Software health reportschema 0.31.0 · metrics 2.10.0 · 2026-08-08 19:21 UTC

langchain-ai / langchain-litellm

🦜🔗 LangChain interface to LiteLLM

PythonMIT★ 46 stars⑂ 33 forkssince Apr 2025View on GitHub ↗

langchain-ai/langchain-litellm holds a health index of 88 out of 100, placing it in the Excellent band. It scores highest on Vitality (90/100) and lowest on AI Readiness (67/100). It was last updated 4 days ago. A single contributor accounts for most of its recent work.

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.

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)

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 74 is calibrated to 88 on the published index scale (record calibration 2026-08-02).

Ownership

LangChainOrganization

21,533 followers255 public repossince Mar 2023

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

Package ecosystems

Registry	Package	Version	Downloads / mo	Versions	Last publish
PyPI	langchain-litellm	0.7.0	4,505,335	25	54 days ago

Metrics by category

Vitality

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

90Excellent · 21% of overall

Development activity

84Excellent

How it's scored

36/36	Push recency — last push 4 days ago
20.1/36	Commit cadence — 29/52 weeks with commits
18/18	Commit volume — 162 commits in the last year
10/10	OpenSSF Scorecard: Maintained — 30 commit(s) and 4 issue activity found in the last 90 days -- score normalized to 10

Inputs used

commits_last_year	162
human_commit_share	0.63
days_since_last_push	4
active_weeks_last_year	29

Release discipline

100Exceptional

How it's scored

27/27	Ships releases — 24 releases published
36/36	Release recency — latest release 54 days ago
27/27	Release cadence — a release every ~14 days
0/10	OpenSSF Scorecard: Signed-Releases — no data

Inputs used

releases_count	24
latest_release_tag	langchain-litellm==0.7.0
releases_from_tags	no
days_since_latest_release	54
mean_days_between_releases	14

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?

70Good · 17% of overall

Popularity & adoption

39Weak

How it's scored

26.8/60	Stars — 46 stars
12.5/25	Forks — 33 forks
0/15	Watchers — 2 watchers

Inputs used

forks	33
stars	46
watchers	2
growth_state	unverified
growth_factor_pct	100
growth_unverified_reason	no_history

Community health

85Excellent

How it's scored

22.5/22.5	README
22.5/22.5	License — recognized license (MIT)
18/18	CONTRIBUTING guide
13.5/13.5	Code of conduct
0/7.2	Issue template
0/6.3	PR template

Inputs used

has_readme	yes
has_license	yes
readme_badges	9
has_contributing	yes
has_issue_template	no
has_code_of_conduct	yes
readme_badge_services	shields.io
has_pull_request_template	no

Ecosystem adoption (downloads)

100Exceptional

How it's scored

80/80	Monthly downloads — 4,505,335 downloads/month across pypi
0/20	Registry dependents — not reported by this ecosystem

Inputs used

packages	langchain-litellm
dependents	—
ecosystems	pypi
total_downloads	—
monthly_downloads	4,505,335
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)

33At Risk

How it's scored

9/54	Bus factor — 1 contributor(s) cover half of all commits
4.9/22.5	Commit distribution — top contributor authored 78% of commits
13.5/13.5	Contributor breadth — 16 contributors
6/10	OpenSSF Scorecard: Contributors — project has 2 contributing companies or organizations -- score normalized to 6

Inputs used

bus_factor	1
contributors_sampled	16
top_contributor_share	0.783

Issue & PR responsiveness

60Moderate

How it's scored

33.3/42	Issue resolution — 79% of issues closed
26.3/30	PR acceptance — 151/172 decided PRs merged
0/13	Newcomer PR acceptance — 0/4 first-time contributors' PRs merged in 30d
0/15	OpenSSF Scorecard: Code-Review — Found 0/11 approved changesets -- score normalized to 0

Inputs used

merged_prs	151
open_issues	11
closed_issues	42
prs_merged_7d	0
prs_decided_7d	3
prs_merged_30d	0
prs_decided_30d	4
issue_closed_ratio	0.792
closed_unmerged_prs	21
first_time_authors_30d	3
first_time_prs_merged_30d	0
first_time_prs_decided_30d	4

Ownership & stewardship

94Exceptional

How it's scored

30/30	Ownership backing — organization-owned
0/20	Verified domain — verified-domain status not read for this organization
25/25	Owner reach — 21,533 followers of langchain-ai
19.9/25	Track record — 255 public repos, account ~3 yr old

Inputs used

followers	21,533
owner_type	Organization
is_verified	—
owner_login	langchain-ai
public_repos	255
account_age_days	1,255

Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.

Package maintenance

100Exceptional

How it's scored

25/25	Published & resolvable — 1 package(s) on pypi
35/35	Publish recency — latest publish 54 days ago
20/20	Version history — 25 published versions
20/20	Not deprecated — active, not deprecated or yanked

Inputs used

packages	langchain-litellm
ecosystems	pypi
any_deprecated	no
min_days_since_publish	54

Engineering Quality

Are baseline engineering and documentation practices in place?

67Good · 19% of overall

Engineering practices

68Good

How it's scored

24/24	CI workflows — 10 workflow(s)
24/24	Tests present
0/16	Linter config
0/9.6	Pre-commit hooks
0/6.4	.editorconfig
20/20	OpenSSF Scorecard: CI-Tests — 29 out of 29 merged PRs checked by a CI test -- score normalized to 10

Inputs used

has_ci	yes
has_tests	yes
has_editorconfig	no
has_linter_config	no
has_precommit_config	no

Documentation

65Good

How it's scored

30/30	README
0/25	Documentation directory
15/15	Documentation / homepage site — https://docs.langchain.com/oss/python/integrations/providers/litellm
10/10	Repository description
10/10	Topics — 2 topics
0/10	Wiki

Inputs used

topics	langchain, litellm
has_wiki	no
homepage	https://docs.langchain.com/oss/python/integrations/providers/litellm
docs_site	https://docs.langchain.com/oss/python/integrations/providers/litellm
has_readme	yes
has_docs_dir	no
has_description	yes

Security

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

75Good · 16% of overall

Security posture

75Good

How it's scored

7.5/7.5	Binary-Artifacts — no binaries found in the repo
2.2/7.5	Branch-Protection — branch protection is not maximal on development and all release branches
2.5/2.5	CI-Tests — 29 out of 29 merged PRs checked by a CI test -- score normalized to 10
0/2.5	CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
0/7.5	Code-Review — Found 0/11 approved changesets -- score normalized to 0
1.5/2.5	Contributors — project has 2 contributing companies or organizations -- score normalized to 6
10/10	Dangerous-Workflow — no dangerous workflow patterns detected
7.5/7.5	Dependency-Update-Tool — update tool detected
0/5	Fuzzing — project is not fuzzed
2.5/2.5	License — license file detected
7.5/7.5	Maintained — 30 commit(s) and 4 issue activity found in the last 90 days -- score normalized to 10
0/5	Packaging — no data
5/5	Pinned-Dependencies — all dependencies are pinned
5/5	SAST — SAST tool is run on all commits
4.5/5	Security-Policy — security policy file detected
0/7.5	Signed-Releases — no data
7.5/7.5	Token-Permissions — GitHub workflow tokens follow principle of least privilege
6/7.5	Vulnerabilities — 2 existing vulnerabilities detected

Inputs used

source	openssf_scorecard
checks_evaluated	16
scorecard_version	v5.5.0
checks_inconclusive	2
scorecard_aggregate	7.5

Excluded from scoring (no data or not applicable): Packaging, Signed-Releases. Remaining weights renormalized.

Dependency advisories

77Good

How it's scored

12/35	Direct dependencies free of known advisories — 1 affected: cryptography 48.0.1 (high 8.2)
25/25	Indirect dependencies free of known advisories — no indirect dependency carries a known advisory
40/40	No advisories left outstanding — no advisory has been public longer than 90 days

Inputs used

source	osv
advisories	6
affected_packages	1
assessed_packages	63
unassessed_packages	0
affected_by_severity	high 1
direct_affected_packages	1

Matched the pypi:langchain-litellm@0.7.0 runtime dependency closure — what installing the published package pulls in — 63 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.

67Good · 4% of overall

Agent context & guidance

40Weak

How it's scored

0/45	Agent instructions — no CLAUDE.md / AGENTS.md / editor rules
0/15	Machine-readable docs (llms.txt)
40/40	Legible commit history — 56 of 63 human commits state their intent (structured subject or explanatory body)

Inputs used

has_llms_txt	no
llms_txt_url	—
legible_history_share	0.889
agent_instruction_files	—
agent_instruction_max_bytes	—

Verify loop (build / test / typecheck)

81Excellent

How it's scored

18/18	One-command bootstrap — Makefile
22/22	Automated tests
0/11	Lint / format config
11/11	Static type checking — langchain_litellm/py.typed
10/10	Reproducible environment — lockfile
2/10	Demonstrated agent practice — 1 of the last 100 commits agent-authored or agent-credited
8/8	Automated maintenance — 33 of the last 100 commits are automated dependency updates
10/10	OpenSSF Scorecard: Pinned-Dependencies — all dependencies are pinned

Inputs used

has_nix	no
has_tests	yes
lockfiles	uv.lock
has_dockerfile	no
typed_language	no
bootstrap_files	Makefile
has_devcontainer	no
has_linter_config	no
typecheck_configs	langchain_litellm/py.typed
agent_commit_share	0.01
toolchain_manifests	—
dependency_bot_commit_share	0.33

Code legibility for models

82Excellent

How it's scored

27/45	Type-checkable code — Python with type-check config (langchain_litellm/py.typed)
55/55	Manageable file sizes — 0/27 source files over 60KB

Inputs used

primary_language	Python
largest_source_bytes	45,424
source_files_sampled	27
oversized_source_files	0

Key facts

46GitHub stars

16contributors

162commits, last 12 months

4days since last push

24releases

1bus factor

11open 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 ★ / 33 ⇿

0Stars

33Forks

21Releases

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.

Major 0Minor 5Patch 12

Each point covers 2 days.

OpenSSF Scorecard 7.5 / 10

7.5aggregate

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 · 2026-08-08 19:20 UTC

10	Binary-Artifacts	no binaries found in the repo
3	Branch-Protection	branch protection is not maximal on development and all release branches
10	CI-Tests	29 out of 29 merged PRs checked by a CI test -- score normalized to 10
0	CII-Best-Practices	no effort to earn an OpenSSF best practices badge detected
0	Code-Review	Found 0/11 approved changesets -- score normalized to 0
6	Contributors	project has 2 contributing companies or organizations -- score normalized to 6
10	Dangerous-Workflow	no dangerous workflow patterns detected
10	Dependency-Update-Tool	update tool detected
0	Fuzzing	project is not fuzzed
10	License	license file detected
10	Maintained	30 commit(s) and 4 issue activity found in the last 90 days -- score normalized to 10
n/a	Packaging	packaging workflow not detected
10	Pinned-Dependencies	all dependencies are pinned
10	SAST	SAST tool is run on all commits
9	Security-Policy	security policy file detected
n/a	Signed-Releases	no releases found
10	Token-Permissions	GitHub workflow tokens follow principle of least privilege
8	Vulnerabilities	2 existing vulnerabilities detected

Direct dependencies 4

Registry	Package	Version constraint	Manifest
PyPI	langchain-core	`>=1.4.7,<2.0.0`	pyproject.toml
PyPI	litellm	`>=1.83.14,<2.0.0,!=1.82.7,!=1.82.8`	pyproject.toml
PyPI	httpx	`>=0.28.1,<0.29.0`	pyproject.toml
PyPI	cryptography	`>=46.0.5,<51.0.0`	pyproject.toml

All dependencies 169

Full resolved dependency set from the GitHub dependency graph: 4 direct and 165 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

Registry	Package	Version	Relation
PyPI	cryptography	`50.0.0`	direct
PyPI	httpx	`0.28.1`	direct
PyPI	langchain-core	`1.4.7`	direct
PyPI	litellm	`1.93.0`	direct
PyPI	aiohappyeyeballs	`2.6.1`	indirect
PyPI	aiohttp	`3.14.3`	indirect
PyPI	aiosignal	`1.4.0`	indirect
PyPI	annotated-doc	`0.0.4`	indirect
PyPI	annotated-types	`0.7.0`	indirect
PyPI	anyio	`4.12.1`	indirect
PyPI	appnope	`0.1.4`	indirect
PyPI	ast-serialize	`0.6.0`	indirect
PyPI	asttokens	`3.0.1`	indirect
PyPI	async-timeout	`5.0.1`	indirect
PyPI	attrs	`25.4.0`	indirect
PyPI	backports-asyncio-runner	`1.2.0`	indirect
PyPI	blockbuster	`1.5.26`	indirect
PyPI	certifi	`2026.1.4`	indirect
PyPI	cffi	`2.1.0`	indirect
PyPI	charset-normalizer	`3.4.4`	indirect
PyPI	click	`8.1.8`	indirect
PyPI	codespell	`2.4.3`	indirect
PyPI	colorama	`0.4.6`	indirect
PyPI	comm	`0.2.3`	indirect
PyPI	coverage	`7.13.4`	indirect
PyPI	debugpy	`1.8.20`	indirect
PyPI	decorator	`5.2.1`	indirect
PyPI	distro	`1.9.0`	indirect
PyPI	duckdb	`1.4.4`	indirect
PyPI	duckdb-engine	`0.17.0`	indirect
PyPI	exceptiongroup	`1.3.1`	indirect
PyPI	execnet	`2.1.2`	indirect
PyPI	executing	`2.2.1`	indirect
PyPI	fastuuid	`0.14.0`	indirect
PyPI	filelock	`3.24.3`	indirect
PyPI	forbiddenfruit	`0.1.4`	indirect
PyPI	freezegun	`1.5.5`	indirect
PyPI	frozenlist	`1.8.0`	indirect
PyPI	fsspec	`2026.2.0`	indirect
PyPI	greenlet	`3.3.1`	indirect
PyPI	h11	`0.16.0`	indirect
PyPI	hf-xet	`1.2.0`	indirect
PyPI	httpcore	`1.0.9`	indirect
PyPI	huggingface-hub	`1.4.1`	indirect
PyPI	idna	`3.15`	indirect
PyPI	importlib-metadata	`8.5.0`	indirect
PyPI	iniconfig	`2.3.0`	indirect
PyPI	ipykernel	`7.3.0`	indirect
PyPI	ipython	`8.38.0`	indirect
PyPI	ipython	`9.10.0`	indirect
PyPI	ipython-pygments-lexers	`1.1.1`	indirect
PyPI	jedi	`0.19.2`	indirect
PyPI	jinja2	`3.1.6`	indirect
PyPI	jiter	`0.13.0`	indirect
PyPI	jsonpatch	`1.33`	indirect
PyPI	jsonpointer	`3.0.0`	indirect
PyPI	jsonschema	`4.23.0`	indirect
PyPI	jsonschema-specifications	`2025.9.1`	indirect
PyPI	jupyter-client	`8.9.1`	indirect
PyPI	jupyter-core	`5.9.1`	indirect
PyPI	langchain	`1.3.10`	indirect
PyPI	langchain-litellm	`0.7.0`	indirect
PyPI	langchain-protocol	`0.0.15`	indirect
PyPI	langchain-tests	`1.1.7`	indirect
PyPI	langchain-text-splitters	`1.1.2`	indirect
PyPI	langgraph	`1.2.6`	indirect
PyPI	langgraph-checkpoint	`4.1.1`	indirect
PyPI	langgraph-prebuilt	`1.1.0`	indirect
PyPI	langgraph-sdk	`0.4.2`	indirect
PyPI	langsmith	`0.8.18`	indirect
PyPI	lark	`1.3.1`	indirect
PyPI	librt	`0.13.0`	indirect
PyPI	markdown-it-py	`4.0.0`	indirect
PyPI	markupsafe	`3.0.3`	indirect
PyPI	matplotlib-inline	`0.2.1`	indirect
PyPI	mdurl	`0.1.2`	indirect
PyPI	multidict	`6.7.1`	indirect
PyPI	mypy	`2.3.0`	indirect
PyPI	mypy-extensions	`1.1.0`	indirect
PyPI	mypy-protobuf	`5.1.0`	indirect
PyPI	nest-asyncio2	`1.7.2`	indirect
PyPI	numpy	`2.2.6`	indirect
PyPI	numpy	`2.4.2`	indirect
PyPI	openai	`2.24.0`	indirect
PyPI	orjson	`3.11.7`	indirect
PyPI	ormsgpack	`1.12.2`	indirect
PyPI	packaging	`26.0`	indirect
PyPI	pandas	`2.3.3`	indirect
PyPI	parso	`0.8.6`	indirect
PyPI	pathspec	`1.0.4`	indirect
PyPI	pexpect	`4.9.0`	indirect
PyPI	platformdirs	`4.9.2`	indirect
PyPI	pluggy	`1.6.0`	indirect
PyPI	prompt-toolkit	`3.0.52`	indirect
PyPI	propcache	`0.4.1`	indirect
PyPI	protobuf	`6.33.5`	indirect
PyPI	psutil	`7.2.2`	indirect
PyPI	ptyprocess	`0.7.0`	indirect
PyPI	pure-eval	`0.2.3`	indirect
PyPI	py-cpuinfo	`9.0.0`	indirect
PyPI	pycparser	`3.0`	indirect
PyPI	pydantic	`2.12.5`	indirect
PyPI	pydantic-core	`2.41.5`	indirect
PyPI	pygments	`2.19.2`	indirect
PyPI	pytest	`9.1.1`	indirect
PyPI	pytest-asyncio	`1.4.0`	indirect
PyPI	pytest-benchmark	`5.0.1`	indirect
PyPI	pytest-codspeed	`4.3.0`	indirect
PyPI	pytest-cov	`7.1.0`	indirect
PyPI	pytest-dotenv	`0.5.2`	indirect
PyPI	pytest-mock	`3.15.1`	indirect
PyPI	pytest-recording	`0.13.4`	indirect
PyPI	pytest-socket	`0.8.0`	indirect
PyPI	pytest-watcher	`0.6.3`	indirect
PyPI	pytest-xdist	`3.8.0`	indirect
PyPI	python-dateutil	`2.9.0.post0`	indirect
PyPI	python-dotenv	`1.2.2`	indirect
PyPI	pytz	`2025.2`	indirect
PyPI	pyyaml	`6.0.3`	indirect
PyPI	pyzmq	`27.1.0`	indirect
PyPI	referencing	`0.37.0`	indirect
PyPI	regex	`2026.2.19`	indirect
PyPI	requests	`2.33.0`	indirect
PyPI	requests-mock	`1.12.1`	indirect
PyPI	requests-toolbelt	`1.0.0`	indirect
PyPI	responses	`0.26.2`	indirect
PyPI	rich	`14.3.3`	indirect
PyPI	rpds-py	`0.30.0`	indirect
PyPI	ruff	`0.16.0`	indirect
PyPI	shellingham	`1.5.4`	indirect
PyPI	six	`1.17.0`	indirect
PyPI	sniffio	`1.3.1`	indirect
PyPI	sqlalchemy	`2.0.46`	indirect
PyPI	stack-data	`0.6.3`	indirect
PyPI	syrupy	`5.5.3`	indirect
PyPI	tenacity	`9.1.4`	indirect
PyPI	tiktoken	`0.12.0`	indirect
PyPI	tokenizers	`0.22.2`	indirect
PyPI	toml	`0.10.2`	indirect
PyPI	tomli	`2.4.0`	indirect
PyPI	tornado	`6.5.7`	indirect
PyPI	tqdm	`4.67.3`	indirect
PyPI	traitlets	`5.14.3`	indirect
PyPI	typer	`0.23.1`	indirect
PyPI	typer-slim	`0.23.1`	indirect
PyPI	types-cffi	`1.17.0.20250915`	indirect
PyPI	types-chardet	`5.0.4.6`	indirect
PyPI	types-protobuf	`6.32.1.20251210`	indirect
PyPI	types-pyopenssl	`24.1.0.20240722`	indirect
PyPI	types-pytz	`2026.3.1.20260727`	indirect
PyPI	types-pyyaml	`6.0.12.20260724`	indirect
PyPI	types-redis	`4.6.0.20241004`	indirect
PyPI	types-requests	`2.33.0.20260712`	indirect
PyPI	types-setuptools	`82.0.0.20260210`	indirect
PyPI	types-toml	`0.10.8.20260518`	indirect
PyPI	typing-extensions	`4.15.0`	indirect
PyPI	typing-inspection	`0.4.2`	indirect
PyPI	tzdata	`2025.3`	indirect
PyPI	urllib3	`2.7.0`	indirect
PyPI	uuid-utils	`0.14.0`	indirect
PyPI	vcrpy	`8.2.1`	indirect
PyPI	watchdog	`6.0.0`	indirect
PyPI	wcwidth	`0.6.0`	indirect
PyPI	websockets	`15.0.1`	indirect
PyPI	wrapt	`2.1.1`	indirect
PyPI	xxhash	`3.6.0`	indirect
PyPI	yarl	`1.22.0`	indirect
PyPI	zipp	`3.23.0`	indirect
PyPI	zstandard	`0.25.0`	indirect

Dependency advisories 1

Installing pypi:langchain-litellm@0.7.0 pulls in 63 packages, direct and transitive: 1 carry known advisories, of which 1 are direct dependencies.

Package	Version	Relation	Severity	Advisories	Fixed in
cryptography	`48.0.1`	direct	high	6	`50.0.0`

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.

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 v0.31.0 — full methodology · metrics wiki.

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

Software health index

Score profile

Ownership

Package ecosystems

Metrics by category

Key facts

Data collection warnings

More detail

Feedback

Related records