Public record
Software health reportschema 0.34.0 · metrics 2.10.0 · 2026-09-15 23:33 UTC

vndee / llm-sandbox

Lightweight and portable LLM sandbox runtime (code interpreter) Python library.

PythonMIT★ 1,120 stars⑂ 106 forkssince Jun 2024View on GitHub ↗
KindLibraryCommand-line toolhow this is determined
#code-generation#code-interpreter#large-language-models#llm-sandbox

vndee/llm-sandbox holds a health index of 95 out of 100, placing it in the Exceptional band. It scores highest on Engineering Quality (94/100) and lowest on Sustainability & Governance (66/100). It was last updated 1 day ago. A single contributor accounts for most of its recent work.

95
overall / 100
Exceptional

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.

95
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 82 is calibrated to 95 on the published index scale (record calibration 2026-08-02).

Ownership

Duy HuynhPersonal account
177 followers142 public repossince May 2017Looking for the next cool idea

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-sandbox0.3.44621,6416143 days agopython

Metrics by category

Vitality

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

89Excellent · 21% of overall

Development activity

82Excellent
How it's scored
36/36Push recency — last push 1 days ago
18/36Commit cadence — 26/52 weeks with commits
18/18Commit volume — 281 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year281
human_commit_share0.72
days_since_last_push1
active_weeks_last_year26

Release discipline

100Exceptional
How it's scored
27/27Ships releases — 45 releases published
36/36Release recency — latest release 43 days ago
27/27Release cadence — a release every ~18.9 days
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count45
latest_release_tag0.3.44
releases_from_tagsno
days_since_latest_release43
mean_days_between_releases18.9
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?

81Excellent · 17% of overall

Popularity & adoption

68Good
How it's scored
49.5/60Stars — 1,120 stars
16.8/25Forks — 106 forks
1.7/15Watchers — 3 watchers
Inputs used
forks106
stars1,120
watchers3
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

Community health

85Excellent
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
0/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges5
has_contributingyes
has_issue_templateno
has_code_of_conductyes
readme_badge_servicescodecov.io, shields.io, sonarcloud.io
has_pull_request_templateno

Ecosystem adoption (downloads)

96Exceptional
How it's scored
77.2/80Monthly downloads — 621,641 downloads/month across pypi
0/20Registry dependents — not reported by this ecosystem
Inputs used
packagesllm-sandbox
dependents—
ecosystemspypi
total_downloads—
monthly_downloads621,641
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?

66Good · 23% of overall

Maintainer resilience (bus factor)

35Weak
How it's scored
9/54Bus factor — 1 contributor(s) cover half of all commits
2.7/22.5Commit distribution — top contributor authored 88% of commits
13.5/13.5Contributor breadth — 20 contributors
10/10OpenSSF Scorecard: Contributors — project has 12 contributing companies or organizations
Inputs used
bus_factor1
contributors_sampled20
top_contributor_share0.881

Issue & PR responsiveness

80Excellent
How it's scored
30.3/42Issue resolution — 72% of issues closed
26.3/30PR acceptance — 121/138 decided PRs merged
13/13Newcomer PR acceptance — 2/2 first-time contributors' PRs merged in 30d
10.5/15OpenSSF Scorecard: Code-Review — Found 5/7 approved changesets -- score normalized to 7
Inputs used
merged_prs121
open_issues19
closed_issues49
prs_merged_7d2
prs_decided_7d2
prs_merged_30d4
prs_decided_30d4
issue_closed_ratio0.721
closed_unmerged_prs17
first_time_authors_30d1
first_time_prs_merged_30d2
first_time_prs_decided_30d2

Ownership & stewardship

64Moderate
How it's scored
10/30Ownership backing — personal (user) account
0/20Verified domain — not applicable to user accounts
16.2/25Owner reach — 177 followers of vndee
25/25Track record — 142 public repos, account ~9 yr old
Inputs used
followers177
owner_typeUser
is_verified—
owner_loginvndee
public_repos142
account_age_days3,424
Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 1 package(s) on pypi
35/35Publish recency — latest publish 43 days ago
20/20Version history — 61 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagesllm-sandbox
ecosystemspypi
any_deprecatedno
min_days_since_publish43

Engineering Quality

Are baseline engineering and documentation practices in place?

94Exceptional · 19% of overall

Engineering practices

90Excellent
How it's scored
24/24CI workflows — 8 workflow(s)
24/24Tests present
16/16Linter config — pyproject.toml ([tool.ruff]), tox.ini
9.6/9.6Pre-commit hooks
0/6.4.editorconfig
16/20OpenSSF Scorecard: CI-Tests — 11 out of 13 merged PRs checked by a CI test -- score normalized to 8
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://vndee.github.io/llm-sandbox/
10/10Repository description
10/10Topics — 4 topics
10/10Wiki
Inputs used
topicscode-generation, code-interpreter, large-language-models, llm-sandbox
has_wikiyes
homepagehttps://vndee.github.io/llm-sandbox/
docs_sitehttps://vndee.github.io/llm-sandbox/
has_readmeyes
has_docs_diryes
has_descriptionyes

Security

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

81Excellent · 16% of overall

Security posture

76Good
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
2/2.5CI-Tests — 11 out of 13 merged PRs checked by a CI test -- score normalized to 8
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
5.2/7.5Code-Review — Found 5/7 approved changesets -- score normalized to 7
2.5/2.5Contributors — project has 12 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
7.5/7.5Maintained — 30 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 10
5/5Packaging — packaging workflow detected
0/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0
5/5SAST — SAST tool is run on all commits
5/5Security-Policy — security policy file detected
0/7.5Signed-Releases — no data
6/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
6/7.5Vulnerabilities — 2 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated17
scorecard_versionv5.5.0
checks_inconclusive1
scorecard_aggregate7.6
Excluded from scoring (no data or not applicable): Signed-Releases. Remaining weights renormalized.

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_packages5
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-sandbox@0.3.44 runtime dependency closure — what installing the published package pulls in — 5 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.

79Good · 4% of overall

Agent context & guidance

85Excellent
How it's scored
45/45Agent instructions — .github/copilot-instructions.md, CLAUDE.md
0/15Machine-readable docs (llms.txt)
40/40Legible commit history — 70 of 72 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtno
llms_txt_url—
legible_history_share0.972
agent_instruction_files.github/copilot-instructions.md, CLAUDE.md
agent_instruction_max_bytes11,367

Verify loop (build / test / typecheck)

75Good
How it's scored
18/18One-command bootstrap — Makefile
22/22Automated tests
11/11Lint / format config — pyproject.toml ([tool.ruff]), tox.ini
0/11Static type checking
10/10Reproducible environment — lockfile
6/10Demonstrated agent practice — 3 of the last 100 commits agent-authored or agent-credited
8/8Automated maintenance — 27 of the last 100 commits are automated dependency updates
0/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0
Inputs used
has_nixno
has_testsyes
lockfilesuv.lock
has_dockerfileno
typed_languageno
bootstrap_filesMakefile
has_devcontainerno
has_linter_configyes
typecheck_configs—
agent_commit_share0.03
toolchain_manifests—
dependency_bot_commit_share0.27

Code legibility for models

54Moderate
How it's scored
0/45Type-checkable code — Python without a type-check config
54.2/55Manageable file sizes — 2/144 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes105,061
source_files_sampled144
oversized_source_files2

Machine-readable interfaces

100Exceptional
How it's scored
0/40API schema (OpenAPI/GraphQL/proto) — not applicable to this kind of software
20/20MCP server
40/40Runnable examples — examples
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

1,120GitHub stars
20contributors
281commits, last 12 months
1days since last push
45releases
1bus factor
19open issues
PyPIpackage ecosystems

Data collection warnings

  • Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
  • pypi download statistics for 'llm-sandbox' unavailable this scan (stats endpoint failed after retries); adoption may be under-evidenced
  • pypi download figures for llm-sandbox carried forward from the previous scan (stats endpoint unavailable this scan)

More detail

Star and fork history 0 ★ / 106 ⇿
0Stars
106Forks
45Releases

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.

02040608010012010672024-072025-082026-09
Major 0Minor 1Patch 44

Each point covers 2 days.

OpenSSF Scorecard 7.6 / 10
7.6aggregate

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 · 2026-09-15 23:32 UTC

10Binary-Artifactsno binaries found in the repo
3Branch-Protectionbranch protection is not maximal on development and all release branches
8CI-Tests11 out of 13 merged PRs checked by a CI test -- score normalized to 8
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
7Code-ReviewFound 5/7 approved changesets -- score normalized to 7
10Contributorsproject has 12 contributing companies or organizations
10Dangerous-Workflowno dangerous workflow patterns detected
10Dependency-Update-Toolupdate tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
10Maintained30 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 10
10Packagingpackaging workflow detected
0Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 0
10SASTSAST tool is run on all commits
10Security-Policysecurity policy file detected
n/aSigned-Releasesno releases found
8Token-Permissionsdetected GitHub workflow tokens with excessive permissions
8Vulnerabilities2 existing vulnerabilities detected
Direct dependencies 1
RegistryPackageVersion constraintManifest
PyPIpydantic>=2.11.5pyproject.toml
All dependencies 172

Full resolved dependency set from the GitHub dependency graph: 2 direct and 170 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPIpydantic2.11.5direct
PyPIpydantic2.13.4direct
PyPIaiohappyeyeballs2.6.1indirect
PyPIaiohttp3.14.3indirect
PyPIaiosignal1.4.0indirect
PyPIaiosqlite0.21.0indirect
PyPIannotated-types0.7.0indirect
PyPIanyio4.9.0indirect
PyPIasync-timeout4.0.3indirect
PyPIattrs25.3.0indirect
PyPIbabel2.17.0indirect
PyPIbackrefs5.8indirect
PyPIbanks2.4.5indirect
PyPIcachetools5.5.2indirect
PyPIcertifi2025.4.26indirect
PyPIcffi2.1.0indirect
PyPIcfgv3.4.0indirect
PyPIchardet5.2.0indirect
PyPIcharset-normalizer3.4.2indirect
PyPIclick8.2.1indirect
PyPIcolorama0.4.6indirect
PyPIcoverage7.8.2indirect
PyPIcryptography50.0.0indirect
PyPIcsscompressor0.9.5indirect
PyPIdataclasses-json0.6.7indirect
PyPIdefusedxml0.7.1indirect
PyPIdeprecated1.2.18indirect
PyPIdeptry0.23.0indirect
PyPIdirtyjson1.0.8indirect
PyPIdistlib0.3.9indirect
PyPIdistro1.9.0indirect
PyPIdocker7.1.0indirect
PyPIdurationpy0.10indirect
PyPIexceptiongroup1.3.0indirect
PyPIfilelock3.32.2indirect
PyPIfiletype1.2.0indirect
PyPIfrozenlist1.6.0indirect
PyPIfsspec2025.5.1indirect
PyPIghp-import2.1.0indirect
PyPIgitdb4.0.12indirect
PyPIgitpython3.1.59indirect
PyPIgoogle-auth2.40.2indirect
PyPIgreenlet3.2.2indirect
PyPIgriffe1.7.3indirect
PyPIh110.16.0indirect
PyPIhtmlmin20.1.13indirect
PyPIhttpcore1.0.9indirect
PyPIhttpx0.28.1indirect
PyPIhttpx-sse0.4.1indirect
PyPIidentify2.6.12indirect
PyPIidna3.15indirect
PyPIiniconfig2.1.0indirect
PyPIjinja23.1.6indirect
PyPIjiter0.10.0indirect
PyPIjoblib1.5.1indirect
PyPIjsmin3.0.1indirect
PyPIjsonpatch1.33indirect
PyPIjsonpointer3.0.0indirect
PyPIjsonschema4.24.0indirect
PyPIjsonschema-specifications2025.4.1indirect
PyPIkubernetes32.0.1indirect
PyPIlangchain1.3.9indirect
PyPIlangchain-core1.5.3indirect
PyPIlangchain-openai1.2.1indirect
PyPIlangchain-protocol0.0.18indirect
PyPIlanggraph1.2.10indirect
PyPIlanggraph-checkpoint4.1.1indirect
PyPIlanggraph-prebuilt1.1.0indirect
PyPIlanggraph-sdk0.4.2indirect
PyPIlangsmith0.10.15indirect
PyPIllama-index0.14.23indirect
PyPIllama-index-core0.14.23indirect
PyPIllama-index-embeddings-openai0.6.0indirect
PyPIllama-index-instrumentation0.5.0indirect
PyPIllama-index-llms-openai0.7.10indirect
PyPIllama-index-workflows2.22.2indirect
PyPIllm-sandbox0.3.13indirect
PyPImarkdown3.8.1indirect
PyPImarkupsafe3.0.2indirect
PyPImarshmallow3.26.2indirect
PyPImcp1.29.0indirect
PyPImergedeep1.3.4indirect
PyPImkdocs1.6.1indirect
PyPImkdocs-autorefs1.4.2indirect
PyPImkdocs-get-deps0.2.0indirect
PyPImkdocs-git-revision-date-localized-plugin1.4.6indirect
PyPImkdocs-material9.7.7indirect
PyPImkdocs-material-extensions1.3.1indirect
PyPImkdocs-minify-plugin0.8.0indirect
PyPImkdocstrings0.29.1indirect
PyPImkdocstrings-python1.16.11indirect
PyPImultidict6.4.4indirect
PyPImypy1.15.0indirect
PyPImypy-extensions1.1.0indirect
PyPInest-asyncio1.6.0indirect
PyPInetworkx3.4.2indirect
PyPInltk3.10.3indirect
PyPInodeenv1.9.1indirect
PyPInumpy2.2.6indirect
PyPIoauthlib3.2.2indirect
PyPIopenai2.28.0indirect
PyPIorjson3.11.9indirect
PyPIormsgpack1.12.2indirect
PyPIpackaging24.2indirect
PyPIpaginate0.5.7indirect
PyPIpathspec0.12.1indirect
PyPIpillow12.3.0indirect
PyPIplatformdirs4.3.8indirect
PyPIpluggy1.6.0indirect
PyPIpodman5.4.0.1indirect
PyPIpre-commit4.2.0indirect
PyPIpropcache0.3.1indirect
PyPIpyasn10.6.4indirect
PyPIpyasn1-modules0.4.2indirect
PyPIpycparser2.22indirect
PyPIpydantic-core2.33.2indirect
PyPIpydantic-core2.46.4indirect
PyPIpydantic-settings2.10.1indirect
PyPIpygments2.20.0indirect
PyPIpyjwt2.13.0indirect
PyPIpymdown-extensions11.0.1indirect
PyPIpyproject-api1.9.0indirect
PyPIpytest9.0.3indirect
PyPIpytest-cov6.1.1indirect
PyPIpython-dateutil2.9.0.post0indirect
PyPIpython-dotenv1.2.2indirect
PyPIpython-multipart0.0.31indirect
PyPIpytz2025.2indirect
PyPIpywin32310indirect
PyPIpywin32312indirect
PyPIpyyaml6.0.2indirect
PyPIpyyaml-env-tag1.1indirect
PyPIreferencing0.36.2indirect
PyPIregex2024.11.6indirect
PyPIrequests2.33.0indirect
PyPIrequests-oauthlib2.0.0indirect
PyPIrequests-toolbelt1.0.0indirect
PyPIrequirements-parser0.13.0indirect
PyPIrpds-py0.25.1indirect
PyPIrsa4.9.1indirect
PyPIruff0.11.11indirect
PyPIsetuptools83.0.0indirect
PyPIsix1.17.0indirect
PyPIsmmap5.0.2indirect
PyPIsniffio1.3.1indirect
PyPIsqlalchemy2.0.41indirect
PyPIsse-starlette2.3.6indirect
PyPIstarlette1.3.1indirect
PyPItenacity9.1.2indirect
PyPItiktoken0.9.0indirect
PyPItinytag2.3.0indirect
PyPItomli2.2.1indirect
PyPItox4.26.0indirect
PyPItox-uv1.25.0indirect
PyPItqdm4.67.1indirect
PyPItyping-extensions4.13.2indirect
PyPItyping-extensions4.16.0indirect
PyPItyping-inspect0.9.0indirect
PyPItyping-inspection0.4.1indirect
PyPItyping-inspection0.4.2indirect
PyPIurllib32.7.0indirect
PyPIuuid-utils0.17.0indirect
PyPIuv0.11.15indirect
PyPIuvicorn0.34.3indirect
PyPIvirtualenv20.36.1indirect
PyPIwatchdog6.0.0indirect
PyPIwebsocket-client1.8.0indirect
PyPIwebsockets15.0.1indirect
PyPIwrapt1.17.2indirect
PyPIxxhash3.5.0indirect
PyPIyarl1.20.0indirect
PyPIzstandard0.23.0indirect
Dependency advisories 0

Installing pypi:llm-sandbox@0.3.44 pulls in 5 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 vndee/llm-sandbox. Read them side by side →

100deepset-ai/haystackOpen-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.Exceptional99ray-project/rayRay is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.Exceptional97NVIDIA-NeMo/CuratorScalable data pre processing and curation toolkit for LLMsExceptional97redis/redis-vl-pythonRedis Vector Library (RedisVL) -- the AI-native Python client for Redis.Exceptional100PrefectHQ/prefectPrefect is a workflow orchestration framework for building resilient data pipelines in Python.Exceptional100optuna/optunaA hyperparameter optimization frameworkExceptional

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.