# bentoml/BentoML — health index 96/100 (Exceptional)

> Inspection of the public repository bentoml/BentoML by inspect.software. It holds a health index of 96 out of 100, placing it in the Exceptional band. The index is a signal derived from publicly visible practice, not a warranty, a security audit, or an endorsement, and it is independent of payment.

- Repository: https://github.com/bentoml/BentoML
- Report page: https://inspect.software/software/bentoml/BentoML
- Full JSON report: https://inspect.software/api/repositories/bentoml/BentoML/report
- Badge: https://raw.githubusercontent.com/inspect-software/badges/main/v1/b/bentoml/BentoML.svg
- Inspected: 2026-08-12
- Methodology: metrics 2.10.0, report schema 0.31.0 (https://inspect.software/methodology.md)

## Category summary

| Category | Weight | Index | Band |
|---|---|---|---|
| Vitality | 21% | 80/100 | Excellent |
| Community & Adoption | 17% | 93/100 | Exceptional |
| Sustainability & Governance | 23% | 87/100 | Excellent |
| Engineering Quality | 19% | 91/100 | Excellent |
| Security | 16% | 65/100 | Good |
| AI Readiness | 4% | 72/100 | Good |

The weighted overall 83 is calibrated to 96 on the published index scale (record calibration 2026-08-02).

## Repository facts

| Field | Value |
|---|---|
| Description | The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more! |
| Classification | cli, library, network-service |
| Homepage | https://bentoml.com |
| Primary language | Python |
| License | Apache-2.0 |
| Stars | 8,782 |
| Forks | 1,009 |
| Created | 2019-04-02 |
| Last push | 2026-08-03 |
| Latest release | v1.4.39 |
| Commits (last year) | 127 |
| Bus factor | 4 |
| Topics | model-serving, mlops, llmops, generative-ai, llm-inference, model-inference-service, inference-platform, deep-learning, llm-serving, machine-learning, python, multimodal, ml-engineering, llm, ai-inference |

## Published packages

| Registry | Package | Latest | Monthly downloads |
|---|---|---|---|
| pypi | bentoml | 1.4.39 | 256,155 |

## Vitality — 80/100 (Excellent)

Is the project alive — is code being written and are releases shipping? Weight: 21% of the overall index.

### Development activity — 73/100 (Good)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Push recency | partial | 28.8 / 36 | last push 9 days ago |
| Commit cadence | partial | 24.9 / 36 | 36/52 weeks with commits |
| Commit volume | met | 18 / 18 | 127 commits in the last year |
| OpenSSF Scorecard: Maintained | partial | 1 / 10 | 2 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 1 |

### Release discipline — 90/100 (Excellent)

Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Ships releases | met | 27 / 27 | 100 releases published |
| Release recency | partial | 27 / 36 | latest release 97 days ago |
| Release cadence | met | 27 / 27 | a release every ~17.9 days |
| OpenSSF Scorecard: Signed-Releases | excluded | 0 / 10 | no releases found |

### Abandonment — 100/100 (Exceptional)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Project is still maintained | met | 100 / 100 | last human commit 80 days ago |

## Community & Adoption — 93/100 (Exceptional)

Does the project have users, downloads, attention, and a welcoming setup for contributors? Weight: 17% of the overall index.

### Popularity & adoption — 96/100 (Exceptional)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Stars | met | 60 / 60 | 8,782 stars |
| Forks | met | 25 / 25 | 1,009 forks |
| Watchers | partial | 10.5 / 15 | 80 watchers |

### Community health — 92/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| README | met | 22.5 / 22.5 | — |
| License | met | 22.5 / 22.5 | recognized license (Apache-2.0) |
| CONTRIBUTING guide | met | 18 / 18 | — |
| Code of conduct | met | 13.5 / 13.5 | — |
| Issue template | not met | 0 / 7.2 | — |
| PR template | met | 6.3 / 6.3 | — |

### Ecosystem adoption (downloads) — 90/100 (Excellent)

Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Monthly downloads | partial | 72.1 / 80 | 256,155 downloads/month across pypi |
| Registry dependents | excluded | 0 / 20 | not reported by this ecosystem |

## Sustainability & Governance — 87/100 (Excellent)

Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep? Weight: 23% of the overall index.

### Maintainer resilience (bus factor) — 85/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Bus factor | partial | 43.2 / 54 | 4 contributor(s) cover half of all commits |
| Commit distribution | partial | 18.7 / 22.5 | top contributor authored 17% of commits |
| Contributor breadth | met | 13.5 / 13.5 | 97 contributors |
| OpenSSF Scorecard: Contributors | met | 10 / 10 | project has 39 contributing companies or organizations |

### Issue & PR responsiveness — 69/100 (Good)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Issue resolution | partial | 36.8 / 42 | 88% of issues closed |
| PR acceptance | partial | 26.2 / 30 | 3630/4164 decided PRs merged |
| Newcomer PR acceptance | not met | 0 / 13 | 0/9 first-time contributors' PRs merged in 30d |
| OpenSSF Scorecard: Code-Review | partial | 6 / 15 | Found 9/22 approved changesets -- score normalized to 4 |

### Ownership & stewardship — 97/100 (Exceptional)

Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Ownership backing | met | 30 / 30 | organization-owned |
| Verified domain | excluded | 0 / 20 | verified-domain status not read for this organization |
| Owner reach | partial | 22.8 / 25 | 1,465 followers of bentoml |
| Track record | met | 25 / 25 | 112 public repos, account ~7 yr old |

### Package maintenance — 100/100 (Exceptional)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Published & resolvable | met | 25 / 25 | 1 package(s) on pypi |
| Publish recency | met | 35 / 35 | latest publish 97 days ago |
| Version history | met | 20 / 20 | 219 published versions |
| Not deprecated | met | 20 / 20 | active, not deprecated or yanked |

## Engineering Quality — 91/100 (Excellent)

Are baseline engineering and documentation practices in place? Weight: 19% of the overall index.

### Engineering practices — 92/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| CI workflows | met | 24 / 24 | 5 workflow(s) |
| Tests present | met | 24 / 24 | — |
| Linter config | met | 16 / 16 | — |
| Pre-commit hooks | met | 9.6 / 9.6 | — |
| .editorconfig | not met | 0 / 6.4 | — |
| OpenSSF Scorecard: CI-Tests | partial | 18 / 20 | 22 out of 24 merged PRs checked by a CI test -- score normalized to 9 |

### Documentation — 90/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| README | met | 30 / 30 | — |
| Documentation directory | met | 25 / 25 | — |
| Documentation / homepage site | met | 15 / 15 | https://bentoml.com |
| Repository description | met | 10 / 10 | — |
| Topics | met | 10 / 10 | 15 topics |
| Wiki | not met | 0 / 10 | — |

## Security — 65/100 (Good)

Are visible security and supply-chain practices strong, with no malicious dependency and no unresolved high-risk jurisdiction exposure? Weight: 16% of the overall index.

### Security posture — 56/100 (Moderate)

Excluded from scoring (no data or not applicable): Branch-Protection, Signed-Releases. Remaining weights renormalized.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Binary-Artifacts | met | 7.5 / 7.5 | no binaries found in the repo |
| Branch-Protection | excluded | 0 / 7.5 | internal 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 |
| CI-Tests | partial | 2.2 / 2.5 | 22 out of 24 merged PRs checked by a CI test -- score normalized to 9 |
| CII-Best-Practices | not met | 0 / 2.5 | no effort to earn an OpenSSF best practices badge detected |
| Code-Review | partial | 3 / 7.5 | Found 9/22 approved changesets -- score normalized to 4 |
| Contributors | met | 2.5 / 2.5 | project has 39 contributing companies or organizations |
| Dangerous-Workflow | met | 10 / 10 | no dangerous workflow patterns detected |
| Dependency-Update-Tool | met | 7.5 / 7.5 | update tool detected |
| Fuzzing | not met | 0 / 5 | project is not fuzzed |
| License | met | 2.5 / 2.5 | license file detected |
| Maintained | partial | 0.8 / 7.5 | 2 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 1 |
| Packaging | met | 5 / 5 | packaging workflow detected |
| Pinned-Dependencies | not met | 0 / 5 | dependency not pinned by hash detected -- score normalized to 0 |
| SAST | partial | 4.5 / 5 | SAST tool detected but not run on all commits |
| Security-Policy | met | 5 / 5 | security policy file detected |
| Signed-Releases | excluded | 0 / 7.5 | no releases found |
| Token-Permissions | not met | 0 / 7.5 | detected GitHub workflow tokens with excessive permissions |
| Vulnerabilities | not met | 0 / 7.5 | 119 existing vulnerabilities detected |

### Dependency advisories — 100/100 (Exceptional)

Excluded from scoring (no data or not applicable): No advisories left outstanding. Remaining weights renormalized. Matched the pypi:bentoml@1.4.39 runtime dependency closure — what installing the published package pulls in — 67 packages. Reachability is not analyzed.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Direct dependencies free of known advisories | met | 35 / 35 | no direct dependency carries a known advisory |
| Indirect dependencies free of known advisories | met | 25 / 25 | no indirect dependency carries a known advisory |
| No advisories left outstanding | excluded | 0 / 40 | no advisory carries a publication date |

### Malicious dependencies — 100/100 (Exceptional)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| No dependency reported as a malicious package | met | 100 / 100 | no dependency is reported as a malicious package |

### High-Risk Jurisdiction Exposure — 100/100 (Exceptional)

Only high-confidence self-published location evidence affects this multiplier. Ambiguous matches are review-only; country evidence is not proof of nationality, citizenship, legal registration, malicious intent, or sanctions status.

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Policy exposure multiplier | met | 100 / 100 | no confirmed policy-scope location match |

## AI Readiness — 72/100 (Good)

How well is the repo equipped to be developed and maintained with AI coding agents? Carries a deliberately small weight: agent tooling is a real maintenance signal, but its absence must never gate the top of the scale (calibration saturates at raw 91, so 100/100 remains reachable with AI Readiness at zero).

### Agent context & guidance — 40/100 (Weak)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Agent instructions | not met | 0 / 45 | no CLAUDE.md / AGENTS.md / editor rules |
| Machine-readable docs (llms.txt) | not met | 0 / 15 | — |
| Legible commit history | met | 40 / 40 | 74 of 79 human commits state their intent (structured subject or explanatory body) |

### Verify loop (build / test / typecheck) — 88/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| One-command bootstrap | met | 18 / 18 | Makefile, docs/Makefile, noxfile.py |
| Automated tests | met | 22 / 22 | — |
| Lint / format config | met | 11 / 11 | — |
| Static type checking | met | 11 / 11 | src/bentoml/py.typed, src/bentoml_cli/py.typed |
| Reproducible environment | met | 10 / 10 | devcontainer, Dockerfile, lockfile |
| Demonstrated agent practice | partial | 8 / 10 | 4 of the last 100 commits agent-authored or agent-credited |
| Automated maintenance | met | 8 / 8 | 13 of the last 100 commits are automated dependency updates |
| OpenSSF Scorecard: Pinned-Dependencies | not met | 0 / 10 | dependency not pinned by hash detected -- score normalized to 0 |

### Code legibility for models — 82/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| Type-checkable code | partial | 27 / 45 | Python with type-check config (src/bentoml/py.typed, src/bentoml_cli/py.typed) |
| Manageable file sizes | partial | 54.6 / 55 | 3/440 source files over 60KB |

### Machine-readable interfaces — 80/100 (Excellent)

| Criterion | Status | Points | Detail |
|---|---|---|---|
| API schema (OpenAPI/GraphQL/proto) | met | 40 / 40 | src/bentoml/grpc/v1/service.proto, src/bentoml/grpc/v1alpha1/service.proto, tests/proto/service_test.proto |
| MCP server | not met | 0 / 20 | — |
| Runnable examples | met | 40 / 40 | examples |

## Collection warnings

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

## What this report is

inspect.software measures public repositories against a single published, versioned methodology and reports the result as a 1–100 health index. Findings are signals derived from what is visible in public repository data — they are not a security audit, a warranty, or an endorsement, and no result depends on payment.

- Methodology, formulas and weights: https://inspect.software/methodology.md
- What a result does and does not claim: https://inspect.software/wiki/signals-not-warranties.md
- Rating bands: https://inspect.software/wiki/scoring-bands.md
- Corrections: https://inspect.software/contact.md
- Index of all documents: https://inspect.software/llms.txt