Public record
Software health reportschema 0.16.0 · metrics 2.10.0 · 2026-07-21 02:39 UTC

lightseekorg / tokenspeed

TokenSpeed is a speed-of-light LLM inference engine.

PythonMIT★ 1,639 stars⑂ 194 forkssince May 2026View on GitHub ↗
KindLibraryNetwork servicehow this is determined
#deepseek#gpt-oss#kimi#lightseek#llm#minimax#qwen#speed-of-light#tokenspeed#blackwell#glm#vlm#inkling

lightseekorg/tokenspeed holds a health index of 84 out of 100, placing it in the Excellent band. It scores highest on Engineering Quality (96/100) and lowest on Vitality (38/100). It was last updated today. 5 contributors account for most of its recent work.

84
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.

84
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 71 is calibrated to 84 on the published index scale (record calibration 2026-08-02).

Ownership

LightSeek FoundationOrganization
173 followers7 public repossince Oct 2025

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

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publish
PyPItokenspeed0.0.1581140 days ago
PyPItokenspeed-mla0.2.01,674,56294 days ago
PyPItokenspeed-scheduler0.1.2-36 days ago
PyPItokenspeed-kernel-amd0.1.2-31 day ago

Metrics by category

Vitality

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

38Weak · 21% of overall

Development activity

62Moderate
How it's scored
36/36Push recency — last push 0 days ago
7.6/36Commit cadence — 11/52 weeks with commits
18/18Commit volume — 543 commits in the last year
0/10OpenSSF Scorecard: Maintained — project was created within the last 90 days. Please review its contents carefully
Inputs used
commits_last_year543
human_commit_share—
days_since_last_push0
active_weeks_last_year11

Release discipline

1Critical
How it's scored
0/27Ships releases — no releases published
0/36Release recency — no releases
0/27Release cadence — no releases
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count0
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?

88Excellent · 17% of overall

Popularity & adoption

77Good
How it's scored
52.1/60Stars — 1,639 stars
19/25Forks — 194 forks
5.8/15Watchers — 12 watchers
Inputs used
forks194
stars1,639
watchers12
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

Community health

92Excellent
How it's scored
22.5/22.5README
22.5/22.5License — recognized license (MIT)
18/18CONTRIBUTING guide
13.5/13.5Code of conduct
0/7.2Issue template
6.3/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges—
has_contributingyes
has_issue_templateno
has_code_of_conductyes
readme_badge_services—
has_pull_request_templateyes

Ecosystem adoption (downloads)

100Exceptional
How it's scored
80/80Monthly downloads — 1,674,562 downloads/month across pypi
0/20Registry dependents — not reported by this ecosystem
Inputs used
packagestokenspeed-mla, tokenspeed-kernel-amd
dependents—
ecosystemspypi
total_downloads—
monthly_downloads1,674,562
unverified_packages_excludedtokenspeed, tokenspeed-scheduler
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?

83Excellent · 23% of overall

Maintainer resilience (bus factor)

87Excellent
How it's scored
45.9/54Bus factor — 5 contributor(s) cover half of all commits
17.6/22.5Commit distribution — top contributor authored 22% of commits
13.5/13.5Contributor breadth — 54 contributors
10/10OpenSSF Scorecard: Contributors — project has 19 contributing companies or organizations
Inputs used
bus_factor5
contributors_sampled54
top_contributor_share0.218

Issue & PR responsiveness

81Excellent
How it's scored
33.6/42Issue resolution — 80% of issues closed
24.7/30PR acceptance — 555/675 decided PRs merged
0/13Newcomer PR acceptance — no first-time contributor's PR decided in 30d
12/15OpenSSF Scorecard: Code-Review — Found 25/30 approved changesets -- score normalized to 8
Inputs used
merged_prs555
open_issues6
closed_issues24
prs_merged_7d—
prs_decided_7d—
prs_merged_30d—
prs_decided_30d—
issue_closed_ratio0.8
closed_unmerged_prs120
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

68Good
How it's scored
30/30Ownership backing — organization-owned
0/20Verified domain — verified-domain status not read for this organization
16.1/25Owner reach — 173 followers of lightseekorg
8.1/25Track record — 7 public repos, account ~0 yr old
Inputs used
followers173
owner_typeOrganization
is_verified—
owner_loginlightseekorg
public_repos7
account_age_days275
Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 4 package(s) on pypi
35/35Publish recency — latest publish 1 days ago
20/20Version history — 9 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagestokenspeed, tokenspeed-mla, tokenspeed-scheduler, tokenspeed-kernel-amd
ecosystemspypi
any_deprecatedno
min_days_since_publish1

Engineering Quality

Are baseline engineering and documentation practices in place?

96Exceptional · 19% of overall

Engineering practices

94Exceptional
How it's scored
24/24CI workflows — 21 workflow(s)
24/24Tests present
16/16Linter config
9.6/9.6Pre-commit hooks
0/6.4.editorconfig
20/20OpenSSF Scorecard: CI-Tests — 30 out of 30 merged PRs checked by a CI test -- score normalized to 10
Inputs used
has_ciyes
has_testsyes
has_editorconfigno
has_linter_configyes
has_precommit_configyes

Documentation

100Exceptional
How it's scored
30/30README
25/25Documentation directory
15/15Documentation / homepage site — https://lightseek.org/blog/lightseek-tokenspeed.html
10/10Repository description
10/10Topics — 13 topics
10/10Wiki
Inputs used
topicsdeepseek, gpt-oss, kimi, lightseek, llm, minimax, qwen, speed-of-light, tokenspeed, blackwell, glm, vlm, inkling
has_wikiyes
homepagehttps://lightseek.org/blog/lightseek-tokenspeed.html
docs_sitehttps://lightseek.org/blog/lightseek-tokenspeed.html
has_readmeyes
has_docs_diryes
has_descriptionyes

Security

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

51Moderate · 16% of overall

Security posture

51Moderate
How it's scored
7.5/7.5Binary-Artifacts — no binaries found in the repo
3.8/7.5Branch-Protection — branch protection is not maximal on development and all release branches
2.5/2.5CI-Tests — 30 out of 30 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
6/7.5Code-Review — Found 25/30 approved changesets -- score normalized to 8
2.5/2.5Contributors — project has 19 contributing companies or organizations
10/10Dangerous-Workflow — no dangerous workflow patterns detected
0/7.5Dependency-Update-Tool — no update tool detected
0/5Fuzzing — project is not fuzzed
2.5/2.5License — license file detected
0/7.5Maintained — project was created within the last 90 days. Please review its contents carefully
5/5Packaging — packaging workflow detected
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
5/5Security-Policy — security policy file detected
0/7.5Signed-Releases — no data
0/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
4.5/7.5Vulnerabilities — 4 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated17
scorecard_versionv5.5.0
checks_inconclusive1
scorecard_aggregate5.1
Excluded from scoring (no data or not applicable): 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.

57Moderate · 4% of overall

Agent context & guidance

75Good
How it's scored
45/45Agent instructions — AGENTS.md, CLAUDE.md
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_filesAGENTS.md, CLAUDE.md
agent_instruction_max_bytes2,009
Excluded from scoring (no data or not applicable): Legible commit history. Remaining weights renormalized.

Verify loop (build / test / typecheck)

52Moderate
How it's scored
0/18One-command bootstrap
22/22Automated tests
11/11Lint / 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_files—
has_devcontainerno
has_linter_configyes
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

53Moderate
How it's scored
0/45Type-checkable code — Python without a type-check config
53.4/55Manageable file sizes — 28/984 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes393,516
source_files_sampled984
oversized_source_files28

Machine-readable interfaces

40Weak
How it's scored
0/40API schema (OpenAPI/GraphQL/proto)
0/20MCP server
40/40Runnable examples — recipes
Inputs used
example_dirsrecipes
has_mcp_signalno
api_schema_files—
interfaces_expected_ofnetwork-service

Key facts

1,639GitHub stars
54contributors
543commits, last 12 months
0days since last push
0releases
5bus factor
6open issues
npm, PyPIpackage ecosystems

Data collection warnings

  • GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository

More detail

OpenSSF Scorecard 5.1 / 10
5.1aggregate

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 · 2026-07-21 02:39 UTC

10Binary-Artifactsno binaries found in the repo
5Branch-Protectionbranch protection is not maximal on development and all release branches
10CI-Tests30 out of 30 merged PRs checked by a CI test -- score normalized to 10
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
8Code-ReviewFound 25/30 approved changesets -- score normalized to 8
10Contributorsproject has 19 contributing companies or organizations
10Dangerous-Workflowno dangerous workflow patterns detected
0Dependency-Update-Toolno update tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
0Maintainedproject was created within the last 90 days. Please review its contents carefully
10Packagingpackaging workflow detected
0Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 0
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
6Vulnerabilities4 existing vulnerabilities detected
Direct dependencies 52
RegistryPackageVersion constraintManifest
PyPIaiohttp—python/pyproject.toml
PyPIcompressed-tensors—python/pyproject.toml
PyPIdill—python/pyproject.toml
PyPIeinops—python/pyproject.toml
PyPIfastapi—python/pyproject.toml
PyPIgrpcio-health-checking==1.81.1python/pyproject.toml
PyPIgrpcio-reflection==1.81.1python/pyproject.toml
PyPIhf_transfer—python/pyproject.toml
PyPIhuggingface_hub—python/pyproject.toml
PyPImodelscope—python/pyproject.toml
PyPImsgspec—python/pyproject.toml
PyPIninja—python/pyproject.toml
PyPInumpy—python/pyproject.toml
PyPIopenai>=2.24.1python/pyproject.toml
PyPIopenai-harmony—python/pyproject.toml
PyPIorjson—python/pyproject.toml
PyPIpackaging—python/pyproject.toml
PyPIpartial-json-parser—python/pyproject.toml
PyPIpeft—python/pyproject.toml
PyPIpillow—python/pyproject.toml
PyPIprometheus-client—python/pyproject.toml
PyPIpsutil—python/pyproject.toml
PyPIpybase64—python/pyproject.toml
PyPIpybind11—python/pyproject.toml
PyPIpydantic—python/pyproject.toml
PyPIpy-spy—python/pyproject.toml
PyPIpytest-asyncio—python/pyproject.toml
PyPIpython-multipart—python/pyproject.toml
PyPIpyzmq—python/pyproject.toml
PyPIrequests—python/pyproject.toml
PyPIsetproctitle—python/pyproject.toml
PyPItiktoken—python/pyproject.toml
PyPItokenspeed-mooncake>=0.3.11.post20260527python/pyproject.toml
PyPItokenspeed-smg==1.8.0.post20260720python/pyproject.toml
PyPItokenspeed-smg-grpc-proto==0.4.14.post20260720python/pyproject.toml
PyPItokenspeed-smg-grpc-servicer==0.7.0.post20260720python/pyproject.toml
PyPItorch==2.11.0python/pyproject.toml
PyPItorch_memory_saver==0.0.9.post1python/pyproject.toml
PyPItorchvision—python/pyproject.toml
PyPItqdm—python/pyproject.toml
PyPItransformers==5.12.0python/pyproject.toml
PyPIuv—python/pyproject.toml
PyPIuvicorn—python/pyproject.toml
PyPIuvloop—python/pyproject.toml
PyPIxgrammar==0.2.2python/pyproject.toml
PyPIviztracer—python/pyproject.toml
PyPItorch—tokenspeed-kernel-amd/pyproject.toml
PyPItokenspeed-triton>=3.8.10.post20260709tokenspeed-kernel-amd/pyproject.toml
PyPIapache-tvm-ffi==0.1.12tokenspeed-mla/pyproject.toml
PyPInvidia-cutlass-dsl—tokenspeed-mla/pyproject.toml
PyPItokenspeed-triton>=3.8.10.post20260709tokenspeed-mla/pyproject.toml
PyPItorch—tokenspeed-mla/pyproject.toml
All dependencies not collected

The resolved dependency set could not be collected for this report: GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository

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 lightseekorg/tokenspeed. Read them side by side →

98sgl-project/sglangSGLang is a high-performance serving framework for large language models and multimodal models.Exceptional99vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMsExceptional95ollama/ollamaGet up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.Exceptional99huggingface/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. Exceptional94unslothai/unslothUnsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, GLM and other models.Exceptional96NVIDIA-NeMo/Automodel🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face supportExceptional

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 v0.16.0 — full methodology · metrics wiki.

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