Public record
Software health reportschema 0.34.0 · metrics 2.10.0 · 2026-08-28 05:29 UTC

MinishLab / semble

Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read

PythonMIT★ 5,966 stars⑂ 257 forkssince Apr 2026View on GitHub ↗
KindLibraryCommand-line toolhow this is determined
#agents#code-search#embeddings#mcp#mcp-server#model-context-protocol#retrieval

MinishLab/semble holds a health index of 91 out of 100, placing it in the Excellent band. It scores highest on Engineering Quality (91/100) and lowest on Security (57/100). It was last updated 2 days ago. A single contributor accounts for most of its recent work.

91
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.

91
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 77 is calibrated to 91 on the published index scale (record calibration 2026-08-02).

Ownership

MinishOrganization
390 followers12 public repossince Aug 2024

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

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publishTags
PyPIsemble0.5.5121,9132715 days agocode-searchhybrid-searchsemantic-searchmcpagentragembeddings

Metrics by category

Vitality

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

86Excellent · 21% of overall

Development activity

77Good
How it's scored
36/36Push recency — last push 2 days ago
13.2/36Commit cadence — 19/52 weeks with commits
18/18Commit volume — 135 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 15 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year135
human_commit_share1
days_since_last_push2
active_weeks_last_year19

Release discipline

100Exceptional
How it's scored
27/27Ships releases — 26 releases published
36/36Release recency — latest release 15 days ago
27/27Release cadence — a release every ~6.7 days
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count26
latest_release_tagv0.5.5
releases_from_tagsno
days_since_latest_release15
mean_days_between_releases6.7
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?

83Excellent · 17% of overall

Popularity & adoption

87Excellent
How it's scored
60/60Stars — 5,966 stars
20.1/25Forks — 257 forks
6.8/15Watchers — 18 watchers
Inputs used
forks257
stars5,966
watchers18
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

Community health

77Good
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
6.3/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges3
has_contributingyes
has_issue_templateno
has_code_of_conductno
readme_badge_servicescodecov.io, shields.io
has_pull_request_templateyes

Ecosystem adoption (downloads)

85Excellent
How it's scored
67.8/80Monthly downloads — 121,913 downloads/month across pypi
0/20Registry dependents — not reported by this ecosystem
Inputs used
packagessemble
dependents—
ecosystemspypi
total_downloads—
monthly_downloads121,913
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?

68Good · 23% of overall

Maintainer resilience (bus factor)

39Weak
How it's scored
9/54Bus factor — 1 contributor(s) cover half of all commits
7.7/22.5Commit distribution — top contributor authored 66% of commits
12.2/13.5Contributor breadth — 9 contributors
10/10OpenSSF Scorecard: Contributors — project has 4 contributing companies or organizations
Inputs used
bus_factor1
contributors_sampled9
top_contributor_share0.659

Issue & PR responsiveness

86Excellent
How it's scored
41.6/42Issue resolution — 99% of issues closed
25.4/30PR acceptance — 132/156 decided PRs merged
8.7/13Newcomer PR acceptance — 2/3 first-time contributors' PRs merged in 30d
10.5/15OpenSSF Scorecard: Code-Review — Found 21/30 approved changesets -- score normalized to 7
Inputs used
merged_prs132
open_issues1
closed_issues95
prs_merged_7d2
prs_decided_7d2
prs_merged_30d9
prs_decided_30d10
issue_closed_ratio0.99
closed_unmerged_prs24
first_time_authors_30d2
first_time_prs_merged_30d2
first_time_prs_decided_30d3

Ownership & stewardship

61Moderate
How it's scored
30/30Ownership backing — organization-owned
0/20Verified domain
18.6/25Owner reach — 390 followers of MinishLab
12.2/25Track record — 12 public repos, account ~2 yr old
Inputs used
followers390
owner_typeOrganization
is_verifiedno
owner_loginMinishLab
public_repos12
account_age_days748

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 1 package(s) on pypi
35/35Publish recency — latest publish 15 days ago
20/20Version history — 27 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagessemble
ecosystemspypi
any_deprecatedno
min_days_since_publish15

Engineering Quality

Are baseline engineering and documentation practices in place?

91Excellent · 19% of overall

Engineering practices

92Excellent
How it's scored
24/24CI workflows — 2 workflow(s)
24/24Tests present
16/16Linter config — pyproject.toml ([tool.ruff])
9.6/9.6Pre-commit hooks
0/6.4.editorconfig
18/20OpenSSF Scorecard: CI-Tests — 29 out of 30 merged PRs checked by a CI test -- score normalized to 9
Inputs used
has_ciyes
has_testsyes
has_editorconfigno
has_linter_configyes
has_precommit_configyes

Documentation

90Excellent
How it's scored
30/30README
25/25Documentation directory
15/15Documentation / homepage site — https://minish.ai/packages/semble/introduction/
10/10Repository description
10/10Topics — 7 topics
0/10Wiki
Inputs used
topicsagents, code-search, embeddings, mcp, mcp-server, model-context-protocol, retrieval
has_wikino
homepagehttps://minish.ai/packages/semble/introduction/
docs_sitehttps://minish.ai/packages/semble/introduction/
has_readmeyes
has_docs_diryes
has_descriptionyes

Security

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

57Moderate · 16% of overall

Security posture

46Weak
How it's scored
7.5/7.5Binary-Artifacts — no binaries found in the repo
0/7.5Branch-Protection — branch protection not enabled on development/release branches
2.2/2.5CI-Tests — 29 out of 30 merged PRs checked by a CI test -- score normalized to 9
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
5.2/7.5Code-Review — Found 21/30 approved changesets -- score normalized to 7
2.5/2.5Contributors — project has 4 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
7.5/7.5Maintained — 30 commit(s) and 15 issue activity found in the last 90 days -- score normalized to 10
5/5Packaging — packaging workflow detected
2/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 4
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 — 39 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated17
scorecard_versionv5.5.0
checks_inconclusive1
scorecard_aggregate4.6
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_packages30
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:semble@0.5.5 runtime dependency closure — what installing the published package pulls in — 30 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.

80Excellent · 4% of overall

Agent context & guidance

85Excellent
How it's scored
45/45Agent instructions — src/semble/agents/claude.md, src/semble/agents/gemini.md
0/15Machine-readable docs (llms.txt)
40/40Legible commit history — 100 of 100 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtno
llms_txt_url—
legible_history_share1
agent_instruction_filessrc/semble/agents/claude.md, src/semble/agents/gemini.md
agent_instruction_max_bytes2,122

Verify loop (build / test / typecheck)

76Good
How it's scored
18/18One-command bootstrap — Makefile
22/22Automated tests
11/11Lint / format config — pyproject.toml ([tool.ruff])
11/11Static type checking — src/semble/py.typed
10/10Reproducible environment — lockfile
0/10Demonstrated agent practice — no agent-authored commits among the last 100
0/8Automated maintenance — no automated dependency updates observed
4/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 4
Inputs used
has_nixno
has_testsyes
lockfilesuv.lock
has_dockerfileno
typed_languageno
bootstrap_filesMakefile
has_devcontainerno
has_linter_configyes
typecheck_configssrc/semble/py.typed
agent_commit_share0
toolchain_manifests—
dependency_bot_commit_share0

Code legibility for models

82Excellent
How it's scored
27/45Type-checkable code — Python with type-check config (src/semble/py.typed)
55/55Manageable file sizes — 0/66 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes25,544
source_files_sampled66
oversized_source_files0

Key facts

5,966GitHub stars
9contributors
135commits, last 12 months
2days since last push
26releases
1bus factor
1open issues
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 ★ / 257 ⇿
0Stars
257Forks
26Releases

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.

050100150200250300257252026-042026-062026-08
Major 0Minor 5Patch 21
OpenSSF Scorecard 4.6 / 10
4.6aggregate

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 · 2026-08-28 05:29 UTC

10Binary-Artifactsno binaries found in the repo
0Branch-Protectionbranch protection not enabled on development/release branches
9CI-Tests29 out of 30 merged PRs checked by a CI test -- score normalized to 9
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
7Code-ReviewFound 21/30 approved changesets -- score normalized to 7
10Contributorsproject has 4 contributing companies or organizations
10Dangerous-Workflowno dangerous workflow patterns detected
0Dependency-Update-Toolno update tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
10Maintained30 commit(s) and 15 issue activity found in the last 90 days -- score normalized to 10
10Packagingpackaging workflow detected
4Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 4
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
0Vulnerabilities39 existing vulnerabilities detected
Direct dependencies 7
RegistryPackageVersion constraintManifest
PyPImodel2vec>=0.4.0pyproject.toml
PyPIvicinity>=0.4.4pyproject.toml
PyPInumpy>=1.24.0pyproject.toml
PyPIpathspec>=0.12pyproject.toml
PyPIorjson—pyproject.toml
PyPIquestionary>=2.0,<3.0pyproject.toml
PyPIsemble-grammars>=0.1.2pyproject.toml
All dependencies 134

Full resolved dependency set from the GitHub dependency graph: 8 direct and 126 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPImodel2vec0.8.1direct
PyPInumpy2.2.6direct
PyPInumpy2.4.4direct
PyPIorjson3.11.9direct
PyPIpathspec1.1.1direct
PyPIquestionary2.1.1direct
PyPIsemble-grammars0.1.2direct
PyPIvicinity0.4.4direct
PyPIannotated-doc0.0.4indirect
PyPIannotated-types0.7.0indirect
PyPIanyio4.13.0indirect
PyPIast-serialize0.3.0indirect
PyPIattrs26.1.0indirect
PyPIcertifi2026.4.22indirect
PyPIcffi2.0.0indirect
PyPIcfgv3.5.0indirect
PyPIcharset-normalizer3.4.7indirect
PyPIclick8.3.3indirect
PyPIcolorama0.4.6indirect
PyPIcontourpy1.3.2indirect
PyPIcontourpy1.3.3indirect
PyPIcoverage7.14.0indirect
PyPIcryptography48.0.0indirect
PyPIcuda-bindings12.9.4indirect
PyPIcuda-pathfinder1.5.4indirect
PyPIcycler0.12.1indirect
PyPIdistlib0.4.0indirect
PyPIdistro1.9.0indirect
PyPIdocstring-parser-fork0.0.14indirect
PyPIeinops0.8.2indirect
PyPIexceptiongroup1.3.1indirect
PyPIfilelock3.29.0indirect
PyPIfonttools4.62.1indirect
PyPIfsspec2026.4.0indirect
PyPIh110.16.0indirect
PyPIhf-xet1.5.0indirect
PyPIhttpcore1.0.9indirect
PyPIhttpx0.28.1indirect
PyPIhttpx-sse0.4.3indirect
PyPIhuggingface-hub1.14.0indirect
PyPIidentify2.6.19indirect
PyPIidna3.14indirect
PyPIiniconfig2.3.0indirect
PyPIjinja23.1.6indirect
PyPIjiter0.14.0indirect
PyPIjoblib1.5.3indirect
PyPIjsonschema4.26.0indirect
PyPIjsonschema-specifications2025.9.1indirect
PyPIkiwisolver1.5.0indirect
PyPIlibrt0.11.0indirect
PyPImarkdown-it-py4.2.0indirect
PyPImarkupsafe3.0.3indirect
PyPImatplotlib3.10.9indirect
PyPImcp1.27.1indirect
PyPImdurl0.1.2indirect
PyPImpmath1.3.0indirect
PyPImypy2.1.0indirect
PyPImypy-extensions1.1.0indirect
PyPInetworkx3.4.2indirect
PyPInetworkx3.6.1indirect
PyPInodeenv1.10.0indirect
PyPInvidia-cublas-cu1212.8.4.1indirect
PyPInvidia-cuda-cupti-cu1212.8.90indirect
PyPInvidia-cuda-nvrtc-cu1212.8.93indirect
PyPInvidia-cuda-runtime-cu1212.8.90indirect
PyPInvidia-cudnn-cu129.10.2.21indirect
PyPInvidia-cufft-cu1211.3.3.83indirect
PyPInvidia-cufile-cu121.13.1.3indirect
PyPInvidia-curand-cu1210.3.9.90indirect
PyPInvidia-cusolver-cu1211.7.3.90indirect
PyPInvidia-cusparse-cu1212.5.8.93indirect
PyPInvidia-cusparselt-cu120.7.1indirect
PyPInvidia-nccl-cu122.27.5indirect
PyPInvidia-nvjitlink-cu1212.8.93indirect
PyPInvidia-nvshmem-cu123.4.5indirect
PyPInvidia-nvtx-cu1212.8.90indirect
PyPIopenai2.36.0indirect
PyPIpackaging26.2indirect
PyPIpillow12.2.0indirect
PyPIplatformdirs4.9.6indirect
PyPIpluggy1.6.0indirect
PyPIpre-commit4.6.0indirect
PyPIprompt-toolkit3.0.52indirect
PyPIpycparser3.0indirect
PyPIpydantic2.13.4indirect
PyPIpydantic-core2.46.4indirect
PyPIpydantic-settings2.14.1indirect
PyPIpydoclint0.8.3indirect
PyPIpygments2.20.0indirect
PyPIpyjwt2.12.1indirect
PyPIpyparsing3.3.2indirect
PyPIpytest9.0.3indirect
PyPIpytest-cov7.1.0indirect
PyPIpython-dateutil2.9.0.post0indirect
PyPIpython-discovery1.3.0indirect
PyPIpython-dotenv1.2.2indirect
PyPIpython-multipart0.0.28indirect
PyPIpywin32311indirect
PyPIpyyaml6.0.3indirect
PyPIreferencing0.37.0indirect
PyPIregex2026.5.9indirect
PyPIrequests2.34.0indirect
PyPIrich15.0.0indirect
PyPIrpds-py0.30.0indirect
PyPIruff0.15.12indirect
PyPIsafetensors0.7.0indirect
PyPIscikit-learn1.7.2indirect
PyPIscikit-learn1.8.0indirect
PyPIscipy1.15.3indirect
PyPIscipy1.17.1indirect
PyPIsentence-transformers5.5.0indirect
PyPIsetuptools82.0.1indirect
PyPIshellingham1.5.4indirect
PyPIsix1.17.0indirect
PyPIsniffio1.3.1indirect
PyPIsse-starlette3.4.3indirect
PyPIstarlette1.0.0indirect
PyPIsympy1.14.0indirect
PyPIthreadpoolctl3.6.0indirect
PyPItiktoken0.12.0indirect
PyPItokenizers0.22.2indirect
PyPItomli2.4.1indirect
PyPItorch2.10.0indirect
PyPItqdm4.67.3indirect
PyPItransformers5.8.0indirect
PyPItree-sitter0.25.2indirect
PyPItriton3.6.0indirect
PyPItyper0.25.1indirect
PyPItyping-extensions4.15.0indirect
PyPItyping-inspection0.4.2indirect
PyPIurllib32.7.0indirect
PyPIuvicorn0.46.0indirect
PyPIvirtualenv21.3.2indirect
PyPIwcwidth0.7.0indirect
Dependency advisories 0

Installing pypi:semble@0.5.5 pulls in 30 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 MinishLab/semble. Read them side by side →

95Tencent/WeKnoraOpen-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.Exceptional96PrefectHQ/fastmcp🚀 The fast, Pythonic way to build MCP servers and clients.Exceptional100deepset-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.Exceptional96electric-sql/electricThe agent platform built on sync.Exceptional95trpc-group/trpc-agent-goA Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.Exceptional100run-llama/llama_indexLlamaIndex is the leading document agent and OCR platformExceptional

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.