.50.0pyproject.toml
PyPIpydantic>=2.0pyproject.toml
PyPIpydantic-settings>=2.0pyproject.toml
PyPIaiosqlite>=0.20.0pyproject.toml
PyPIaiohttp>=3.9.0pyproject.toml
PyPIstructlog>=24.4.0pyproject.toml
PyPIfastapi>=0.100.0pyproject.toml
PyPIuvicorn>=0.24.0pyproject.toml
All dependencies 133

Full resolved dependency set from the GitHub dependency graph: 18 direct and 115 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPIaiohttp—direct
PyPIaiohttp3.13.4direct
PyPIaiosqlite—direct
PyPIaiosqlite0.22.1direct
PyPIfastapi—direct
PyPIfastapi0.135.3direct
PyPIlitellm—direct
PyPIlitellm1.82.6direct
PyPImcp—direct
PyPImcp2.0.0direct
PyPIpydantic—direct
PyPIpydantic2.12.5direct
PyPIpydantic-settings—direct
PyPIpydantic-settings2.13.1direct
PyPIstructlog—direct
PyPIstructlog25.5.0direct
PyPIuvicorn—direct
PyPIuvicorn0.42.0direct
PyPIagno—indirect
PyPIagno2.5.14indirect
PyPIaiohappyeyeballs2.6.1indirect
PyPIaiosignal1.4.0indirect
PyPIannotated-doc0.0.4indirect
PyPIannotated-types0.7.0indirect
PyPIanyio4.13.0indirect
PyPIattrs26.1.0indirect
PyPIcertifi2026.2.25indirect
PyPIcffi2.0.0indirect
PyPIcharset-normalizer3.4.6indirect
PyPIclick8.3.1indirect
PyPIcolorama0.4.6indirect
PyPIcryptography46.0.6indirect
PyPIdistro1.9.0indirect
PyPIdocstring-parser0.17.0indirect
PyPIexecnet2.1.2indirect
PyPIfastuuid0.14.0indirect
PyPIfilelock3.25.2indirect
PyPIfrozenlist1.8.0indirect
PyPIfsspec2026.3.0indirect
PyPIgitdb4.0.12indirect
PyPIgitpython3.1.46indirect
PyPIgoogleapis-common-protos1.74.0indirect
PyPIgrpcio1.80.0indirect
PyPIh110.16.0indirect
PyPIh24.3.0indirect
PyPIhatchling—indirect
PyPIhf-xet1.4.2indirect
PyPIhpack4.1.0indirect
PyPIhttpcore1.0.9indirect
PyPIhttpcore22.11.0indirect
PyPIhttpx—indirect
PyPIhttpx0.28.1indirect
PyPIhttpx22.11.0indirect
PyPIhttpx2-jsfetch1.0indirect
PyPIhuggingface-hub1.8.0indirect
PyPIhyperframe6.1.0indirect
PyPIhypothesis6.165.10indirect
PyPIidna3.19indirect
PyPIimportlib-metadata8.7.1indirect
PyPIiniconfig2.3.0indirect
PyPIjinja23.1.6indirect
PyPIjiter0.13.0indirect
PyPIjsonschema4.26.0indirect
PyPIjsonschema-specifications2025.9.1indirect
PyPIlinkify-it-py2.1.0indirect
PyPIllm-routing—indirect
PyPIllm-routing13.3.2indirect
PyPImarkdown-it-py4.0.0indirect
PyPImarkupsafe3.0.3indirect
PyPImcp-types2.0.0indirect
PyPImdit-py-plugins0.6.1indirect
PyPImdurl0.1.2indirect
PyPImultidict6.7.1indirect
PyPIopenai2.30.0indirect
PyPIopentelemetry-api1.41.0indirect
PyPIopentelemetry-exporter-otlp-proto-common1.41.0indirect
PyPIopentelemetry-exporter-otlp-proto-grpc—indirect
PyPIopentelemetry-exporter-otlp-proto-grpc1.41.0indirect
PyPIopentelemetry-proto1.41.0indirect
PyPIopentelemetry-sdk—indirect
PyPIopentelemetry-sdk1.41.0indirect
PyPIopentelemetry-semantic-conventions0.62b0indirect
PyPIpackaging26.0indirect
PyPIplatformdirs4.9.6indirect
PyPIpluggy1.6.0indirect
PyPIpropcache0.4.1indirect
PyPIprotobuf6.33.6indirect
PyPIpycparser3.0indirect
PyPIpydantic-core2.41.5indirect
PyPIpygments2.19.2indirect
PyPIpyjwt2.12.1indirect
PyPIpytest—indirect
PyPIpytest9.0.2indirect
PyPIpytest-asyncio—indirect
PyPIpytest-asyncio1.3.0indirect
PyPIpytest-timeout—indirect
PyPIpytest-timeout2.4.0indirect
PyPIpytest-xdist—indirect
PyPIpytest-xdist3.8.0indirect
PyPIpython-dotenv1.2.2indirect
PyPIpython-multipart0.0.22indirect
PyPIpywin32311indirect
PyPIpyyaml—indirect
PyPIpyyaml6.0.3indirect
PyPIreferencing0.37.0indirect
PyPIregex2026.3.32indirect
PyPIrequests2.33.0indirect
PyPIrich14.3.3indirect
PyPIrpds-py0.30.0indirect
PyPIruff—indirect
PyPIruff0.15.8indirect
PyPIshellingham1.5.4indirect
PyPIsmmap5.0.3indirect
PyPIsniffio1.3.1indirect
PyPIsortedcontainers2.4.0indirect
PyPIsse-starlette3.3.3indirect
PyPIstarlette1.0.0indirect
PyPItextual8.2.6indirect
PyPItiktoken0.12.0indirect
PyPItokenizers0.22.2indirect
PyPItqdm4.67.3indirect
PyPItree-sitter—indirect
PyPItree-sitter0.25.2indirect
PyPItree-sitter-languages—indirect
PyPItree-sitter-languages1.10.2indirect
PyPItruststore0.10.4indirect
PyPItyper0.24.1indirect
PyPItyping-extensions4.15.0indirect
PyPItyping-inspection0.4.2indirect
PyPIuc-micro-py2.0.0indirect
PyPIurllib32.6.3indirect
PyPIyarl1.23.0indirect
PyPIzipp3.23.0indirect
Dependency advisories 0

Installing pypi:llm-routing@13.3.2 pulls in 73 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 ypollak2/llm-router. Read them side by side →

96diegosouzapw/OmniRouteNever stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 550+ contributorsExceptional98strands-agents/toolsA set of tools that gives agents powerful capabilities.Exceptional96yamadashy/repomix📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.Exceptional96vercel/aiThe AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents Exceptional98PostHog/posthog-jsSend usage data from your web app or site to PostHog, with autocapture.Exceptional96TanStack/ai🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid.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, npm.