Public record
Software health reportschema 0.34.0 · metrics 2.10.0 · 2026-10-04 12:31 UTC

lyonzin / knowledge-rag

Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external servers, zero API keys.

PythonMIT★ 290 stars⑂ 42 forkssince Feb 2026View on GitHub ↗
KindCommand-line toolLibraryMCP serverhow this is determined
#claude#claude-code#local-ai#mcp#rag#retrieval-augmented-generation#semantic-search#vector-database#knowledge-base#reranking#document-search#hybrid-search#mcp-server#antigravity#claude-code-cli#codex#cursor-ai#inteligencia-artificial#rag-chatbot#rag-pipeline

lyonzin/knowledge-rag holds a health index of 87 out of 100, placing it in the Excellent band. It scores highest on Engineering Quality (94/100) and lowest on Sustainability & Governance (55/100). It was last updated today. A single contributor accounts for most of its recent work.

87
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.

87
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 73 is calibrated to 87 on the published index scale (record calibration 2026-08-02).

Ownership

Lyon.Personal account
6 followers39 public repossince Mar 2019HARDWAY

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
PyPIknowledge-rag4.10.02,343470 days agobm25chromadbclaude-codeembeddingsfastembedhybrid-searchknowledge-baselocal-aimcpragrerankingretrieval-augmented-generationsemantic-search
npmknowledge-rag4.9.04512211 days agoragmcpclaude-codesemantic-searchembeddingsknowledge-baselocal-airetrieval-augmented-generationhybrid-searchclaude

Metrics by category

Vitality

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

90Excellent · 21% of overall

Development activity

83Excellent
How it's scored
36/36Push recency — last push 0 days ago
18.7/36Commit cadence — 27/52 weeks with commits
18/18Commit volume — 250 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 14 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year250
human_commit_share0.76
days_since_last_push0
active_weeks_last_year27

Release discipline

100Exceptional
How it's scored
27/27Ships releases — 19 releases published
36/36Release recency — latest release 0 days ago
27/27Release cadence — a release every ~7.1 days
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count19
latest_release_tagv4.10.0
releases_from_tagsno
days_since_latest_release0
mean_days_between_releases7.1
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

53Moderate
How it's scored
39.9/60Stars — 290 stars
13.4/25Forks — 42 forks
0/15Watchers — 1 watchers
Inputs used
forks42
stars290
watchers1
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_badges10
has_contributingyes
has_issue_templateno
has_code_of_conductyes
readme_badge_servicesbestpractices.coreinfrastructure.org, github.com, shields.io
has_pull_request_templateyes

Ecosystem adoption (downloads)

58Moderate
How it's scored
46/80Monthly downloads — 2,794 downloads/month across npm, pypi
0/20Registry dependents — not reported by this ecosystem
Inputs used
packagesknowledge-rag, knowledge-rag
dependents—
ecosystemsnpm, pypi
total_downloads—
monthly_downloads2,794
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?

55Moderate · 23% of overall

Maintainer resilience (bus factor)

23At Risk
How it's scored
9/54Bus factor — 1 contributor(s) cover half of all commits
1/22.5Commit distribution — top contributor authored 96% of commits
6.8/13.5Contributor breadth — 5 contributors
6/10OpenSSF Scorecard: Contributors — project has 2 contributing companies or organizations -- score normalized to 6
Inputs used
bus_factor1
contributors_sampled5
top_contributor_share0.957

Issue & PR responsiveness

63Moderate
How it's scored
42/42Issue resolution — 100% of issues closed
19.8/30PR acceptance — 122/185 decided PRs merged
0/13Newcomer PR acceptance — 0/1 first-time contributors' PRs merged in 30d
1.5/15OpenSSF Scorecard: Code-Review — Found 4/26 approved changesets -- score normalized to 1
Inputs used
merged_prs122
open_issues0
closed_issues45
prs_merged_7d6
prs_decided_7d8
prs_merged_30d7
prs_decided_30d9
issue_closed_ratio1
closed_unmerged_prs63
first_time_authors_30d1
first_time_prs_merged_30d0
first_time_prs_decided_30d1

Ownership & stewardship

50Moderate
How it's scored
10/30Ownership backing — personal (user) account
0/20Verified domain — not applicable to user accounts
6.1/25Owner reach — 6 followers of lyonzin
23.7/25Track record — 39 public repos, account ~7 yr old
Inputs used
followers6
owner_typeUser
is_verified—
owner_loginlyonzin
public_repos39
account_age_days2,757
Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 2 package(s) on npm, pypi
35/35Publish recency — latest publish 0 days ago
20/20Version history — 47 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagesknowledge-rag, knowledge-rag
ecosystemsnpm, pypi
any_deprecatedno
min_days_since_publish0

Engineering Quality

Are baseline engineering and documentation practices in place?

94Exceptional · 19% of overall

Engineering practices

90Excellent
How it's scored
24/24CI workflows — 7 workflow(s)
24/24Tests present
16/16Linter config — pyproject.toml ([tool.ruff])
9.6/9.6Pre-commit hooks
0/6.4.editorconfig
16/20OpenSSF Scorecard: CI-Tests — 25 out of 30 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://pypi.org/project/knowledge-rag/
10/10Repository description
10/10Topics — 20 topics
10/10Wiki
Inputs used
topicsclaude, claude-code, local-ai, mcp, rag, retrieval-augmented-generation, semantic-search, vector-database, knowledge-base, reranking, document-search, hybrid-search, mcp-server, antigravity, claude-code-cli, codex, cursor-ai, inteligencia-artificial, rag-chatbot, rag-pipeline
has_wikiyes
homepagehttps://pypi.org/project/knowledge-rag/
docs_sitehttps://pypi.org/project/knowledge-rag/
has_readmeyes
has_docs_diryes
has_descriptionyes

Security

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

61Moderate · 16% of overall

Security posture

61Moderate
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 — 25 out of 30 merged PRs checked by a CI test -- score normalized to 8
1.2/2.5CII-Best-Practices — badge detected: Passing
0.8/7.5Code-Review — Found 4/26 approved changesets -- score normalized to 1
1.5/2.5Contributors — project has 2 contributing companies or organizations -- score normalized to 6
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 14 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
3.5/5SAST — SAST tool detected but not run on all commits
5/5Security-Policy — security policy file detected
0/7.5Signed-Releases — no data
0/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
3/7.5Vulnerabilities — 6 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated17
scorecard_versionv5.5.0
checks_inconclusive1
scorecard_aggregate6.1
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.

63Moderate · 4% of overall

Agent context & guidance

40Weak
How it's scored
0/45Agent instructions — no CLAUDE.md / AGENTS.md / editor rules
0/15Machine-readable docs (llms.txt)
40/40Legible commit history — 76 of 76 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtno
llms_txt_url—
legible_history_share1
agent_instruction_files—
agent_instruction_max_bytes—

Verify loop (build / test / typecheck)

69Good
How it's scored
18/18One-command bootstrap — tests/fixtures/formats/Makefile
22/22Automated tests
11/11Lint / format config — pyproject.toml ([tool.ruff])
0/11Static type checking
10/10Reproducible environment — Dockerfile
0/10Demonstrated agent practice — no agent-authored commits among the last 100
8/8Automated maintenance — 7 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
lockfiles—
has_dockerfileyes
typed_languageno
bootstrap_filestests/fixtures/formats/Makefile
has_devcontainerno
has_linter_configyes
typecheck_configs—
agent_commit_share0
toolchain_manifests—
dependency_bot_commit_share0.07

Code legibility for models

55Moderate
How it's scored
0/45Type-checkable code — Python without a type-check config
54.6/55Manageable file sizes — 1/148 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes241,842
source_files_sampled148
oversized_source_files1

Machine-readable interfaces

100Exceptional
How it's scored
40/40API schema (OpenAPI/GraphQL/proto) — tests/fixtures/formats/sample.proto
20/20MCP server
40/40Runnable examples — examples, notebooks
Inputs used
example_dirsexamples, notebooks
has_mcp_signalyes
api_schema_filestests/fixtures/formats/sample.proto
interfaces_expected_of—

Key facts

290GitHub stars
5contributors
250commits, last 12 months
0days since last push
19releases
1bus factor
0open issues
npm, PyPIpackage ecosystems

Data collection warnings

  • Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
  • deps.dev does not index pypi:knowledge-rag@4.10.0; advisories assessed against the repository dependency graph instead
  • No resolved dependencies carried a version and a supported ecosystem

More detail

Star and fork history 0 ★ / 42 ⇿
0Stars
42Forks
18Releases

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.

010203040504242026-022026-062026-10
Major 1Minor 8Patch 9
OpenSSF Scorecard 6.1 / 10
6.1aggregate

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 · 2026-10-04 12:31 UTC

10Binary-Artifactsno binaries found in the repo
3Branch-Protectionbranch protection is not maximal on development and all release branches
8CI-Tests25 out of 30 merged PRs checked by a CI test -- score normalized to 8
5CII-Best-Practicesbadge detected: Passing
1Code-ReviewFound 4/26 approved changesets -- score normalized to 1
6Contributorsproject has 2 contributing companies or organizations -- score normalized to 6
10Dangerous-Workflowno dangerous workflow patterns detected
10Dependency-Update-Toolupdate tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
10Maintained30 commit(s) and 14 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
7SASTSAST tool detected but not run on all commits
10Security-Policysecurity policy file detected
n/aSigned-Releasesno releases found
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
4Vulnerabilities6 existing vulnerabilities detected
Direct dependencies 12
RegistryPackageVersion constraintManifest
PyPIchromadb>=1.4.0pyproject.toml
PyPIpymupdf>=1.23.0pyproject.toml
PyPIfastembed>=0.4.0pyproject.toml
PyPImcp>=2.0.0,<3.0.0pyproject.toml
PyPInumpy>=1.24.0pyproject.toml
PyPIrequests>=2.33.0pyproject.toml
PyPIbeautifulsoup4>=4.12.0pyproject.toml
PyPIpython-docx>=1.0.0pyproject.toml
PyPIopenpyxl>=3.1.0pyproject.toml
PyPIpython-pptx>=1.0.0pyproject.toml
PyPIwatchdog>=4.0.0pyproject.toml
PyPIpyyaml>=6.0pyproject.toml
All dependencies 35

Full resolved dependency set from the GitHub dependency graph: 12 direct and 23 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPIbeautifulsoup4—direct
PyPIchromadb—direct
PyPIfastembed—direct
PyPImcp—direct
PyPInumpy—direct
PyPIopenpyxl—direct
PyPIpymupdf—direct
PyPIpython-docx—direct
PyPIpython-pptx—direct
PyPIpyyaml—direct
PyPIrequests—direct
PyPIwatchdog—direct
PyPIbandit—indirect
PyPIhatchling—indirect
PyPIhypothesis—indirect
PyPIinterrogate—indirect
PyPImutmut—indirect
PyPImypy—indirect
PyPInvidia-cublas-cu12—indirect
PyPInvidia-cuda-runtime-cu12—indirect
PyPInvidia-cudnn-cu12—indirect
PyPIonnxruntime-gpu—indirect
PyPIpip-audit—indirect
PyPIpre-commit—indirect
PyPIpsutil—indirect
PyPIpytest—indirect
PyPIpytest-benchmark—indirect
PyPIpytest-cov—indirect
PyPIpytest-memray—indirect
PyPIpytest-rerunfailures—indirect
PyPIpytest-timeout—indirect
PyPIradon—indirect
PyPIruff—indirect
PyPIuvicorn—indirect
PyPIvulture—indirect
Dependency advisories not assessed

Advisory matching could not run for this report: No resolved dependencies carried a version and a supported ecosystem

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 lyonzin/knowledge-rag. Read them side by side →

94Tencent/WeKnoraOpen-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.Exceptional97Observal/ObservalObserval is self-hosted registry for your coding agent extensions with a built in insight engine. Setup Observal, define the scope and share your Skills, MCPs and Agents with your peers.Exceptional94jgravelle/jcodemunch-mcpCut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.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.Exceptional98awslabs/cli-agent-orchestratorMulti-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessionsExceptional94infiniflow/infinityThe AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.Exceptional

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, npm.