Public record
Software health reportschema 0.34.0 · metrics 2.10.0 · 2026-09-17 09:34 UTC

LazyAGI / LazyLLM

Easiest and laziest way for building multi-agent LLMs applications.

PythonApache-2.0★ 3,885 stars⑂ 415 forkssince Jun 2024View on GitHub ↗
KindCommand-line toolLibraryNetwork servicehow this is determined
#llms#ai-agent#deep-learning#langchain#llamaindex#rag#agents#data#finetuning#framework#llm#documentation-tool#knowlege-graph#lazyllm

LazyAGI/LazyLLM holds a health index of 89 out of 100, placing it in the Excellent band. It scores highest on Vitality (95/100) and lowest on Security (46/100). It was last updated today. 2 contributors account for most of its recent work.

89
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.

89
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 75 is calibrated to 89 on the published index scale (record calibration 2026-08-02).

Ownership

LazyAGIOrganization
255 followers10 public repossince Jun 2024

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

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publish
PyPIlazyllm1.3.06,8345017 days ago

Metrics by category

Vitality

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

95Exceptional · 21% of overall

Development activity

99Exceptional
How it's scored
36/36Push recency — last push 0 days ago
34.6/36Commit cadence — 50/52 weeks with commits
18/18Commit volume — 379 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 2 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year379
human_commit_share1
days_since_last_push0
active_weeks_last_year50

Release discipline

90Excellent
How it's scored
27/27Ships releases — 37 releases published
36/36Release recency — latest release 17 days ago
27/27Release cadence — a release every ~6.5 days
0/10OpenSSF Scorecard: Signed-Releases — Project has not signed or included provenance with any releases.
Inputs used
releases_count37
latest_release_tagv1.3.0
releases_from_tagsno
days_since_latest_release17
mean_days_between_releases6.5

Community & Adoption

Does the project have users, downloads, attention, and a welcoming setup for contributors?

83Excellent · 17% of overall

Popularity & adoption

92Excellent
How it's scored
58.2/60Stars — 3,885 stars
21.8/25Forks — 415 forks
12.1/15Watchers — 150 watchers
Inputs used
forks415
stars3,885
watchers150
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

Community health

72Good
How it's scored
22.5/22.5README
22.5/22.5License — recognized license (Apache-2.0)
0/18CONTRIBUTING guide
13.5/13.5Code of conduct
0/7.2Issue template
6.3/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges3
has_contributingno
has_issue_templateno
has_code_of_conductyes
readme_badge_servicesgithub.com, shields.io
has_pull_request_templateyes

Sustainability & Governance

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

74Good · 23% of overall

Maintainer resilience (bus factor)

61Moderate
How it's scored
25.2/54Bus factor — 2 contributor(s) cover half of all commits
12.4/22.5Commit distribution — top contributor authored 45% of commits
13.5/13.5Contributor breadth — 50 contributors
10/10OpenSSF Scorecard: Contributors — project has 5 contributing companies or organizations
Inputs used
bus_factor2
contributors_sampled50
top_contributor_share0.448

Issue & PR responsiveness

82Excellent
How it's scored
32.2/42Issue resolution — 77% of issues closed
25/30PR acceptance — 960/1,153 decided PRs merged
13/13Newcomer PR acceptance — 6/6 first-time contributors' PRs merged in 30d
12/15OpenSSF Scorecard: Code-Review — Found 26/30 approved changesets -- score normalized to 8
Inputs used
merged_prs960
open_issues33
closed_issues108
prs_merged_7d4
prs_decided_7d5
prs_merged_30d30
prs_decided_30d34
issue_closed_ratio0.766
closed_unmerged_prs193
first_time_authors_30d5
first_time_prs_merged_30d6
first_time_prs_decided_30d6

Ownership & stewardship

60Moderate
How it's scored
30/30Ownership backing — organization-owned
0/20Verified domain
17.3/25Owner reach — 255 followers of LazyAGI
12.2/25Track record — 10 public repos, account ~2 yr old
Inputs used
followers255
owner_typeOrganization
is_verifiedno
owner_loginLazyAGI
public_repos10
account_age_days835

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 1 package(s) on pypi
35/35Publish recency — latest publish 17 days ago
20/20Version history — 50 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packageslazyllm
ecosystemspypi
any_deprecatedno
min_days_since_publish17

Engineering Quality

Are baseline engineering and documentation practices in place?

74Good · 19% of overall

Engineering practices

64Moderate
How it's scored
24/24CI workflows — 3 workflow(s)
24/24Tests present
16/16Linter config — .flake8
0/9.6Pre-commit hooks
0/6.4.editorconfig
0/20OpenSSF Scorecard: CI-Tests — 0 out of 30 merged PRs checked by a CI test -- score normalized to 0
Inputs used
has_ciyes
has_testsyes
has_editorconfigno
has_linter_configyes
has_precommit_configno

Documentation

90Excellent
How it's scored
30/30README
25/25Documentation directory
15/15Documentation / homepage site — https://docs.lazyllm.ai/
10/10Repository description
10/10Topics — 14 topics
0/10Wiki
Inputs used
topicsllms, ai-agent, deep-learning, langchain, llamaindex, rag, agents, data, finetuning, framework, llm, documentation-tool, knowlege-graph, lazyllm
has_wikino
homepagehttps://docs.lazyllm.ai/
docs_sitehttps://docs.lazyllm.ai/
has_readmeyes
has_docs_diryes
has_descriptionyes

Security

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

46Weak · 16% of overall

Security posture

32At Risk
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
0/2.5CI-Tests — 0 out of 30 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
6/7.5Code-Review — Found 26/30 approved changesets -- score normalized to 8
2.5/2.5Contributors — project has 5 contributing companies or organizations
0/10Dangerous-Workflow — 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 2 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
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 — Project has not signed or included provenance with any releases.
0/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
0/7.5Vulnerabilities — 104 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated18
scorecard_versionv5.5.0
checks_inconclusive0
scorecard_aggregate3.2

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_packages31
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:lazyllm@1.3.0 runtime dependency closure — what installing the published package pulls in — 31 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.

64Moderate · 4% of overall

Agent context & guidance

85Excellent
How it's scored
45/45Agent instructions — docs/lazyllm-skill/assets/agent/agent.md, docs/lazyllm-skill/references/agent.md, lazyllm/AGENTS.md, lazyllm/common/AGENTS.md, lazyllm/components/AGENTS.md, lazyllm/flow/AGENTS.md, lazyllm/module/AGENTS.md, lazyllm/module/llms/onlinemodule/AGENTS.md, lazyllm/tools/AGENTS.md, lazyllm/tools/agent/AGENTS.md, lazyllm/tools/rag/AGENTS.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_filesdocs/lazyllm-skill/assets/agent/agent.md, docs/lazyllm-skill/references/agent.md, lazyllm/AGENTS.md, lazyllm/common/AGENTS.md, lazyllm/components/AGENTS.md, lazyllm/flow/AGENTS.md, lazyllm/module/AGENTS.md, lazyllm/module/llms/onlinemodule/AGENTS.md, lazyllm/tools/AGENTS.md, lazyllm/tools/agent/AGENTS.md, lazyllm/tools/rag/AGENTS.md
agent_instruction_max_bytes15,837

Verify loop (build / test / typecheck)

61Moderate
How it's scored
18/18One-command bootstrap — Makefile
22/22Automated tests
11/11Lint / format config — .flake8
0/11Static type checking
0/10Reproducible environment
10/10Demonstrated agent practice — 9 of the last 100 commits agent-authored or agent-credited
0/8Automated maintenance — no automated dependency updates observed
0/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0
Inputs used
has_nixno
has_testsyes
lockfiles—
has_dockerfileno
typed_languageno
bootstrap_filesMakefile
has_devcontainerno
has_linter_configyes
typecheck_configs—
agent_commit_share0.09
toolchain_manifests—
dependency_bot_commit_share0

Code legibility for models

54Moderate
How it's scored
0/45Type-checkable code — Python without a type-check config
53.8/55Manageable file sizes — 20/886 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes476,471
source_files_sampled886
oversized_source_files20

Machine-readable interfaces

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

Key facts

3,885GitHub stars
50contributors
379commits, last 12 months
0days since last push
37releases
2bus factor
33open issues
PyPIpackage ecosystems

Data collection warnings

  • Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
  • First-time contributor figures cover 12 of 14 authors (cap 12)

More detail

Star and fork history 0 ★ / 415 ⇿
0Stars
415Forks
37Releases

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.

0100200300400500410102024-062025-072026-09
Major 0Minor 8Patch 21

Each point covers 3 days.

OpenSSF Scorecard 3.2 / 10
3.2aggregate

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 · 2026-09-17 09:33 UTC

10Binary-Artifactsno binaries found in the repo
3Branch-Protectionbranch protection is not maximal on development and all release branches
0CI-Tests0 out of 30 merged PRs checked by a CI test -- score normalized to 0
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
8Code-ReviewFound 26/30 approved changesets -- score normalized to 8
10Contributorsproject has 5 contributing companies or organizations
0Dangerous-Workflowdangerous workflow patterns detected
0Dependency-Update-Toolno update tool detected
0Fuzzingproject is not fuzzed
10Licenselicense file detected
10Maintained30 commit(s) and 2 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
0SASTSAST tool is not run on all commits -- score normalized to 0
0Security-Policysecurity policy file not detected
0Signed-ReleasesProject has not signed or included provenance with any releases.
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
0Vulnerabilities104 existing vulnerabilities detected
Direct dependencies 16
RegistryPackageVersion constraintManifest
PyPItoml—pyproject.toml
PyPItqdm—pyproject.toml
PyPIfilelock—pyproject.toml
PyPIpyyaml—pyproject.toml
PyPIpackaging—pyproject.toml
PyPIfastapi>=0.111.0pyproject.toml
PyPIloguru>=0.7.2pyproject.toml
PyPIpydantic>=2.11.7,<3.0.0pyproject.toml
PyPIrequests>=2.32.2pyproject.toml
PyPIuvicorn>=0.23.2pyproject.toml
PyPIcloudpickle>=3.0.0pyproject.toml
PyPIdocstring-parser>=0.16,<0.17pyproject.toml
PyPIjson5>=0.9.25,<0.10.0pyproject.toml
PyPIpyjwt>=2.8.0pyproject.toml
PyPIpsutil>=6.0.0,<7.0.0pyproject.toml
PyPIdeepdiff>=8.6.1pyproject.toml
All dependencies 202

Full resolved dependency set from the GitHub dependency graph: 32 direct and 170 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPIcloudpickle—direct
PyPIcloudpickle3.1.2direct
PyPIdeepdiff—direct
PyPIdeepdiff9.1.0direct
PyPIdocstring-parser—direct
PyPIdocstring-parser0.16direct
PyPIfastapi—direct
PyPIfastapi0.141.1direct
PyPIfilelock—direct
PyPIfilelock3.32.4direct
PyPIjson5—direct
PyPIjson50.9.28direct
PyPIloguru—direct
PyPIloguru0.7.3direct
PyPIpackaging—direct
PyPIpackaging26.3direct
PyPIpsutil—direct
PyPIpsutil6.1.1direct
PyPIpydantic—direct
PyPIpydantic2.13.4direct
PyPIpyjwt—direct
PyPIpyjwt2.13.0direct
PyPIpyyaml—direct
PyPIpyyaml6.0.3direct
PyPIrequests—direct
PyPIrequests2.34.2direct
PyPItoml—direct
PyPItoml0.10.2direct
PyPItqdm—direct
PyPItqdm4.70.0direct
PyPIuvicorn—direct
PyPIuvicorn0.52.4direct
PyPIaccelerate—indirect
PyPIaccelerate0.20.3indirect
PyPIannotated-doc0.0.5indirect
PyPIannotated-types—indirect
PyPIannotated-types0.8.0indirect
PyPIanyio—indirect
PyPIanyio4.14.2indirect
PyPIappdirs—indirect
PyPIasync-timeout—indirect
PyPIbeautifulsoup4—indirect
PyPIbitsandbytes—indirect
PyPIblack—indirect
PyPIbm25s—indirect
PyPIboto3—indirect
PyPIbotocore—indirect
PyPIcachebox5.2.3indirect
PyPIcertifi—indirect
PyPIcertifi2026.7.22indirect
PyPIchardet—indirect
PyPIcharset-normalizer3.5.1indirect
PyPIchattts—indirect
PyPIchromadb—indirect
PyPIclick—indirect
PyPIclick8.5.0indirect
PyPIcollie-lm—indirect
PyPIcolorama—indirect
PyPIcolorama0.4.6indirect
PyPIctranslate2—indirect
PyPIdashscope—indirect
PyPIdatasets—indirect
PyPIdatasketch1.9.0indirect
PyPIdeepspeed—indirect
PyPIdeepspeed0.12.3indirect
PyPIdiffusers—indirect
PyPIdistro—indirect
PyPIdocx2txt—indirect
PyPIdynaconf—indirect
PyPIebooklib—indirect
PyPIelasticsearch—indirect
PyPIexceptiongroup—indirect
PyPIexceptiongroup1.3.1indirect
PyPIfaiss-cpu—indirect
PyPIfasttext-predict0.9.2.4indirect
PyPIfire—indirect
PyPIflagembedding—indirect
PyPIflake8—indirect
PyPIflash-attn—indirect
PyPIfsspec—indirect
PyPIftfy—indirect
PyPIfunasr—indirect
PyPIgoogle—indirect
PyPIgradio—indirect
PyPIgradio5.49.1indirect
PyPIgradio-client—indirect
PyPIgrpcio—indirect
PyPIgrpcio-status—indirect
PyPIh11—indirect
PyPIh110.16.0indirect
PyPIhtml2text—indirect
PyPIhttpcore—indirect
PyPIhttpx—indirect
PyPIhuggingface-hub—indirect
PyPIhuggingface-hub0.35.3indirect
PyPIidna—indirect
PyPIidna3.19indirect
PyPIimageio—indirect
PyPIimageio-ffmpeg—indirect
PyPIinfinity-emb—indirect
PyPIjieba—indirect
PyPIjson-repair—indirect
PyPIlangfuse—indirect
PyPIlazyllm-llamafactory—indirect
PyPIlazyllm-lmdeploy—indirect
PyPIlazyllm-verl—indirect
PyPIlibcst1.4.0indirect
PyPIlightllm—indirect
PyPIloralib—indirect
PyPIloralib0.1.1indirect
PyPIlxml-html-clean0.4.3indirect
PyPImath-verify0.9.0indirect
PyPImcp—indirect
PyPImilvus-lite2.4.10indirect
PyPImistune—indirect
PyPImkdocs—indirect
PyPImkdocs-autorefs—indirect
PyPImkdocs-material—indirect
PyPImkdocs-section-index—indirect
PyPImkdocs-static-i18n—indirect
PyPImkdocstrings—indirect
PyPImkdocstrings-python—indirect
PyPImodelscope—indirect
PyPInbconvert—indirect
PyPInbformat—indirect
PyPInltk—indirect
PyPInumpy—indirect
PyPInumpy1.26.4indirect
PyPIolefile—indirect
PyPIopenai-whisper—indirect
PyPIopenpyxl—indirect
PyPIopensearch-py—indirect
PyPIopentelemetry-api—indirect
PyPIopentelemetry-exporter-otlp-proto-http—indirect
PyPIopentelemetry-sdk—indirect
PyPIoptimum—indirect
PyPIorderly-set5.5.0indirect
PyPIpandas—indirect
PyPIpeft—indirect
PyPIpeft0.3.0indirect
PyPIpluggy—indirect
PyPIpowermem—indirect
PyPIprotobuf—indirect
PyPIpsycopg2-binary—indirect
PyPIpyahocorasick2.3.0indirect
PyPIpydantic-core—indirect
PyPIpydantic-core2.46.4indirect
PyPIpydub—indirect
PyPIpymilvus—indirect
PyPIpymongo—indirect
PyPIpymysql—indirect
PyPIpypdf—indirect
PyPIpystemmer—indirect
PyPIpytesseract—indirect
PyPIpytest—indirect
PyPIpytest-cov—indirect
PyPIpytest-order—indirect
PyPIpytest-rerunfailures—indirect
PyPIpytest-xdist—indirect
PyPIpython-docx—indirect
PyPIpython-multipart—indirect
PyPIpython-pptx—indirect
PyPIqdrant-client—indirect
PyPIqdrant-client1.19.0indirect
PyPIqwen-vl-utils—indirect
PyPIrank-bm25—indirect
PyPIrapidfuzz—indirect
PyPIredis—indirect
PyPIredisvl—indirect
PyPIrotary-embedding-torch—indirect
PyPIscikit-learn—indirect
PyPIscipy—indirect
PyPIsentence-transformers—indirect
PyPIsentencepiece—indirect
PyPIsentencepiece0.1.99indirect
PyPIsniffio—indirect
PyPIsortedcontainers—indirect
PyPIspacy—indirect
PyPIsqlalchemy—indirect
PyPIstarlette1.6.0indirect
PyPItenacity—indirect
PyPItensorboard—indirect
PyPItensorboard-data-server—indirect
PyPItiktoken—indirect
PyPItimm—indirect
PyPItokenizers—indirect
PyPItokenizers0.13.3indirect
PyPItorch—indirect
PyPItorchvision—indirect
PyPItrafilatura2.0.0indirect
PyPItransformers—indirect
PyPItyper—indirect
PyPItyping-extensions—indirect
PyPItyping-extensions4.16.0indirect
PyPItyping-inspection0.4.4indirect
PyPIurllib32.7.0indirect
PyPIvllm—indirect
PyPIvolcengine-python-sdk—indirect
PyPIwandb—indirect
PyPIwikipedia—indirect
PyPIwin32-setctime1.2.0indirect
PyPIzhipuai—indirect
Dependency advisories 0

Installing pypi:lazyllm@1.3.0 pulls in 31 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 LazyAGI/LazyLLM. Read them side by side →

100run-llama/llama_indexLlamaIndex is the document processing platform for AIExceptional98langchain-ai/langgraphBuild resilient agents.Exceptional98langchain-ai/langchainThe agent engineering platform.Exceptional100Arize-ai/phoenixAI Observability & EvaluationExceptional100deepset-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.Exceptional96CopilotKit/CopilotKitThe Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI ProtocolExceptional

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.