Public record
Software health reportschema 0.34.0 · metrics 2.10.0 · 2026-09-20 01:34 UTC

runcycles / cycles-openclaw-budget-guard

Cycles budget and action guard for OpenClaw agents

TypeScriptApache-2.0★ 7 stars⑂ 0 forkssince Mar 2026View on GitHub ↗
KindLibraryhow this is determined
#openclaw#cost-control#ai-agents#budget#llm#ai-governance#finops#llmops#openclaw-plugin#agent-governance#agent-runtime#agent-safety#multi-tenant#runtime-authority#action-control#agentic-ai#budget-control

runcycles/cycles-openclaw-budget-guard holds a health index of 83 out of 100, placing it in the Excellent band. It scores highest on Vitality (89/100) and lowest on Community & Adoption (45/100). It was last updated 6 days ago. A single contributor accounts for most of its recent work.

83
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.

83
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 70 is calibrated to 83 on the published index scale (record calibration 2026-08-02).

Ownership

runcycles.ioOrganization
11 followers20 public repossince Feb 2026

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

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publishTags
npm@runcycles/openclaw-budget-guard0.9.0862454 days agoai-agentagent-budgetagent-governancebudget-controlcost-controlcost-enforcementspending-limitllm-costruntime-authorityaction-controlaction-authorityaudit-trailauditcompliancemulti-tenantopenclawopenclaw-pluginmcpclaudeanthropicopenaicyclesruncycles

Metrics by category

Vitality

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

89Excellent · 21% of overall

Development activity

81Excellent
How it's scored
36/36Push recency — last push 6 days ago
17.3/36Commit cadence — 25/52 weeks with commits
18/18Commit volume — 358 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year358
human_commit_share0.25
days_since_last_push6
active_weeks_last_year25

Release discipline

100Exceptional
How it's scored
27/27Ships releases — 23 releases published
36/36Release recency — latest release 54 days ago
27/27Release cadence — a release every ~13.2 days
0/10OpenSSF Scorecard: Signed-Releases — no data
Inputs used
releases_count23
latest_release_tagv0.9.0
releases_from_tagsno
days_since_latest_release54
mean_days_between_releases13.2
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?

45Weak · 17% of overall

Popularity & adoption

13Critical
How it's scored
12.6/60Stars — 7 stars
0/25Forks — 0 forks
0/15Watchers — 0 watchers
Inputs used
forks0
stars7
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_badges6
has_contributingyes
has_issue_templateno
has_code_of_conductyes
readme_badge_servicesgithub.com, shields.io
has_pull_request_templateyes

Ecosystem adoption (downloads)

32At Risk
How it's scored
25.9/80Monthly downloads — 86 downloads/month across npm
0/20Registry dependents — not reported by this ecosystem
Inputs used
packages@runcycles/openclaw-budget-guard
dependents—
ecosystemsnpm
total_downloads—
monthly_downloads86
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?

61Moderate · 23% of overall

Maintainer resilience (bus factor)

27At Risk
How it's scored
9/54Bus factor — 1 contributor(s) cover half of all commits
9.3/22.5Commit distribution — top contributor authored 59% of commits
2.7/13.5Contributor breadth — 2 contributors
6/10OpenSSF Scorecard: Contributors — project has 2 contributing companies or organizations -- score normalized to 6
Inputs used
bus_factor1
contributors_sampled2
top_contributor_share0.586

Issue & PR responsiveness

82Excellent
How it's scored
42/42Issue resolution — 100% of issues closed
29.4/30PR acceptance — 149/152 decided PRs merged
0/13Newcomer PR acceptance — no first-time contributor's PR decided in 30d
0/15OpenSSF Scorecard: Code-Review — Found 0/2 approved changesets -- score normalized to 0
Inputs used
merged_prs149
open_issues0
closed_issues8
prs_merged_7d0
prs_decided_7d0
prs_merged_30d0
prs_decided_30d0
issue_closed_ratio1
closed_unmerged_prs3
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

49Weak
How it's scored
30/30Ownership backing — organization-owned
0/20Verified domain
7.8/25Owner reach — 11 followers of runcycles
10.8/25Track record — 20 public repos, account ~0 yr old
Inputs used
followers11
owner_typeOrganization
is_verifiedno
owner_loginruncycles
public_repos20
account_age_days223

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 1 package(s) on npm
35/35Publish recency — latest publish 54 days ago
20/20Version history — 24 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packages@runcycles/openclaw-budget-guard
ecosystemsnpm
any_deprecatedno
min_days_since_publish54

Engineering Quality

Are baseline engineering and documentation practices in place?

67Good · 19% of overall

Engineering practices

68Good
How it's scored
24/24CI workflows — 3 workflow(s)
24/24Tests present
0/16Linter config
0/9.6Pre-commit hooks
0/6.4.editorconfig
20/20OpenSSF Scorecard: CI-Tests — 14 out of 14 merged PRs checked by a CI test -- score normalized to 10
Inputs used
has_ciyes
has_testsyes
has_editorconfigno
has_linter_configno
has_precommit_configno

Documentation

65Good
How it's scored
30/30README
0/25Documentation directory
15/15Documentation / homepage site — https://runcycles.io
10/10Repository description
10/10Topics — 17 topics
0/10Wiki
Inputs used
topicsopenclaw, cost-control, ai-agents, budget, llm, ai-governance, finops, llmops, openclaw-plugin, agent-governance, agent-runtime, agent-safety, multi-tenant, runtime-authority, action-control, agentic-ai, budget-control
has_wikino
homepagehttps://runcycles.io
docs_sitehttps://runcycles.io
has_readmeyes
has_docs_dirno
has_descriptionyes

Security

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

85Excellent · 16% of overall

Security posture

81Excellent
How it's scored
7.5/7.5Binary-Artifacts — no binaries found in the repo
0/7.5Branch-Protection — no data
2.5/2.5CI-Tests — 14 out of 14 merged PRs checked by a CI test -- score normalized to 10
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
0/7.5Code-Review — Found 0/2 approved changesets -- score normalized to 0
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 0 issue activity found in the last 90 days -- score normalized to 10
5/5Packaging — packaging workflow detected
3.5/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 7
5/5SAST — SAST tool is run on all commits
5/5Security-Policy — security policy file detected
0/7.5Signed-Releases — no data
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_evaluated16
scorecard_versionv5.5.0
checks_inconclusive2
scorecard_aggregate8.1
Excluded from scoring (no data or not applicable): Branch-Protection, Signed-Releases. Remaining weights renormalized.

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_packages1
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 npm:@runcycles/openclaw-budget-guard@0.9.0 runtime dependency closure — what installing the published package pulls in — 1 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.

80Excellent · 4% of overall

Agent context & guidance

100Exceptional
How it's scored
45/45Agent instructions — CLAUDE.md
15/15Machine-readable docs (llms.txt) — llms.txt served by the project website (https://runcycles.io/llms.txt)
40/40Legible commit history — 25 of 25 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtyes
llms_txt_urlhttps://runcycles.io/llms.txt
legible_history_share1
agent_instruction_filesCLAUDE.md
agent_instruction_max_bytes666

Verify loop (build / test / typecheck)

58Moderate
How it's scored
0/18One-command bootstrap
22/22Automated tests
0/11Lint / format config
11/11Static type checking — tsconfig.json
10/10Reproducible environment — lockfile
0/10Demonstrated agent practice — no agent-authored commits among the last 100
8/8Automated maintenance — 50 of the last 100 commits are automated dependency updates
7/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 7
Inputs used
has_nixno
has_testsyes
lockfilespackage-lock.json
has_dockerfileno
typed_languageyes
bootstrap_files—
has_devcontainerno
has_linter_configno
typecheck_configstsconfig.json
agent_commit_share0
toolchain_manifests—
dependency_bot_commit_share0.5

Code legibility for models

98Exceptional
How it's scored
45/45Type-checkable code — TypeScript (statically typed)
52.6/55Manageable file sizes — 1/23 source files over 60KB
Inputs used
primary_languageTypeScript
largest_source_bytes138,162
source_files_sampled23
oversized_source_files1

Key facts

7GitHub stars
2contributors
358commits, last 12 months
6days since last push
23releases
1bus factor
0open issues
npmpackage ecosystems

Data collection warnings

  • Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token

More detail

OpenSSF Scorecard 8.1 / 10
8.1aggregate

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 · 2026-09-20 01:34 UTC

10Binary-Artifactsno binaries found in the repo
n/aBranch-Protectioninternal error: error during branchesHandler.setup: internal error: some github tokens can't read classic branch protection rules: https://github.com/ossf/scorecard-action/blob/main/docs/authentication/fine-grained-auth-token.md
10CI-Tests14 out of 14 merged PRs checked by a CI test -- score normalized to 10
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
0Code-ReviewFound 0/2 approved changesets -- score normalized to 0
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 0 issue activity found in the last 90 days -- score normalized to 10
10Packagingpackaging workflow detected
7Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 7
10SASTSAST tool is run on all commits
10Security-Policysecurity policy file detected
n/aSigned-Releasesno releases found
10Token-PermissionsGitHub workflow tokens follow principle of least privilege
10Vulnerabilities0 existing vulnerabilities detected
Direct dependencies 1
RegistryPackageVersion constraintManifest
npmruncycles^0.4.0package.json
All dependencies 178

Full resolved dependency set from the GitHub dependency graph: 1 direct and 177 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
npmruncycles0.4.3direct
npm@babel/helper-string-parser7.27.1indirect
npm@babel/helper-validator-identifier7.28.5indirect
npm@babel/parser7.29.0indirect
npm@babel/types7.29.0indirect
npm@bcoe/v8-coverage1.0.2indirect
npm@esbuild/aix-ppc640.28.1indirect
npm@esbuild/android-arm0.28.1indirect
npm@esbuild/android-arm640.28.1indirect
npm@esbuild/android-x640.28.1indirect
npm@esbuild/darwin-arm640.28.1indirect
npm@esbuild/darwin-x640.28.1indirect
npm@esbuild/freebsd-arm640.28.1indirect
npm@esbuild/freebsd-x640.28.1indirect
npm@esbuild/linux-arm0.28.1indirect
npm@esbuild/linux-arm640.28.1indirect
npm@esbuild/linux-ia320.28.1indirect
npm@esbuild/linux-loong640.28.1indirect
npm@esbuild/linux-mips64el0.28.1indirect
npm@esbuild/linux-ppc640.28.1indirect
npm@esbuild/linux-riscv640.28.1indirect
npm@esbuild/linux-s390x0.28.1indirect
npm@esbuild/linux-x640.28.1indirect
npm@esbuild/netbsd-arm640.28.1indirect
npm@esbuild/netbsd-x640.28.1indirect
npm@esbuild/openbsd-arm640.28.1indirect
npm@esbuild/openbsd-x640.28.1indirect
npm@esbuild/openharmony-arm640.28.1indirect
npm@esbuild/sunos-x640.28.1indirect
npm@esbuild/win32-arm640.28.1indirect
npm@esbuild/win32-ia320.28.1indirect
npm@esbuild/win32-x640.28.1indirect
npm@jridgewell/gen-mapping0.3.13indirect
npm@jridgewell/resolve-uri3.1.2indirect
npm@jridgewell/sourcemap-codec1.5.5indirect
npm@jridgewell/trace-mapping0.3.31indirect
npm@oxc-project/types0.146.0indirect
npm@rolldown/binding-android-arm-eabi1.2.5indirect
npm@rolldown/binding-android-arm641.2.5indirect
npm@rolldown/binding-darwin-arm641.2.5indirect
npm@rolldown/binding-darwin-x641.2.5indirect
npm@rolldown/binding-freebsd-x641.2.5indirect
npm@rolldown/binding-linux-arm-gnueabihf1.2.5indirect
npm@rolldown/binding-linux-arm64-gnu1.2.5indirect
npm@rolldown/binding-linux-arm64-musl1.2.5indirect
npm@rolldown/binding-linux-ppc64-gnu1.2.5indirect
npm@rolldown/binding-linux-s390x-gnu1.2.5indirect
npm@rolldown/binding-linux-x64-gnu1.2.5indirect
npm@rolldown/binding-linux-x64-musl1.2.5indirect
npm@rolldown/binding-openharmony-arm641.2.5indirect
npm@rolldown/binding-win32-arm64-msvc1.2.5indirect
npm@rolldown/binding-win32-x64-msvc1.2.5indirect
npm@rolldown/pluginutils1.0.1indirect
npm@rollup/rollup-android-arm-eabi4.59.0indirect
npm@rollup/rollup-android-arm644.59.0indirect
npm@rollup/rollup-darwin-arm644.59.0indirect
npm@rollup/rollup-darwin-x644.59.0indirect
npm@rollup/rollup-freebsd-arm644.59.0indirect
npm@rollup/rollup-freebsd-x644.59.0indirect
npm@rollup/rollup-linux-arm-gnueabihf4.59.0indirect
npm@rollup/rollup-linux-arm-musleabihf4.59.0indirect
npm@rollup/rollup-linux-arm64-gnu4.59.0indirect
npm@rollup/rollup-linux-arm64-musl4.59.0indirect
npm@rollup/rollup-linux-loong64-gnu4.59.0indirect
npm@rollup/rollup-linux-loong64-musl4.59.0indirect
npm@rollup/rollup-linux-ppc64-gnu4.59.0indirect
npm@rollup/rollup-linux-ppc64-musl4.59.0indirect
npm@rollup/rollup-linux-riscv64-gnu4.59.0indirect
npm@rollup/rollup-linux-riscv64-musl4.59.0indirect
npm@rollup/rollup-linux-s390x-gnu4.59.0indirect
npm@rollup/rollup-linux-x64-gnu4.59.0indirect
npm@rollup/rollup-linux-x64-musl4.59.0indirect
npm@rollup/rollup-openbsd-x644.59.0indirect
npm@rollup/rollup-openharmony-arm644.59.0indirect
npm@rollup/rollup-win32-arm64-msvc4.59.0indirect
npm@rollup/rollup-win32-ia32-msvc4.59.0indirect
npm@rollup/rollup-win32-x64-gnu4.59.0indirect
npm@rollup/rollup-win32-x64-msvc4.59.0indirect
npm@standard-schema/spec1.1.0indirect
npm@types/chai5.2.3indirect
npm@types/deep-eql4.0.2indirect
npm@types/estree1.0.8indirect
npm@types/node26.4.1indirect
npm@vitest/coverage-v84.1.11indirect
npm@vitest/expect4.1.11indirect
npm@vitest/mocker4.1.11indirect
npm@vitest/pretty-format4.1.11indirect
npm@vitest/runner4.1.11indirect
npm@vitest/snapshot4.1.11indirect
npm@vitest/spy4.1.11indirect
npm@vitest/utils4.1.11indirect
npmacorn8.16.0indirect
npmany-promise1.3.0indirect
npmassertion-error2.0.1indirect
npmast-v8-to-istanbul1.0.0indirect
npmbundle-require5.1.0indirect
npmcac6.7.14indirect
npmchai6.2.2indirect
npmchokidar4.0.3indirect
npmcommander4.1.1indirect
npmconfbox0.1.8indirect
npmconsola3.4.2indirect
npmconvert-source-map2.0.0indirect
npmdebug4.4.3indirect
npmdetect-libc2.1.2indirect
npmes-module-lexer2.0.0indirect
npmesbuild0.28.1indirect
npmestree-walker3.0.3indirect
npmexpect-type1.3.0indirect
npmfdir6.5.0indirect
npmfix-dts-default-cjs-exports1.0.1indirect
npmfsevents2.3.3indirect
npmhas-flag4.0.0indirect
npmhtml-escaper2.0.2indirect
npmistanbul-lib-coverage3.2.2indirect
npmistanbul-lib-report3.0.1indirect
npmistanbul-reports3.2.0indirect
npmjoycon3.1.1indirect
npmjs-tokens10.0.0indirect
npmlightningcss1.33.0indirect
npmlightningcss-android-arm641.33.0indirect
npmlightningcss-darwin-arm641.33.0indirect
npmlightningcss-darwin-x641.33.0indirect
npmlightningcss-freebsd-x641.33.0indirect
npmlightningcss-linux-arm-gnueabihf1.33.0indirect
npmlightningcss-linux-arm64-gnu1.33.0indirect
npmlightningcss-linux-arm64-musl1.33.0indirect
npmlightningcss-linux-x64-gnu1.33.0indirect
npmlightningcss-linux-x64-musl1.33.0indirect
npmlightningcss-win32-arm64-msvc1.33.0indirect
npmlightningcss-win32-x64-msvc1.33.0indirect
npmlilconfig3.1.3indirect
npmlines-and-columns1.2.4indirect
npmload-tsconfig0.2.5indirect
npmmagic-string0.30.21indirect
npmmagicast0.5.2indirect
npmmake-dir4.0.0indirect
npmmlly1.8.1indirect
npmms2.1.3indirect
npmmz2.7.0indirect
npmnanoid3.3.18indirect
npmobject-assign4.1.1indirect
npmobug2.1.1indirect
npmpathe2.0.3indirect
npmpicocolors1.1.1indirect
npmpicomatch4.0.5indirect
npmpirates4.0.7indirect
npmpkg-types1.3.1indirect
npmpostcss8.5.26indirect
npmpostcss-load-config6.0.1indirect
npmreaddirp4.1.2indirect
npmresolve-from5.0.0indirect
npmrolldown1.2.5indirect
npmrollup4.59.0indirect
npmsemver7.7.4indirect
npmsiginfo2.0.0indirect
npmsource-map0.7.6indirect
npmsource-map-js1.2.1indirect
npmstackback0.0.2indirect
npmstd-env4.0.0indirect
npmsucrase3.35.1indirect
npmsupports-color7.2.0indirect
npmthenify3.3.1indirect
npmthenify-all1.6.0indirect
npmtinybench2.9.0indirect
npmtinyexec0.3.2indirect
npmtinyexec1.0.4indirect
npmtinyglobby0.2.17indirect
npmtinyrainbow3.1.0indirect
npmtree-kill1.2.2indirect
npmts-interface-checker0.1.13indirect
npmtsup8.5.1indirect
npmtypescript6.0.3indirect
npmufo1.6.3indirect
npmundici-types8.3.0indirect
npmvite8.2.2indirect
npmvitest4.1.11indirect
npmwhy-is-node-running2.3.0indirect
Dependency advisories 0

Installing npm:@runcycles/openclaw-budget-guard@0.9.0 pulls in 1 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 runcycles/cycles-openclaw-budget-guard. Read them side by side →

98Agenta-AI/agentaAgenta is a workspace where you and your team build agents and automations.Exceptional97strands-agents/harness-sdkBuild an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.Exceptional96diegosouzapw/OmniRouteNever stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 550+ contributorsExceptional95MemTensor/MemOSSelf-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.Exceptional98ComposioHQ/composioComposio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.Exceptional97langgenius/difyBuild Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.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 — npm.