Public record
Software health reportschema 0.34.0 · metrics 2.10.0 · 2026-10-17 08:11 UTC

ryanduguid / australian-accounting

Local engines for ATO small-business benchmarks, Payday Super 2026 and Division 7A loan review, available through the aus-accounting-mcp server. Synthetic fixtures only.

PythonApache-2.0★ 2 stars⑂ 0 forkssince Aug 2026View on GitHub ↗
KindMCP serverCommand-line toolLibraryhow this is determined
#ato-benchmarks#australian-tax#payday-super#ato#python#accounting-ai#agent-skills#claude-code#codex#mcp#accounting#mcp-server#model-context-protocol#australian-taxation#cursor#tax-prep#australian-accounting

ryanduguid/australian-accounting holds a health index of 80 out of 100, placing it in the Excellent band. It scores highest on AI Readiness (93/100) and lowest on Community & Adoption (49/100). It was last updated today. A single contributor accounts for most of its recent work.

80
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.

80
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 68 is calibrated to 80 on the published index scale (record calibration 2026-08-02).

Ownership

Ryan DuguidPersonal account
11 followers129 public repossince Dec 2023

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
PyPIthe-wip-tally0.1.435154 days agoaasb-15accountingaustraliaconstructioncontract-assetminingwip
PyPIaus-accounting-mcp0.5.02,699210 days agoaccountingaccounting-aiatoato-benchmarksaustralian-taxdivision-7amcp-servermodel-context-protocolpayday-supertax
PyPIsolomons-sword0.2.0761812 days agoaccountingaustralian-taxbamforddivision-6itaa1936section-100asection-99btrust-accounting
PyPIdiv7a-loan-review0.2.01,044812 days agoaustraliadivision-7aitaa-1936accountingatotax
PyPIthe-exchequer-tally0.1.835554 days ago—
PyPIpayday-super-checker0.1.101,777104 days agoaustraliasuperannuationpayday-superaccountingato
PyPIato-benchmark-compare0.1.121,058114 days agoaccountingatoaustraliabenchmarkssmall-businesstax

Metrics by category

Vitality

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

74Good · 21% of overall

Development activity

60Moderate
How it's scored
36/36Push recency — last push 0 days ago
6.2/36Commit cadence — 9/52 weeks with commits
18/18Commit volume — 371 commits in the last year
0/10OpenSSF Scorecard: Maintained — project was created within the last 90 days. Please review its contents carefully
Inputs used
commits_last_year371
human_commit_share0.93
days_since_last_push0
active_weeks_last_year9

Release discipline

96Exceptional
How it's scored
27/27Ships releases — 71 releases published
36/36Release recency — latest release 0 days ago
27/27Release cadence — a release every ~1.4 days
6/10OpenSSF Scorecard: Signed-Releases — 3 out of the last 5 releases have a total of 3 signed artifacts.
Inputs used
releases_count71
latest_release_tagaus-accounting-mcp/v0.5.0
releases_from_tagsno
days_since_latest_release0
mean_days_between_releases1.4

Community & Adoption

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

49Weak · 17% of overall

Popularity & adoption

1Critical
How it's scored
0/60Stars — 2 stars
0/25Forks — 0 forks
0/15Watchers — 0 watchers
Inputs used
forks0
stars2
watchers0
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 (Apache-2.0)
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_badges12
has_contributingyes
has_issue_templateno
has_code_of_conductyes
readme_badge_servicesgithub.com, shields.io
has_pull_request_templateyes

Ecosystem adoption (downloads)

65Good
How it's scored
52.1/80Monthly downloads — 8,045 downloads/month across pypi
0/20Registry dependents — not reported by this ecosystem
Inputs used
packagesthe-wip-tally, aus-accounting-mcp, solomons-sword, div7a-loan-review, the-exchequer-tally, payday-super-checker, ato-benchmark-compare
dependents—
ecosystemspypi
total_downloads—
monthly_downloads8,045
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?

54Moderate · 23% of overall

Maintainer resilience (bus factor)

10Critical
How it's scored
9/54Bus factor — 1 contributor(s) cover half of all commits
0/22.5Commit distribution — top contributor authored 100% of commits
1.4/13.5Contributor breadth — 1 contributors
0/10OpenSSF Scorecard: Contributors — project has 0 contributing companies or organizations -- score normalized to 0
Inputs used
bus_factor1
contributors_sampled1
top_contributor_share1

Issue & PR responsiveness

79Good
How it's scored
42/42Issue resolution — 100% of issues closed
27/30PR acceptance — 365/405 decided PRs merged
0/13Newcomer PR acceptance — no first-time contributor's PR decided in 30d
0/15OpenSSF Scorecard: Code-Review — Found 0/28 approved changesets -- score normalized to 0
Inputs used
merged_prs365
open_issues0
closed_issues1
prs_merged_7d37
prs_decided_7d38
prs_merged_30d53
prs_decided_30d56
issue_closed_ratio1
closed_unmerged_prs40
first_time_authors_30d0
first_time_prs_merged_30d0
first_time_prs_decided_30d0
Excluded from scoring (no data or not applicable): Newcomer PR acceptance. Remaining weights renormalized.

Ownership & stewardship

46Weak
How it's scored
10/30Ownership backing — personal (user) account
0/20Verified domain — not applicable to user accounts
7.8/25Owner reach — 11 followers of ryanduguid
18.7/25Track record — 129 public repos, account ~2 yr old
Inputs used
followers11
owner_typeUser
is_verified—
owner_loginryanduguid
public_repos129
account_age_days1,049
Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 7 package(s) on pypi
35/35Publish recency — latest publish 0 days ago
20/20Version history — 21 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagesthe-wip-tally, aus-accounting-mcp, solomons-sword, div7a-loan-review, the-exchequer-tally, payday-super-checker, ato-benchmark-compare
ecosystemspypi
any_deprecatedno
min_days_since_publish0

Engineering Quality

Are baseline engineering and documentation practices in place?

80Excellent · 19% of overall

Engineering practices

90Excellent
How it's scored
24/24CI workflows — 22 workflow(s)
24/24Tests present
16/16Linter config — apps/aus-accounting-mcp/pyproject.toml ([tool.ruff]), apps/lodgeit-calculator-adapter/pyproject.toml ([tool.ruff]), packages/ato-benchmark-compare/pyproject.toml ([tool.ruff]), packages/au-tax-rates-data/pyproject.toml ([tool.ruff]), packages/australian-tax-calculators/pyproject.toml ([tool.ruff]), packages/div7a-loan-review/pyproject.toml ([tool.ruff]), packages/payday-super-checker/pyproject.toml ([tool.ruff]), packages/solomons-sword/pyproject.toml ([tool.ruff]), packages/the-exchequer-tally/pyproject.toml ([tool.ruff]), packages/the-wip-tally/pyproject.toml ([tool.ruff]), pyproject.toml ([tool.ruff])
0/9.6Pre-commit hooks
6.4/6.4.editorconfig
20/20OpenSSF Scorecard: CI-Tests — 30 out of 30 merged PRs checked by a CI test -- score normalized to 10
Inputs used
has_ciyes
has_testsyes
has_editorconfigyes
has_linter_configyes
has_precommit_configno

Documentation

65Good
How it's scored
30/30README
0/25Documentation directory
15/15Documentation / homepage site — https://duguid.com.au/tools/australian-tax-ai-agents/
10/10Repository description
10/10Topics — 17 topics
0/10Wiki
Inputs used
topicsato-benchmarks, australian-tax, payday-super, ato, python, accounting-ai, agent-skills, claude-code, codex, mcp, accounting, mcp-server, model-context-protocol, australian-taxation, cursor, tax-prep, australian-accounting
has_wikino
homepagehttps://duguid.com.au/tools/australian-tax-ai-agents/
docs_sitehttps://duguid.com.au/tools/australian-tax-ai-agents/
has_readmeyes
has_docs_dirno
has_descriptionyes

Security

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

79Good · 16% of overall

Security posture

74Good
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
2.5/2.5CI-Tests — 30 out of 30 merged PRs checked by a CI test -- score normalized to 10
1.2/2.5CII-Best-Practices — badge detected: Passing
0/7.5Code-Review — Found 0/28 approved changesets -- score normalized to 0
0/2.5Contributors — project has 0 contributing companies or organizations -- score normalized to 0
10/10Dangerous-Workflow — no dangerous workflow patterns detected
7.5/7.5Dependency-Update-Tool — update tool detected
5/5Fuzzing — project is fuzzed
2.5/2.5License — license file detected
0/7.5Maintained — project was created within the last 90 days. Please review its contents carefully
5/5Packaging — packaging workflow detected
5/5Pinned-Dependencies — all dependencies are pinned
5/5SAST — SAST tool detected
5/5Security-Policy — security policy file detected
4.5/7.5Signed-Releases — 3 out of the last 5 releases have a total of 3 signed artifacts.
7.5/7.5Token-Permissions — GitHub workflow tokens follow principle of least privilege
7.5/7.5Vulnerabilities — 0 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated18
scorecard_versionv5.5.0
checks_inconclusive0
scorecard_aggregate7.4

Dependency advisories

100Exceptional
How it's scored
35/35Direct dependencies free of known advisories — no direct dependency carries a known advisory
0/25Indirect dependencies free of known advisories — transitive set not separable from development and test dependencies in this scope
0/40No advisories left outstanding — no advisory carries a publication date
Inputs used
sourceosv
advisories0
affected_packages0
assessed_packages112
unassessed_packages2
affected_by_severitynone
direct_affected_packages0
Excluded from scoring (no data or not applicable): Indirect dependencies free of known advisories, No advisories left outstanding. Remaining weights renormalized. Matched 112 resolved dependencies against OSV. 2 could not be assessed — no resolved version, an unsupported ecosystem, or beyond the reported package list. This repository publishes no package the index resolves, so the repository dependency graph was assessed instead. That graph mixes development and test pins with shipped dependencies, so only the declared runtime dependencies are scored; transitive findings are reported as context and excluded from the score. 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.

93Exceptional · 4% of overall

Agent context & guidance

100Exceptional
How it's scored
45/45Agent instructions — AGENTS.md, CLAUDE.md, apps/aus-accounting-mcp/AGENTS.md, apps/aus-accounting-mcp/CLAUDE.md, apps/lodgeit-calculator-adapter/AGENTS.md
15/15Machine-readable docs (llms.txt) — llms.txt present
40/40Legible commit history — 92 of 93 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtyes
llms_txt_url—
legible_history_share0.989
agent_instruction_filesAGENTS.md, CLAUDE.md, apps/aus-accounting-mcp/AGENTS.md, apps/aus-accounting-mcp/CLAUDE.md, apps/lodgeit-calculator-adapter/AGENTS.md
agent_instruction_max_bytes3,522

Verify loop (build / test / typecheck)

90Excellent
How it's scored
18/18One-command bootstrap — justfile
22/22Automated tests
11/11Lint / format config — apps/aus-accounting-mcp/pyproject.toml ([tool.ruff]), apps/lodgeit-calculator-adapter/pyproject.toml ([tool.ruff]), packages/ato-benchmark-compare/pyproject.toml ([tool.ruff]), packages/au-tax-rates-data/pyproject.toml ([tool.ruff]), packages/australian-tax-calculators/pyproject.toml ([tool.ruff]), packages/div7a-loan-review/pyproject.toml ([tool.ruff]), packages/payday-super-checker/pyproject.toml ([tool.ruff]), packages/solomons-sword/pyproject.toml ([tool.ruff]), packages/the-exchequer-tally/pyproject.toml ([tool.ruff]), packages/the-wip-tally/pyproject.toml ([tool.ruff]), pyproject.toml ([tool.ruff])
11/11Static type checking — packages/ato-benchmark-compare/atobenchmark/py.typed, packages/div7a-loan-review/div7aloan/py.typed, packages/payday-super-checker/paydaysuper/py.typed, packages/solomons-sword/louisgoldberg/py.typed, packages/the-exchequer-tally/edwinnixon/py.typed, packages/the-wip-tally/wiptally/py.typed
10/10Reproducible environment — devcontainer, lockfile
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
10/10OpenSSF Scorecard: Pinned-Dependencies — all dependencies are pinned
Inputs used
has_nixno
has_testsyes
lockfilesuv.lock
has_dockerfileno
typed_languageno
bootstrap_filesjustfile
has_devcontaineryes
has_linter_configyes
typecheck_configspackages/ato-benchmark-compare/atobenchmark/py.typed, packages/div7a-loan-review/div7aloan/py.typed, packages/payday-super-checker/paydaysuper/py.typed, packages/solomons-sword/louisgoldberg/py.typed, packages/the-exchequer-tally/edwinnixon/py.typed, packages/the-wip-tally/wiptally/py.typed
agent_commit_share0
toolchain_manifests—
dependency_bot_commit_share0.07

Code legibility for models

81Excellent
How it's scored
27/45Type-checkable code — Python with type-check config (packages/ato-benchmark-compare/atobenchmark/py.typed, packages/div7a-loan-review/div7aloan/py.typed, packages/payday-super-checker/paydaysuper/py.typed, packages/solomons-sword/louisgoldberg/py.typed, packages/the-exchequer-tally/edwinnixon/py.typed, packages/the-wip-tally/wiptally/py.typed)
54.4/55Manageable file sizes — 3/270 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes157,272
source_files_sampled270
oversized_source_files3

Machine-readable interfaces

100Exceptional
How it's scored
0/40API schema (OpenAPI/GraphQL/proto) — not applicable to this kind of software
20/20MCP server
40/40Runnable examples — examples
Inputs used
example_dirsexamples
has_mcp_signalyes
api_schema_files—
interfaces_expected_of—
Excluded from scoring (no data or not applicable): API schema (OpenAPI/GraphQL/proto). Remaining weights renormalized.

Key facts

2GitHub stars
1contributors
371commits, last 12 months
0days since last push
71releases
1bus factor
0open issues
PyPIpackage ecosystems

Data collection warnings

  • Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
  • Could not fetch pypi package 'au-tax-rates-data' from its registry

More detail

OpenSSF Scorecard 7.4 / 10
7.4aggregate

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 · 2026-10-17 08:11 UTC

10Binary-Artifactsno binaries found in the repo
3Branch-Protectionbranch protection is not maximal on development and all release branches
10CI-Tests30 out of 30 merged PRs checked by a CI test -- score normalized to 10
5CII-Best-Practicesbadge detected: Passing
0Code-ReviewFound 0/28 approved changesets -- score normalized to 0
0Contributorsproject has 0 contributing companies or organizations -- score normalized to 0
10Dangerous-Workflowno dangerous workflow patterns detected
10Dependency-Update-Toolupdate tool detected
10Fuzzingproject is fuzzed
10Licenselicense file detected
0Maintainedproject was created within the last 90 days. Please review its contents carefully
10Packagingpackaging workflow detected
10Pinned-Dependenciesall dependencies are pinned
10SASTSAST tool detected
10Security-Policysecurity policy file detected
6Signed-Releases3 out of the last 5 releases have a total of 3 signed artifacts.
10Token-PermissionsGitHub workflow tokens follow principle of least privilege
10Vulnerabilities0 existing vulnerabilities detected
Direct dependencies 5
RegistryPackageVersion constraintManifest
PyPImcp>=2.3.0,<3apps/aus-accounting-mcp/pyproject.toml
PyPIpayday-super-checker==0.1.9apps/aus-accounting-mcp/pyproject.toml
PyPIato-benchmark-compare==0.1.11apps/aus-accounting-mcp/pyproject.toml
PyPIdiv7a-loan-review==0.2.0apps/aus-accounting-mcp/pyproject.toml
PyPIaustralian-tax-calculators==0.2.0apps/aus-accounting-mcp/pyproject.toml
All dependencies 114

Full resolved dependency set from the GitHub dependency graph: 10 direct and 104 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPIato-benchmark-compare0.1.11direct
PyPIato-benchmark-compare0.1.12direct
PyPIaustralian-tax-calculators0.1.3direct
PyPIaustralian-tax-calculators0.2.0direct
PyPIdiv7a-loan-review0.1.2direct
PyPIdiv7a-loan-review0.2.0direct
PyPImcp—direct
PyPImcp2.3.0direct
PyPIpayday-super-checker0.1.10direct
PyPIpayday-super-checker0.1.9direct
PyPIannotated-types0.8.0indirect
PyPIanyio4.14.2indirect
PyPIanyio4.15.1indirect
PyPIast-serialize0.12.1indirect
PyPIast-serialize0.8.0indirect
PyPIatheris3.1.0indirect
PyPIattrs26.1.0indirect
PyPIau-tax-rates-data0.1.0indirect
PyPIaus-accounting-mcp0.5.0indirect
PyPIbuild—indirect
PyPIbuild1.6.1indirect
PyPIcertifi2026.7.22indirect
PyPIcffi2.1.1indirect
PyPIchardet7.6.0indirect
PyPIcharset-normalizer3.5.1indirect
PyPIclick8.4.2indirect
PyPIclick8.5.0indirect
PyPIcolorama0.4.6indirect
PyPIcoverage7.15.4indirect
PyPIcoverage7.16.2indirect
PyPIcryptography50.0.0indirect
PyPIcryptography50.0.1indirect
PyPIdiff-cover10.6.0indirect
PyPIdocutils0.23indirect
PyPIet-xmlfile2.0.0indirect
PyPIh110.16.0indirect
PyPIhatchling1.32.4indirect
PyPIholidays0.106indirect
PyPIhttpcore22.12.0indirect
PyPIhttpx22.12.0indirect
PyPIhttpx2-jsfetch1.0indirect
PyPIhypothesis6.169.0indirect
PyPIid1.6.1indirect
PyPIidna3.19indirect
PyPIiniconfig2.3.0indirect
PyPIjaraco-classes3.4.0indirect
PyPIjaraco-context6.1.2indirect
PyPIjaraco-functools4.6.0indirect
PyPIjeepney0.9.0indirect
PyPIjinja23.1.6indirect
PyPIjsonschema4.26.0indirect
PyPIjsonschema-specifications2025.9.1indirect
PyPIkeyring25.7.0indirect
PyPIlibrt0.15.0indirect
PyPIlibrt0.16.0indirect
PyPIlodgeit-calculator-adapter0.1.0indirect
PyPImarkdown-it-py4.2.0indirect
PyPImarkupsafe3.0.3indirect
PyPImcp-types2.3.0indirect
PyPImdurl0.1.2indirect
PyPImore-itertools11.1.0indirect
PyPImypy2.3.1indirect
PyPImypy2.4.0indirect
PyPImypy-extensions1.1.0indirect
PyPInh30.3.7indirect
PyPIopenpyxl3.1.5indirect
PyPIopentelemetry-api1.44.0indirect
PyPIpackaging26.3indirect
PyPIpathspec1.1.1indirect
PyPIpillow12.3.0indirect
PyPIpluggy1.6.0indirect
PyPIpycparser3.0indirect
PyPIpydantic2.13.4indirect
PyPIpydantic2.13.5indirect
PyPIpydantic-core2.46.4indirect
PyPIpydantic-core2.46.5indirect
PyPIpygments2.20.0indirect
PyPIpygments2.21.0indirect
PyPIpyjwt2.15.1indirect
PyPIpyproject-hooks1.2.0indirect
PyPIpytest9.1.1indirect
PyPIpytest-cov7.1.0indirect
PyPIpython-dateutil2.9.0.post0indirect
PyPIpython-multipart0.0.32indirect
PyPIpywin32312indirect
PyPIpywin32-ctypes0.2.3indirect
PyPIreadme-renderer45.0indirect
PyPIreadme-renderer46.0indirect
PyPIreferencing0.37.0indirect
PyPIrequests2.34.2indirect
PyPIrequests-toolbelt1.0.0indirect
PyPIrfc39862.0.0indirect
PyPIrich15.0.0indirect
PyPIrpds-py2026.6.3indirect
PyPIruff0.16.5indirect
PyPIruff0.17.0indirect
PyPIsecretstorage3.5.0indirect
PyPIsetuptools84.0.0indirect
PyPIsix1.17.0indirect
PyPIsolomons-sword0.2.0indirect
PyPIsortedcontainers2.4.0indirect
PyPIsse-starlette3.4.11indirect
PyPIsse-starlette3.4.8indirect
PyPIstarlette1.6.0indirect
PyPIthe-exchequer-tally0.1.8indirect
PyPIthe-wip-tally0.1.4indirect
PyPItomlkit0.15.1indirect
PyPItrove-classifiers2026.9.21.13indirect
PyPItruststore0.10.4indirect
PyPItwine7.0.0indirect
PyPItyping-extensions4.16.0indirect
PyPItyping-inspection0.4.4indirect
PyPIurllib32.8.0indirect
PyPIuvicorn0.52.4indirect
Dependency advisories 0

This repository publishes no package the index resolves, so its own dependency graph was assessed — 112 packages, which also include development and test pins that never ship: 0 carry known advisories, of which 0 are direct. 2 could not be assessed — no resolved version, an unsupported ecosystem, or beyond the reported package list.

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 ryanduguid/australian-accounting. Read them side by side →

99awslabs/cli-agent-orchestratorMulti-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessionsExceptional97Observal/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.Exceptional99IBM/mcp-context-forgeAn AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.Exceptional98modelcontextprotocol/python-sdkThe official Python SDK for Model Context Protocol servers and clientsExceptional98CherryHQ/cherry-studioAI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMsExceptional98deepnote/deepnoteDeepnote is a drop-in replacement for Jupyter with an AI-first design, sleek UI, new blocks, and native data integrations. Use Python, R, and SQL locally in your favorite IDE, then scale to Deepnote cloud for real-time collaboration, Deepnote agent, and deployable data apps. https://deepnote.com/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.