Public record
Software health reportschema 0.34.0 · metrics 2.10.0 · 2026-09-10 03:03 UTC

major7apps / pensyve

Universal memory runtime for AI agents

RustCustom license★ 79 stars⑂ 11 forkssince Mar 2026View on GitHub ↗
KindLibraryMCP serverNetwork serviceCommand-line toolhow this is determined
#agent-memory#ai-agents#embeddings#knowledge-graph#langchain#llm#mcp#mcp-server#memory#python#rag#rust#spaced-repetition#vector-search#anthropic#ai-memory#state-management#context-engineering#ai#openai

major7apps/pensyve holds a health index of 81 out of 100, placing it in the Excellent band. It scores highest on Engineering Quality (90/100) and lowest on Security (49/100). It was last updated 6 days ago. A single contributor accounts for most of its recent work.

81
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.

81
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 69 is calibrated to 81 on the published index scale (record calibration 2026-08-02).

Ownership

Major 7 Apps LLCOrganization
13 followers2 public repossince Jun 2024

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

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publishTags
PyPIpensyve4.0.02,657197 days agoaiagentsmemoryllmmcpretrievalembeddings
Gogithub.com/major7apps/pensyve/pensyve-go/v3v3.2.0-319 days ago—
crates.iopensyve-cli2.1.041128 days ago—
crates.iopensyve-mcp2.1.041128 days ago—
crates.iopensyve-core4.0.0101197 days agoagentsaillmmemoryretrievaldatabasescience
npm@pensyve/sdk4.0.0774137 days agoaiagentsmemoryllmmcpretrievalembeddings

Metrics by category

Vitality

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

82Excellent · 21% of overall

Development activity

77Good
How it's scored
36/36Push recency — last push 6 days ago
13.2/36Commit cadence — 19/52 weeks with commits
18/18Commit volume — 751 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 30 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year751
human_commit_share0.71
days_since_last_push6
active_weeks_last_year19

Release discipline

90Excellent
How it's scored
27/27Ships releases — 21 releases published
36/36Release recency — latest release 7 days ago
27/27Release cadence — a release every ~13.3 days
0/10OpenSSF Scorecard: Signed-Releases — Project has not signed or included provenance with any releases.
Inputs used
releases_count21
latest_release_tagv4.0.0
releases_from_tagsno
days_since_latest_release7
mean_days_between_releases13.3

Community & Adoption

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

59Moderate · 17% of overall

Popularity & adoption

42Weak
How it's scored
30.7/60Stars — 79 stars
8.3/25Forks — 11 forks
3.3/15Watchers — 5 watchers
Inputs used
forks11
stars79
watchers5
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

Community health

79Good
How it's scored
22.5/22.5README
16.9/22.5License — license file present, not a recognized license
18/18CONTRIBUTING guide
13.5/13.5Code of conduct
0/7.2Issue template
0/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges4
has_contributingyes
has_issue_templateno
has_code_of_conductyes
readme_badge_servicesgithub.com, shields.io
has_pull_request_templateno

Ecosystem adoption (downloads)

59Moderate
How it's scored
47.3/80Monthly downloads — 3,540 downloads/month across crates, go, npm, pypi
0/20Registry dependents — not reported by this ecosystem
Inputs used
packagespensyve, github.com/major7apps/pensyve/pensyve-go/v3, pensyve-cli, pensyve-mcp, pensyve-core, @pensyve/sdk
dependents—
ecosystemscrates, go, npm, pypi
total_downloads564
monthly_downloads3,540
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?

57Moderate · 23% of overall

Maintainer resilience (bus factor)

21At Risk
How it's scored
9/54Bus factor — 1 contributor(s) cover half of all commits
0.2/22.5Commit distribution — top contributor authored 99% of commits
5.4/13.5Contributor breadth — 4 contributors
6/10OpenSSF Scorecard: Contributors — project has 2 contributing companies or organizations -- score normalized to 6
Inputs used
bus_factor1
contributors_sampled4
top_contributor_share0.992

Issue & PR responsiveness

76Good
How it's scored
35.4/42Issue resolution — 84% of issues closed
21.7/30PR acceptance — 197/272 decided PRs merged
13/13Newcomer PR acceptance — 1/1 first-time contributors' PRs merged in 30d
6/15OpenSSF Scorecard: Code-Review — Found 12/29 approved changesets -- score normalized to 4
Inputs used
merged_prs197
open_issues8
closed_issues43
prs_merged_7d2
prs_decided_7d2
prs_merged_30d42
prs_decided_30d42
issue_closed_ratio0.843
closed_unmerged_prs75
first_time_authors_30d1
first_time_prs_merged_30d1
first_time_prs_decided_30d1

Ownership & stewardship

46Weak
How it's scored
30/30Ownership backing — organization-owned
0/20Verified domain
8.2/25Owner reach — 13 followers of major7apps
7.9/25Track record — 2 public repos, account ~2 yr old
Inputs used
followers13
owner_typeOrganization
is_verifiedno
owner_loginmajor7apps
public_repos2
account_age_days806

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 6 package(s) on crates, go, npm, pypi
35/35Publish recency — latest publish 7 days ago
20/20Version history — 19 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagespensyve, github.com/major7apps/pensyve/pensyve-go/v3, pensyve-cli, pensyve-mcp, pensyve-core, @pensyve/sdk
ecosystemscrates, go, npm, pypi
any_deprecatedno
min_days_since_publish7

Engineering Quality

Are baseline engineering and documentation practices in place?

90Excellent · 19% of overall

Engineering practices

84Excellent
How it's scored
24/24CI workflows — 6 workflow(s)
24/24Tests present
16/16Linter config — Cargo.toml ([workspace.lints]), clippy.toml, pensyve-benchmarks/Cargo.toml ([lints]), pensyve-cli/Cargo.toml ([lints]), pensyve-core/Cargo.toml ([lints]), pensyve-mcp-gateway/Cargo.toml ([lints]), pensyve-mcp-tools/Cargo.toml ([lints]), pensyve-mcp/Cargo.toml ([lints]), pensyve-python/Cargo.toml ([lints]), pyproject.toml ([tool.ruff]), rustfmt.toml
0/9.6Pre-commit hooks
0/6.4.editorconfig
20/20OpenSSF Scorecard: CI-Tests — 27 out of 27 merged PRs checked by a CI test -- score normalized to 10
Inputs used
has_ciyes
has_testsyes
has_editorconfigno
has_linter_configyes
has_precommit_configno

Documentation

100Exceptional
How it's scored
30/30README
25/25Documentation directory
15/15Documentation / homepage site — https://pensyve.com
10/10Repository description
10/10Topics — 20 topics
10/10Wiki
Inputs used
topicsagent-memory, ai-agents, embeddings, knowledge-graph, langchain, llm, mcp, mcp-server, memory, python, rag, rust, spaced-repetition, vector-search, anthropic, ai-memory, state-management, context-engineering, ai, openai
has_wikiyes
homepagehttps://pensyve.com
docs_sitehttps://pensyve.com
has_readmeyes
has_docs_diryes
has_descriptionyes

Security

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

49Weak · 16% of overall

Security posture

49Weak
How it's scored
7.5/7.5Binary-Artifacts — no binaries found in the repo
0/7.5Branch-Protection — branch protection not enabled on development/release branches
2.5/2.5CI-Tests — 27 out of 27 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
3/7.5Code-Review — Found 12/29 approved changesets -- score normalized to 4
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
2.2/2.5License — license file detected
7.5/7.5Maintained — 30 commit(s) and 30 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
5/5Security-Policy — security policy file 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 — 450 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated18
scorecard_versionv5.5.0
checks_inconclusive0
scorecard_aggregate4.9

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.

88Excellent · 4% of overall

Agent context & guidance

100Exceptional
How it's scored
45/45Agent instructions — AGENTS.md, CLAUDE.md, integrations/codex-plugin/AGENTS.md, integrations/hermes/AGENTS.md, integrations/openclaw-plugin/AGENTS.md, integrations/opencode-plugin/AGENTS.md, pensyve-ts/CLAUDE.md
15/15Machine-readable docs (llms.txt) — llms.txt present
40/40Legible commit history — 70 of 71 human commits state their intent (structured subject or explanatory body)
Inputs used
has_llms_txtyes
llms_txt_url—
legible_history_share0.986
agent_instruction_filesAGENTS.md, CLAUDE.md, integrations/codex-plugin/AGENTS.md, integrations/hermes/AGENTS.md, integrations/openclaw-plugin/AGENTS.md, integrations/opencode-plugin/AGENTS.md, pensyve-ts/CLAUDE.md
agent_instruction_max_bytes13,865

Verify loop (build / test / typecheck)

86Excellent
How it's scored
18/18One-command bootstrap — Makefile
22/22Automated tests
11/11Lint / format config — Cargo.toml ([workspace.lints]), clippy.toml, pensyve-benchmarks/Cargo.toml ([lints]), pensyve-cli/Cargo.toml ([lints]), pensyve-core/Cargo.toml ([lints]), pensyve-mcp-gateway/Cargo.toml ([lints]), pensyve-mcp-tools/Cargo.toml ([lints]), pensyve-mcp/Cargo.toml ([lints]), pensyve-python/Cargo.toml ([lints]), pyproject.toml ([tool.ruff]), rustfmt.toml
11/11Static type checking — integrations/langchain-ts/tsconfig.json, integrations/openclaw-plugin/tsconfig.json, integrations/opencode-plugin/tsconfig.json, integrations/vscode/tsconfig.json, pensyve-ts/tsconfig.json
10/10Reproducible environment — Dockerfile, lockfile
6/10Demonstrated agent practice — 3 of the last 100 commits agent-authored or agent-credited
8/8Automated maintenance — 29 of the last 100 commits are automated dependency updates
0/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0
Inputs used
has_nixno
has_testsyes
lockfilesCargo.lock, package-lock.json, uv.lock
has_dockerfileyes
typed_languageyes
bootstrap_filesMakefile
has_devcontainerno
has_linter_configyes
typecheck_configsintegrations/langchain-ts/tsconfig.json, integrations/openclaw-plugin/tsconfig.json, integrations/opencode-plugin/tsconfig.json, integrations/vscode/tsconfig.json, pensyve-ts/tsconfig.json
agent_commit_share0.03
toolchain_manifestsCargo.toml, loadtest/Cargo.toml, pensyve-benchmarks/Cargo.toml, pensyve-cli/Cargo.toml, pensyve-core/Cargo.toml, pensyve-go/go.mod, pensyve-mcp-gateway/Cargo.toml, pensyve-mcp-tools/Cargo.toml, pensyve-mcp/Cargo.toml, pensyve-python/Cargo.toml, pensyve-wasm/Cargo.toml
dependency_bot_commit_share0.29

Code legibility for models

97Exceptional
How it's scored
45/45Type-checkable code — Rust (statically typed)
52.3/55Manageable file sizes — 12/247 source files over 60KB
Inputs used
primary_languageRust
largest_source_bytes500,892
source_files_sampled247
oversized_source_files12

Machine-readable interfaces

60Moderate
How it's scored
0/40API schema (OpenAPI/GraphQL/proto)
20/20MCP server
40/40Runnable examples — examples
Inputs used
example_dirsexamples
has_mcp_signalyes
api_schema_files—
interfaces_expected_ofnetwork-service

Key facts

79GitHub stars
4contributors
751commits, last 12 months
6days since last push
21releases
1bus factor
8open issues
crates.io, Go, npm, PyPIpackage ecosystems

Data collection warnings

  • Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
  • Could not fetch crates package 'pensyve-loadtest' from its registry
  • Could not fetch crates package 'pensyve-wasm' from its registry
  • GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository

More detail

Star and fork history 0 ★ / 11 ⇿
0Stars
11Forks
14Releases

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.

0246810121112026-042026-062026-08
Major 1Minor 5Patch 6
OpenSSF Scorecard 4.9 / 10
4.9aggregate

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 · 2026-09-10 03:03 UTC

10Binary-Artifactsno binaries found in the repo
0Branch-Protectionbranch protection not enabled on development/release branches
10CI-Tests27 out of 27 merged PRs checked by a CI test -- score normalized to 10
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
4Code-ReviewFound 12/29 approved changesets -- score normalized to 4
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
9Licenselicense file detected
10Maintained30 commit(s) and 30 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
10Security-Policysecurity policy file detected
0Signed-ReleasesProject has not signed or included provenance with any releases.
0Token-Permissionsdetected GitHub workflow tokens with excessive permissions
0Vulnerabilities450 existing vulnerabilities detected
Direct dependencies 100
RegistryPackageVersion constraintManifest
crates.ioreqwest0.12loadtest/Cargo.toml
crates.iotokio1loadtest/Cargo.toml
crates.ioserde_json1loadtest/Cargo.toml
crates.ioclap4loadtest/Cargo.toml
crates.iopensyve-core4.0.0pensyve-benchmarks/Cargo.toml
crates.iorand0.10pensyve-benchmarks/Cargo.toml
crates.iorand_distr0.6pensyve-benchmarks/Cargo.toml
crates.ioserde1pensyve-benchmarks/Cargo.toml
crates.ioserde_json1pensyve-benchmarks/Cargo.toml
crates.iochrono0.4pensyve-benchmarks/Cargo.toml
crates.iouuid1pensyve-benchmarks/Cargo.toml
crates.iorayon1.10pensyve-benchmarks/Cargo.toml
crates.ioreqwest0.13pensyve-benchmarks/Cargo.toml
crates.iopensyve-core4.0.0pensyve-cli/Cargo.toml
crates.ioclap4pensyve-cli/Cargo.toml
crates.ioserde_json1pensyve-cli/Cargo.toml
crates.iouuid1pensyve-cli/Cargo.toml
crates.iodirs6pensyve-cli/Cargo.toml
crates.iorusqlite0.40pensyve-core/Cargo.toml
crates.iouuid1pensyve-core/Cargo.toml
crates.ioserde1pensyve-core/Cargo.toml
crates.ioserde_json1pensyve-core/Cargo.toml
crates.iosha20.11pensyve-core/Cargo.toml
crates.iohex0.4pensyve-core/Cargo.toml
crates.iochrono0.4pensyve-core/Cargo.toml
crates.iothiserror2pensyve-core/Cargo.toml
crates.iodirs6pensyve-core/Cargo.toml
crates.ioregex1pensyve-core/Cargo.toml
crates.iofastembed=6.0.1pensyve-core/Cargo.toml
crates.iopetgraph0.8pensyve-core/Cargo.toml
crates.iophf0.14pensyve-core/Cargo.toml
crates.iodashmap6pensyve-core/Cargo.toml
crates.iorayon1.10pensyve-core/Cargo.toml
crates.iotracing0.1pensyve-core/Cargo.toml
crates.ioasync-trait0.1pensyve-core/Cargo.toml
crates.ioreqwest0.12pensyve-core/Cargo.toml
crates.iosqlx-core0.9.0pensyve-core/Cargo.toml
crates.iosqlx-postgres0.9.0pensyve-core/Cargo.toml
crates.iotokio1pensyve-core/Cargo.toml
crates.iotokio-util—pensyve-core/Cargo.toml
crates.iofutures0.3pensyve-core/Cargo.toml
crates.iopensyve-core4.0.0pensyve-mcp-gateway/Cargo.toml
crates.iopensyve-mcp-tools4.0.0pensyve-mcp-gateway/Cargo.toml
crates.iormcp3.1pensyve-mcp-gateway/Cargo.toml
crates.ioaxum0.8pensyve-mcp-gateway/Cargo.toml
crates.iotower-http0.7pensyve-mcp-gateway/Cargo.toml
crates.iotokio1pensyve-mcp-gateway/Cargo.toml
crates.iotower0.5pensyve-mcp-gateway/Cargo.toml
crates.ioserde1pensyve-mcp-gateway/Cargo.toml
crates.ioserde_json1pensyve-mcp-gateway/Cargo.toml
crates.ioschemars1pensyve-mcp-gateway/Cargo.toml
crates.iouuid1pensyve-mcp-gateway/Cargo.toml
crates.ioanyhow1pensyve-mcp-gateway/Cargo.toml
crates.iotracing0.1pensyve-mcp-gateway/Cargo.toml
crates.iotracing-subscriber0.3pensyve-mcp-gateway/Cargo.toml
crates.iosha20.11pensyve-mcp-gateway/Cargo.toml
crates.iohex0.4pensyve-mcp-gateway/Cargo.toml
crates.ioreqwest0.12pensyve-mcp-gateway/Cargo.toml
crates.iodashmap6pensyve-mcp-gateway/Cargo.toml
crates.ioredis1.2pensyve-mcp-gateway/Cargo.toml
crates.iojsonwebtoken11pensyve-mcp-gateway/Cargo.toml
crates.iotokio-util0.7pensyve-mcp-gateway/Cargo.toml
crates.iodirs6pensyve-mcp-gateway/Cargo.toml
crates.iochrono0.4pensyve-mcp-gateway/Cargo.toml
crates.iosqlx-core0.9.0pensyve-mcp-gateway/Cargo.toml
crates.iosqlx-postgres0.9.0pensyve-mcp-gateway/Cargo.toml
crates.iotempfile3pensyve-mcp-gateway/Cargo.toml
crates.iopensyve-core4.0.0pensyve-mcp-tools/Cargo.toml
crates.iormcp3.1pensyve-mcp-tools/Cargo.toml
crates.iotokio1pensyve-mcp-tools/Cargo.toml
crates.iotokio-util—pensyve-mcp-tools/Cargo.toml
crates.ioserde1pensyve-mcp-tools/Cargo.toml
crates.ioserde_json1pensyve-mcp-tools/Cargo.toml
crates.ioschemars1pensyve-mcp-tools/Cargo.toml
crates.iouuid1pensyve-mcp-tools/Cargo.toml
crates.iotracing0.1pensyve-mcp-tools/Cargo.toml
crates.iopensyve-core4.0.0pensyve-mcp/Cargo.toml
crates.iopensyve-mcp-tools4.0.0pensyve-mcp/Cargo.toml
crates.iormcp3.1pensyve-mcp/Cargo.toml
crates.iotokio1pensyve-mcp/Cargo.toml
crates.iouuid1pensyve-mcp/Cargo.toml
crates.iodirs6pensyve-mcp/Cargo.toml
crates.ioanyhow1pensyve-mcp/Cargo.toml
crates.iotracing0.1pensyve-mcp/Cargo.toml
crates.iotracing-subscriber0.3pensyve-mcp/Cargo.toml
crates.iopensyve-core4.0.0pensyve-python/Cargo.toml
crates.iopyo3^0.29.0pensyve-python/Cargo.toml
crates.iouuid1pensyve-python/Cargo.toml
crates.iochrono0.4pensyve-python/Cargo.toml
crates.ioserde_json1pensyve-python/Cargo.toml
crates.iotracing0.1pensyve-python/Cargo.toml
crates.iotracing-subscriber0.3pensyve-python/Cargo.toml
crates.iotokio1pensyve-python/Cargo.toml
crates.iotokio-util—pensyve-python/Cargo.toml
crates.iowasm-bindgen0.2pensyve-wasm/Cargo.toml
crates.ioserde1pensyve-wasm/Cargo.toml
crates.ioserde_json1pensyve-wasm/Cargo.toml
crates.iouuid1pensyve-wasm/Cargo.toml
crates.iochrono0.4pensyve-wasm/Cargo.toml
PyPIhttpx>=0.27pyproject.toml
All dependencies not collected

The resolved dependency set could not be collected for this report: GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository

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 major7apps/pensyve. Read them side by side →

100deepset-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.Exceptional98langchain-ai/langchainjsThe agent engineering platformExceptional98PostHog/posthog-jsSend usage data from your web app or site to PostHog, with autocapture.Exceptional99awslabs/cli-agent-orchestratorMulti-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessionsExceptional98googleapis/mcp-toolboxMCP Toolbox for Databases is an open source MCP server for databases.Exceptional98bytedance/deer-flowAn open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.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, Go, crates.io, npm.