Software health reportschema 0.34.0 · metrics 2.10.0 · 2026-09-15 05:58 UTC

kyegomez / swarms

The Enterprise-Grade Multi-Agent Orchestration Framework. Website: https://swarms.ai

PythonApache-2.0★ 7,172 stars⑂ 1,022 forkssince May 2023View on GitHub ↗

KindCommand-line toolLibraryMCP serverhow this is determined

#artificial-intelligence #langchain #machine-learning #swarms #agents #prompt-engineering #prompt-toolkit #prompting #tree-of-thoughts #ai #chatgpt #gpt4all #huggingface #langchain-python #agentic-workflow #multi-agent-systems #agentic-ai #claude-code

kyegomez/swarms holds a health index of 90 out of 100, placing it in the Excellent band. It scores highest on Community & Adoption (87/100) and lowest on Security (62/100). It was last updated today. 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 76 is calibrated to 90 on the published index scale (record calibration 2026-08-02).

Ownership

Kye GomezPersonal account

3,520 followers448 public repossince Jan 2022Swarms

This repository is owned by a personal account. A single-owner project carries more continuity risk than an organization-backed one.

Package ecosystems

Registry	Package	Version	Downloads / mo	Versions	Last publish	Tags
PyPI	swarms	15.0.2	14,373	622	6 days ago	artificial-intelligence deep-learning optimizers prompt-engineering swarms agents llms transformers multi-agent swarms-of-agents enterprise-grade-agents production-grade-agents multi-grade-agents generative-agents generative-ai agent-marketplace agent-store quant finance algorithmic-trading portfolio-optimization risk-management financial-modeling machine-learning-for-finance natural-language-processing-for-finance

Metrics by category

Vitality

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

84Excellent · 21% of overall

Development activity

100Exceptional

How it's scored

36/36	Push recency — last push 0 days ago
36/36	Commit cadence — 52/52 weeks with commits
18/18	Commit volume — 1,009 commits in the last year
10/10	OpenSSF Scorecard: Maintained — 30 commit(s) and 22 issue activity found in the last 90 days -- score normalized to 10

Inputs used

commits_last_year	1,009
human_commit_share	0.99
days_since_last_push	0
active_weeks_last_year	52

Release discipline

60Moderate

How it's scored

27/27	Ships releases — 100 releases published
7.2/36	Release recency — latest release 626 days ago
19.8/27	Release cadence — a release every ~46.2 days
0/10	OpenSSF Scorecard: Signed-Releases — no data

Inputs used

releases_count	100
latest_release_tag	6.8.1
releases_from_tags	no
days_since_latest_release	626
mean_days_between_releases	46.2

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?

87Excellent · 17% of overall

Popularity & adoption

95Exceptional

How it's scored

60/60	Stars — 7,172 stars
25/25	Forks — 1,022 forks
10.1/15	Watchers — 67 watchers

Inputs used

forks	1,022
stars	7,172
watchers	67
growth_state	unverified
growth_factor_pct	100
growth_unverified_reason	no_history

Community health

92Excellent

How it's scored

22.5/22.5	README
22.5/22.5	License — recognized license (Apache-2.0)
18/18	CONTRIBUTING guide
13.5/13.5	Code of conduct
0/7.2	Issue template
6.3/6.3	PR template

Inputs used

has_readme	yes
has_license	yes
readme_badges	4
has_contributing	yes
has_issue_template	no
has_code_of_conduct	yes
readme_badge_services	shields.io
has_pull_request_template	yes

Ecosystem adoption (downloads)

69Good

How it's scored

55.4/80	Monthly downloads — 14,373 downloads/month across pypi
0/20	Registry dependents — not reported by this ecosystem

Inputs used

packages	swarms
dependents	—
ecosystems	pypi
total_downloads	—
monthly_downloads	14,373
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)

43Weak

How it's scored

9/54	Bus factor — 1 contributor(s) cover half of all commits
10.5/22.5	Commit distribution — top contributor authored 53% of commits
13.5/13.5	Contributor breadth — 52 contributors
10/10	OpenSSF Scorecard: Contributors — project has 9 contributing companies or organizations

Inputs used

bus_factor	1
contributors_sampled	52
top_contributor_share	0.533

Issue & PR responsiveness

62Moderate

How it's scored

37.1/42	Issue resolution — 88% of issues closed
15.5/30	PR acceptance — 698/1,348 decided PRs merged
3.7/13	Newcomer PR acceptance — 2/7 first-time contributors' PRs merged in 30d
6/15	OpenSSF Scorecard: Code-Review — Found 14/30 approved changesets -- score normalized to 4

Inputs used

merged_prs	698
open_issues	90
closed_issues	688
prs_merged_7d	29
prs_decided_7d	35
prs_merged_30d	47
prs_decided_30d	58
issue_closed_ratio	0.884
closed_unmerged_prs	650
first_time_authors_30d	5
first_time_prs_merged_30d	2
first_time_prs_decided_30d	7

Ownership & stewardship

72Good

How it's scored

10/30	Ownership backing — personal (user) account
0/20	Verified domain — not applicable to user accounts
25/25	Owner reach — 3,520 followers of kyegomez
22.2/25	Track record — 448 public repos, account ~4 yr old

Inputs used

followers	3,520
owner_type	User
is_verified	—
owner_login	kyegomez
public_repos	448
account_age_days	1,687

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 6 days ago
20/20	Version history — 622 published versions
20/20	Not deprecated — active, not deprecated or yanked

Inputs used

packages	swarms
ecosystems	pypi
any_deprecated	no
min_days_since_publish	6

Engineering Quality

Are baseline engineering and documentation practices in place?

80Excellent · 19% of overall

Engineering practices

84Excellent

How it's scored

24/24	CI workflows — 10 workflow(s)
24/24	Tests present
16/16	Linter config — pyproject.toml ([tool.ruff], [tool.black])
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	yes
has_precommit_config	no

Documentation

75Good

How it's scored

30/30	README
0/25	Documentation directory
15/15	Documentation / homepage site — https://docs.swarms.world
10/10	Repository description
10/10	Topics — 18 topics
10/10	Wiki

Inputs used

topics	artificial-intelligence, langchain, machine-learning, swarms, agents, prompt-engineering, prompt-toolkit, prompting, tree-of-thoughts, ai, chatgpt, gpt4all, huggingface, langchain-python, agentic-workflow, multi-agent-systems, agentic-ai, claude-code
has_wiki	yes
homepage	https://docs.swarms.world
docs_site	https://docs.swarms.world
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?

62Moderate · 16% of overall

Security posture

61Moderate

How it's scored

7.5/7.5	Binary-Artifacts — no binaries found in the repo
4.5/7.5	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
3/7.5	Code-Review — Found 14/30 approved changesets -- score normalized to 4
2.5/2.5	Contributors — project has 9 contributing companies or organizations
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 22 issue activity found in the last 90 days -- score normalized to 10
0/5	Packaging — no data
0/5	Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0
4/5	SAST — SAST tool is not run on all commits -- score normalized to 8
5/5	Security-Policy — security policy file detected
0/7.5	Signed-Releases — no data
0/7.5	Token-Permissions — detected GitHub workflow tokens with excessive permissions
0/7.5	Vulnerabilities — 21 existing vulnerabilities detected

Inputs used

source	openssf_scorecard
checks_evaluated	16
scorecard_version	v5.5.0
checks_inconclusive	2
scorecard_aggregate	6.1

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

Dependency advisories

65Good

How it's scored

7.6/35	Direct dependencies free of known advisories — 1 affected: litellm 1.76.1 (critical 9.8)
25/25	Indirect dependencies free of known advisories — no indirect dependency carries a known advisory
32.1/40	No advisories left outstanding — 1 advisory-carrying package(s) unaddressed past 90 days; oldest published 164 days ago

Inputs used

source	osv
advisories	31
affected_packages	1
assessed_packages	80
unassessed_packages	0
affected_by_severity	critical 1
direct_affected_packages	1

Matched the pypi:swarms@15.0.2 runtime dependency closure — what installing the published package pulls in — 80 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.

77Good · 4% of overall

Agent context & guidance

100Exceptional

How it's scored

45/45	Agent instructions — CLAUDE.md
15/15	Machine-readable docs (llms.txt) — llms.txt served by the project website (https://docs.swarms.world/llms.txt)
40/40	Legible commit history — 96 of 99 human commits state their intent (structured subject or explanatory body)

Inputs used

has_llms_txt	yes
llms_txt_url	https://docs.swarms.world/llms.txt
legible_history_share	0.97
agent_instruction_files	CLAUDE.md
agent_instruction_max_bytes	35,219

Verify loop (build / test / typecheck)

59Moderate

How it's scored

0/18	One-command bootstrap
22/22	Automated tests
11/11	Lint / format config — pyproject.toml ([tool.ruff], [tool.black])
0/11	Static type checking
10/10	Reproducible environment — Dockerfile
8/10	Demonstrated agent practice — 4 of the last 100 commits agent-authored or agent-credited
8/8	Automated maintenance — 1 of the last 100 commits are automated dependency updates
0/10	OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0

Inputs used

has_nix	no
has_tests	yes
lockfiles	—
has_dockerfile	yes
typed_language	no
bootstrap_files	—
has_devcontainer	no
has_linter_config	yes
typecheck_configs	—
agent_commit_share	0.04
toolchain_manifests	—
dependency_bot_commit_share	0.01

Code legibility for models

54Moderate

How it's scored

0/45	Type-checkable code — Python without a type-check config
54.4/55	Manageable file sizes — 11/988 source files over 60KB

Inputs used

primary_language	Python
largest_source_bytes	176,186
source_files_sampled	988
oversized_source_files	11

Machine-readable interfaces

100Exceptional

How it's scored

0/40	API schema (OpenAPI/GraphQL/proto) — not applicable to this kind of software
20/20	MCP server
40/40	Runnable examples — demos, examples

Inputs used

example_dirs	demos, examples
has_mcp_signal	yes
api_schema_files	—
interfaces_expected_of	—

Excluded from scoring (no data or not applicable): API schema (OpenAPI/GraphQL/proto). Remaining weights renormalized.

Key facts

7,172GitHub stars

52contributors

1,009commits, last 12 months

0days since last push

100releases

1bus factor

90open 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 ★ / 1,022 ⇿

0Stars

1,022Forks

11Releases

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.

Only the most recent history is shown — this repository exceeds the collection window, so the earliest history is not captured.

Major 0Minor 1Patch 10

Each point covers 3 days.

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 · 2026-09-15 05:58 UTC

10	Binary-Artifacts	no binaries found in the repo
6	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
4	Code-Review	Found 14/30 approved changesets -- score normalized to 4
10	Contributors	project has 9 contributing companies or organizations
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 22 issue activity found in the last 90 days -- score normalized to 10
n/a	Packaging	packaging workflow not detected
0	Pinned-Dependencies	dependency not pinned by hash detected -- score normalized to 0
8	SAST	SAST tool is not run on all commits -- score normalized to 8
10	Security-Policy	security policy file detected
n/a	Signed-Releases	no releases found
0	Token-Permissions	detected GitHub workflow tokens with excessive permissions
0	Vulnerabilities	21 existing vulnerabilities detected

Direct dependencies 18

Registry	Package	Version constraint	Manifest
PyPI	setuptools	`*`	pyproject.toml
PyPI	asyncio	`>=3.4.3,<5.0`	pyproject.toml
PyPI	toml	`*`	pyproject.toml
PyPI	loguru	`*`	pyproject.toml
PyPI	pydantic	`*`	pyproject.toml
PyPI	tenacity	`*`	pyproject.toml
PyPI	psutil	`*`	pyproject.toml
PyPI	python-dotenv	`*`	pyproject.toml
PyPI	PyYAML	`*`	pyproject.toml
PyPI	networkx	`*`	pyproject.toml
PyPI	rich	`*`	pyproject.toml
PyPI	litellm	`1.76.1`	pyproject.toml
PyPI	httpx	`*`	pyproject.toml
PyPI	requests	`*`	pyproject.toml
PyPI	mcp	`*`	pyproject.toml
PyPI	schedule	`*`	pyproject.toml
PyPI	opentelemetry-sdk	`*`	pyproject.toml
PyPI	opentelemetry-exporter-otlp-proto-http	`*`	pyproject.toml

All dependencies 135

Full resolved dependency set from the GitHub dependency graph: 35 direct and 100 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

Registry	Package	Version	Relation
PyPI	asyncio	`—`	direct
PyPI	asyncio	`4.0.0`	direct
PyPI	httpx	`—`	direct
PyPI	httpx	`0.28.1`	direct
PyPI	litellm	`1.76.1`	direct
PyPI	loguru	`—`	direct
PyPI	loguru	`0.7.3`	direct
PyPI	mcp	`—`	direct
PyPI	mcp	`2.2.0`	direct
PyPI	networkx	`—`	direct
PyPI	networkx	`3.4.2`	direct
PyPI	opentelemetry-exporter-otlp-proto-http	`—`	direct
PyPI	opentelemetry-exporter-otlp-proto-http	`1.44.0`	direct
PyPI	opentelemetry-sdk	`—`	direct
PyPI	opentelemetry-sdk	`1.44.0`	direct
PyPI	psutil	`—`	direct
PyPI	psutil	`7.2.2`	direct
PyPI	pydantic	`—`	direct
PyPI	pydantic	`2.12.5`	direct
PyPI	pydantic	`2.13.5`	direct
PyPI	python-dotenv	`—`	direct
PyPI	python-dotenv	`1.2.3`	direct
PyPI	pyyaml	`—`	direct
PyPI	pyyaml	`6.0.3`	direct
PyPI	requests	`—`	direct
PyPI	requests	`2.34.2`	direct
PyPI	rich	`—`	direct
PyPI	rich	`15.0.0`	direct
PyPI	schedule	`—`	direct
PyPI	schedule	`1.2.2`	direct
PyPI	setuptools	`84.0.0`	direct
PyPI	tenacity	`—`	direct
PyPI	tenacity	`9.1.4`	direct
PyPI	toml	`—`	direct
PyPI	toml	`0.10.2`	direct
PyPI	aiohappyeyeballs	`2.7.1`	indirect
PyPI	aiohttp	`3.14.3`	indirect
PyPI	aiosignal	`1.4.0`	indirect
PyPI	annotated-types	`0.8.0`	indirect
PyPI	anyio	`4.15.1`	indirect
PyPI	async-timeout	`5.0.1`	indirect
PyPI	attrs	`26.1.0`	indirect
PyPI	black	`26.5.1`	indirect
PyPI	certifi	`2026.7.22`	indirect
PyPI	cffi	`2.1.1`	indirect
PyPI	charset-normalizer	`3.5.1`	indirect
PyPI	click	`8.5.0`	indirect
PyPI	colorama	`0.4.6`	indirect
PyPI	cryptography	`50.0.1`	indirect
PyPI	exceptiongroup	`1.3.1`	indirect
PyPI	fastapi	`—`	indirect
PyPI	fastuuid	`0.14.0`	indirect
PyPI	filelock	`3.32.5`	indirect
PyPI	frozenlist	`1.8.0`	indirect
PyPI	fsspec	`2026.7.0`	indirect
PyPI	googleapis-common-protos	`1.75.3`	indirect
PyPI	gunicorn	`—`	indirect
PyPI	h11	`0.16.0`	indirect
PyPI	hf-xet	`1.6.0`	indirect
PyPI	httpcore	`1.0.9`	indirect
PyPI	httpcore2	`2.12.0`	indirect
PyPI	httpx2	`2.12.0`	indirect
PyPI	httpx2-jsfetch	`1.0`	indirect
PyPI	huggingface-hub	`1.30.0`	indirect
PyPI	idna	`3.19`	indirect
PyPI	importlib-metadata	`9.0.1`	indirect
PyPI	iniconfig	`2.3.0`	indirect
PyPI	jinja2	`3.1.6`	indirect
PyPI	jiter	`0.16.0`	indirect
PyPI	jsonschema	`4.26.0`	indirect
PyPI	jsonschema-specifications	`2025.9.1`	indirect
PyPI	markdown-it-py	`4.2.0`	indirect
PyPI	markupsafe	`3.0.3`	indirect
PyPI	matplotlib	`—`	indirect
PyPI	mcp-types	`2.2.0`	indirect
PyPI	mdurl	`0.1.2`	indirect
PyPI	multidict	`6.7.1`	indirect
PyPI	mypy-extensions	`1.1.0`	indirect
PyPI	mypy-protobuf	`5.1.0`	indirect
PyPI	numpy	`—`	indirect
PyPI	openai	`3.8.0`	indirect
PyPI	openpyxl	`—`	indirect
PyPI	opentelemetry-api	`1.44.0`	indirect
PyPI	opentelemetry-exporter-otlp-proto-common	`1.44.0`	indirect
PyPI	opentelemetry-proto	`1.44.0`	indirect
PyPI	opentelemetry-semantic-conventions	`0.65b0`	indirect
PyPI	packaging	`26.3`	indirect
PyPI	pandas	`—`	indirect
PyPI	passlib	`—`	indirect
PyPI	pathspec	`1.1.1`	indirect
PyPI	platformdirs	`4.11.7`	indirect
PyPI	pluggy	`1.6.0`	indirect
PyPI	propcache	`0.5.2`	indirect
PyPI	protobuf	`7.36.1`	indirect
PyPI	pycparser	`3.0`	indirect
PyPI	pydantic-core	`2.46.5`	indirect
PyPI	pygments	`2.21.0`	indirect
PyPI	pyjwt	`2.13.0`	indirect
PyPI	pytest	`—`	indirect
PyPI	pytest	`9.1.1`	indirect
PyPI	pytest-asyncio	`—`	indirect
PyPI	python-jose	`—`	indirect
PyPI	python-multipart	`—`	indirect
PyPI	python-multipart	`0.0.32`	indirect
PyPI	pytokens	`0.4.1`	indirect
PyPI	pywin32	`312`	indirect
PyPI	referencing	`0.37.0`	indirect
PyPI	regex	`2026.9.3`	indirect
PyPI	rpds-py	`0.30.0`	indirect
PyPI	ruff	`0.16.1`	indirect
PyPI	seaborn	`—`	indirect
PyPI	slowapi	`—`	indirect
PyPI	sniffio	`1.3.1`	indirect
PyPI	sse-starlette	`3.4.11`	indirect
PyPI	stagehand	`—`	indirect
PyPI	starlette	`1.6.0`	indirect
PyPI	swarms	`—`	indirect
PyPI	swarms-memory	`—`	indirect
PyPI	tiktoken	`0.14.0`	indirect
PyPI	tokenizers	`0.23.2`	indirect
PyPI	tomli	`2.4.1`	indirect
PyPI	tqdm	`4.70.0`	indirect
PyPI	truststore	`0.10.4`	indirect
PyPI	types-chardet	`5.0.4.6`	indirect
PyPI	types-protobuf	`7.35.1.20260906`	indirect
PyPI	types-pytz	`2026.3.1.20260727`	indirect
PyPI	types-toml	`0.10.8.20260518`	indirect
PyPI	typing-extensions	`4.16.0`	indirect
PyPI	typing-inspection	`0.4.4`	indirect
PyPI	urllib3	`2.7.0`	indirect
PyPI	uvicorn	`—`	indirect
PyPI	uvicorn	`0.52.4`	indirect
PyPI	win32-setctime	`1.2.0`	indirect
PyPI	yarl	`1.24.5`	indirect
PyPI	zipp	`4.1.0`	indirect

Dependency advisories 1

Installing pypi:swarms@15.0.2 pulls in 80 packages, direct and transitive: 1 carry known advisories, of which 1 are direct dependencies.

Package	Version	Relation	Severity	Advisories	Fixed in
litellm	`1.76.1`	direct	critical	31	`1.84.0`

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 v0.34.0 — 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