Public record
Software health reportschema 0.12.0 · metrics 2.10.0 · 2026-07-18 05:56 UTC

ai-hypercomputer / jetstream

JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).

PythonApache-2.0★ 451 stars⑂ 67 forkssince Mar 2024View on GitHub ↗
#gemma#gpt#gpu#inference#jax#large-language-models#llama#llama2#llm#model-serving#pytorch#tpu#llm-inference#llmops#mlops#transformer

ai-hypercomputer/jetstream holds a health index of 59 out of 100, placing it in the Moderate band. It scores highest on Sustainability & Governance (81/100) and lowest on Vitality (28/100). It was last updated 193 days ago. 6 contributors account for most of its recent work.

59
overall / 100
Moderate

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.

59
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 56 is calibrated to 59 on the published index scale (record calibration 2026-08-02).

Ownership

AI HypercomputerOrganization
512 followers22 public repossince Sep 2024

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

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publish
PyPIgoogle-jetstreampoints to another repo — not scored0.2.22,1854777 days ago

Metrics by category

Vitality

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

28At Risk · 21% of overall

Development activity

7Critical
How it's scored
3.6/36Push recency — last push 193 days ago
0.7/36Commit cadence — 1/52 weeks with commits
2.7/18Commit volume — 1 commits in the last year
0/10OpenSSF Scorecard: Maintained — 0 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 0
Inputs used
commits_last_year1
human_commit_share—
days_since_last_push193
active_weeks_last_year1

Release discipline

60Moderate
How it's scored
27/27Ships releases — 4 releases published
7.2/36Release recency — latest release 576 days ago
19.8/27Release cadence — a release every ~85.7 days
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count4
latest_release_tagv0.3
releases_from_tagsno
days_since_latest_release576
mean_days_between_releases85.7
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?

68Good · 17% of overall

Popularity & adoption

66Good
How it's scored
43/60Stars — 451 stars
15.2/25Forks — 67 forks
7.4/15Watchers — 22 watchers
Inputs used
forks67
stars451
watchers22
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 (Apache-2.0)
18/18CONTRIBUTING guide
0/13.5Code of conduct
0/7.2Issue template
0/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges—
has_contributingyes
has_issue_templateno
has_code_of_conductno
readme_badge_services—
has_pull_request_templateno

Sustainability & Governance

Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?

81Excellent · 23% of overall

Maintainer resilience (bus factor)

90Excellent
How it's scored
48.6/54Bus factor — 6 contributor(s) cover half of all commits
18.1/22.5Commit distribution — top contributor authored 20% of commits
13.5/13.5Contributor breadth — 36 contributors
10/10OpenSSF Scorecard: Contributors — project has 4 contributing companies or organizations
Inputs used
bus_factor6
contributors_sampled36
top_contributor_share0.195

Issue & PR responsiveness

73Good
How it's scored
22.4/42Issue resolution — 53% of issues closed
26.2/30PR acceptance — 209/239 decided PRs merged
0/13Newcomer PR acceptance — no first-time contributor's PR decided in 30d
15/15OpenSSF Scorecard: Code-Review — all changesets reviewed
Inputs used
merged_prs209
open_issues14
closed_issues16
prs_merged_7d—
prs_decided_7d—
prs_merged_30d—
prs_decided_30d—
issue_closed_ratio0.533
closed_unmerged_prs30
first_time_authors_30d—
first_time_prs_merged_30d—
first_time_prs_decided_30d—
Excluded from scoring (no data or not applicable): Newcomer PR acceptance. Remaining weights renormalized.

Ownership & stewardship

79Good
How it's scored
30/30Ownership backing — organization-owned
0/20Verified domain — verified-domain status not read for this organization
19.5/25Owner reach — 512 followers of AI-Hypercomputer
13.6/25Track record — 22 public repos, account ~1 yr old
Inputs used
followers512
owner_typeOrganization
is_verified—
owner_loginAI-Hypercomputer
public_repos22
account_age_days676
Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.

Engineering Quality

Are baseline engineering and documentation practices in place?

59Moderate · 19% of overall

Engineering practices

48Weak
How it's scored
24/24CI workflows — 5 workflow(s)
24/24Tests present
0/16Linter config
0/9.6Pre-commit hooks
0/6.4.editorconfig
0/20OpenSSF Scorecard: CI-Tests — 1 out of 16 merged PRs checked by a CI test -- score normalized to 0
Inputs used
has_ciyes
has_testsyes
has_editorconfigno
has_linter_configno
has_precommit_configno

Documentation

75Good
How it's scored
30/30README
25/25Documentation directory
0/15Documentation / homepage site
10/10Repository description
10/10Topics — 16 topics
0/10Wiki
Inputs used
topicsgemma, gpt, gpu, inference, jax, large-language-models, llama, llama2, llm, model-serving, pytorch, tpu, llm-inference, llmops, mlops, transformer
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?

44Weak · 16% of overall

Security posture

44Weak
How it's scored
7.5/7.5Binary-Artifacts — no binaries found in the repo
0/7.5Branch-Protection — no data
0/2.5CI-Tests — 1 out of 16 merged PRs checked by a CI test -- score normalized to 0
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
7.5/7.5Code-Review — all changesets reviewed
2.5/2.5Contributors — project has 4 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
0/7.5Maintained — 0 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 0
0/5Packaging — no data
0/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0
0/5SAST — SAST tool is not run on all commits -- score normalized to 0
0/5Security-Policy — security policy file not detected
0/7.5Signed-Releases — no data
0/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
0/7.5Vulnerabilities — 20 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated15
scorecard_versionv5.5.0
checks_inconclusive3
scorecard_aggregate4.4
Excluded from scoring (no data or not applicable): Branch-Protection, Packaging, Signed-Releases. Remaining weights renormalized.

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.

40Weak · 4% of overall

Agent context & guidance

1Critical
How it's scored
0/45Agent instructions — no CLAUDE.md / AGENTS.md / editor rules
0/15Machine-readable docs (llms.txt)
0/40Legible commit history — no data
Inputs used
has_llms_txtno
llms_txt_url—
legible_history_share—
agent_instruction_files—
agent_instruction_max_bytes—
Excluded from scoring (no data or not applicable): Legible commit history. Remaining weights renormalized.

Verify loop (build / test / typecheck)

61Moderate
How it's scored
18/18One-command bootstrap — Makefile
22/22Automated tests
0/11Lint / format config
0/11Static type checking
10/10Reproducible environment — Dockerfile
0/10Demonstrated agent practice — no data
0/8Automated maintenance — no data
0/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0
Inputs used
has_nixno
has_testsyes
lockfiles—
has_dockerfileyes
typed_languageno
bootstrap_filesMakefile
has_devcontainerno
has_linter_configno
typecheck_configs—
agent_commit_share—
toolchain_manifests—
dependency_bot_commit_share—
Excluded from scoring (no data or not applicable): Demonstrated agent practice, Automated maintenance. Remaining weights renormalized.

Code legibility for models

55Moderate
How it's scored
0/45Type-checkable code — Python without a type-check config
54.6/55Manageable file sizes — 1/136 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes68,226
source_files_sampled136
oversized_source_files1

Machine-readable interfaces

50Moderate
How it's scored
40/40API schema (OpenAPI/GraphQL/proto) — jetstream/core/proto/jetstream.proto, jetstream/core/proto/multi_lora_decoding.proto, jetstream/engine/tokenizer.proto
0/20MCP server — not applicable to this kind of software
0/40Runnable examples
Inputs used
example_dirs—
has_mcp_signalno
api_schema_filesjetstream/core/proto/jetstream.proto, jetstream/core/proto/multi_lora_decoding.proto, jetstream/engine/tokenizer.proto
interfaces_expected_of—
Excluded from scoring (no data or not applicable): MCP server. Remaining weights renormalized.

Key facts

451GitHub stars
36contributors
1commits, last 12 months
193days since last push
4releases
6bus factor
14open issues
PyPIpackage ecosystems

Data collection warnings

  • pypi package 'google-jetstream' points at a different repository (https://github.com/google/JetStream); excluded from ecosystem scoring

More detail

OpenSSF Scorecard 4.4 / 10
4.4aggregate

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 · 2026-07-18 05:55 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
0CI-Tests1 out of 16 merged PRs checked by a CI test -- score normalized to 0
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
10Code-Reviewall changesets reviewed
10Contributorsproject has 4 contributing companies or organizations
10Dangerous-Workflowno dangerous workflow patterns detected
10Dependency-Update-Toolupdate tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
0Maintained0 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 0
n/aPackagingpackaging workflow not detected
0Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 0
0SASTSAST tool is not run on all commits -- score normalized to 0
0Security-Policysecurity policy file not detected
n/aSigned-Releasesno releases found
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
0Vulnerabilities20 existing vulnerabilities detected
All dependencies 27

Full resolved dependency set from the GitHub dependency graph: 0 direct and 27 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPIabsl-py—indirect
PyPIblobfile—indirect
PyPIcoverage—indirect
PyPIevaluate—indirect
PyPIfastapi—indirect
PyPIflax—indirect
PyPIgrpcio—indirect
PyPIhuggingface-hub—indirect
PyPIjax—indirect
PyPIjax0.4.33indirect
PyPIjaxlib—indirect
PyPInltk—indirect
PyPInumpy—indirect
PyPIpandas—indirect
PyPIparameterized—indirect
PyPIportpicker—indirect
PyPIprometheus-client—indirect
PyPIpytest—indirect
PyPIseqio—indirect
PyPIshortuuid—indirect
PyPIsympy—indirect
PyPItensorboard-plugin-profile—indirect
PyPItiktoken—indirect
PyPItorch2.3.0+cpuindirect
PyPItorchvision0.18.0+cpuindirect
PyPItransformers—indirect
PyPIuvicorn—indirect
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 ai-hypercomputer/jetstream. Read them side by side →

99vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMsExceptional99huggingface/transformers🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. Exceptional96bentoml/BentoMLThe easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!Exceptional100ray-project/rayRay is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.Exceptional98sgl-project/sglangSGLang is a high-performance serving framework for large language models and multimodal models.Exceptional98NVIDIA/Megatron-LMOngoing research training transformer models at scaleExceptional

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 v0.12.0 — full methodology · metrics wiki.

How one result sits in the wider record: aggregate statistics — PyPI.