Easily switch between alternative low-cost AI models in Claude Code/Agent SDK. For those comfortable using Claude agents and commands, it lets you take what you've created and deploy fully hosted agents for real business purposes. Use Claude Code to get the agent working, then deploy it in your favorite cloud.
ruvnet/agentic-flow holds a health index of 71 out of 100, placing it in the Good band. It scores highest on Engineering Quality (93/100) and lowest on Security (32/100). It was last updated 36 days ago. A single contributor accounts for most of its recent work.
71
overall / 100
Good
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.
71
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 63 is calibrated to 71 on the published index scale (record calibration 2026-08-02).
Direct dependencies free of known advisories — 1 affected: sharp 0.34.5 (high 7.3)
6.9/25
Indirect dependencies free of known advisories — 4 affected: @opentelemetry/propagator-jaeger 2.7.1 (high 7.5), adm-zip 0.5.18 (high 7.5), @opentelemetry/core 1.30.1 (moderate 5.3), +1 more
40/40
No advisories left outstanding — no advisory has been public longer than 90 days
Inputs used
source
osv
advisories
5
affected_packages
5
assessed_packages
584
unassessed_packages
0
affected_by_severity
high 3, moderate 2
direct_affected_packages
1
Matched the npm:agentic-flow@2.1.2 runtime dependency closure — what installing the published package pulls in — 584 packages. Reachability is not analyzed.
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.
Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
Could not fetch npm package '@agentic-flow/reasoningbank-benchmark' from its registry
npm package 'analysis' points at a different repository (https://github.com/seikho/analysis); excluded from ecosystem scoring
GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
OpenSSF Scorecard did not return a usable result (killed by SIGKILL — most likely the container's memory limit; 2026/09/04 10:09:56 Warning: PATs stored in env variables GITHUB_AUTH_TOKEN and GITHUB_TOKEN differ. Scorecard will use the former.); skipping Scorecard checks
More detail
Star and fork history 0 ★ / 175 ⇿
0Stars
175Forks
24Releases
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 1Minor 5Patch 16
Each point covers 2 days.
Direct dependencies 67
Registry
Package
Version constraint
Manifest
npm
@anthropic-ai/claude-agent-sdk
^0.1.5
agentic-flow/package.json
npm
@anthropic-ai/sdk
^0.65.0
agentic-flow/package.json
npm
@google/genai
^1.22.0
agentic-flow/package.json
npm
@metaharness/router
^0.3.2
agentic-flow/package.json
npm
@ruvector/core
^0.1.29
agentic-flow/package.json
npm
@ruvector/edge-full
^0.1.0
agentic-flow/package.json
npm
@ruvector/router
^0.1.30
agentic-flow/package.json
npm
@ruvector/ruvllm
^2.5.5
agentic-flow/package.json
npm
@ruvector/tiny-dancer
^0.1.17
agentic-flow/package.json
npm
@supabase/supabase-js
^2.78.0
agentic-flow/package.json
npm
@huggingface/transformers
^3.8.1
agentic-flow/package.json
npm
agentdb
3.0.0-alpha.20
agentic-flow/package.json
npm
axios
^1.12.2
agentic-flow/package.json
npm
dotenv
^16.4.5
agentic-flow/package.json
npm
express
^5.1.0
agentic-flow/package.json
npm
fastmcp
^3.19.0
agentic-flow/package.json
npm
glob
^13.0.0
agentic-flow/package.json
npm
gun
^0.2020.1241
agentic-flow/package.json
npm
http-proxy-middleware
^3.0.5
agentic-flow/package.json
npm
ruvector
0.2.40
agentic-flow/package.json
npm
ruvector-onnx-embeddings-wasm
^0.1.2
agentic-flow/package.json
npm
tiktoken
^1.0.22
agentic-flow/package.json
npm
ulid
^3.0.1
agentic-flow/package.json
npm
ws
^8.20.0
agentic-flow/package.json
npm
yaml
^2.8.1
agentic-flow/package.json
npm
zod
^3.25.76
agentic-flow/package.json
npm
@anthropic-ai/sdk
^0.32.1
bench/package.json
npm
better-sqlite3
^11.7.0
bench/package.json
npm
ulid
^2.3.0
bench/package.json
npm
@anthropic-ai/claude-agent-sdk
^0.1.5
package.json
npm
@anthropic-ai/claude-code
^2.1.150
package.json
npm
@anthropic-ai/sdk
^0.65.0
package.json
npm
@google/genai
^1.22.0
package.json
npm
@ruvector/attention
^0.1.2
package.json
npm
@ruvector/core
^0.1.31
package.json
npm
@ruvector/gnn
^0.1.23
package.json
npm
@ruvector/ruvllm
^2.5.3
package.json
npm
@ruvector/sona
^0.1.3
package.json
npm
@supabase/supabase-js
^2.78.0
package.json
npm
@types/react
^19.2.2
package.json
npm
@types/react-dom
^19.2.2
package.json
npm
@vitejs/plugin-react-swc
^4.2.0
package.json
npm
@xenova/transformers
^2.17.2
package.json
npm
agentdb
^3.0.0-alpha.14
package.json
npm
agentic-payments
^0.1.13
package.json
npm
autoprefixer
^10.4.21
package.json
npm
axios
^1.16.1
package.json
npm
better-sqlite3
^11.10.0
package.json
npm
dotenv
^16.4.5
package.json
npm
express
^5.1.0
package.json
npm
fastmcp
^3.19.0
package.json
npm
http-proxy-middleware
^3.0.5
package.json
npm
lucide-react
^0.548.0
package.json
npm
marked
^17.0.3
package.json
npm
postcss
^8.5.15
package.json
npm
react
^19.2.0
package.json
npm
react-dom
^19.2.0
package.json
npm
react-router-dom
^7.15.1
package.json
npm
ruvector
^0.2.18
package.json
npm
tailwindcss
^4.1.16
package.json
npm
tailwindcss-animate
^1.0.7
package.json
npm
tiktoken
^1.0.22
package.json
npm
ulid
^3.0.1
package.json
npm
vite
^8.0.14
package.json
npm
ws
^8.21.0
package.json
npm
yaml
^2.9.0
package.json
npm
zod
^3.25.76
package.json
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
Dependency advisories 5
Installing npm:agentic-flow@2.1.2 pulls in 584 packages, direct and transitive: 5 carry known advisories, of which 1 are direct dependencies.
Package
Version
Relation
Severity
Advisories
Fixed in
sharp
0.34.5
direct
high
1
0.35.0
@opentelemetry/propagator-jaeger
2.7.1
indirect
high
1
2.9.0
adm-zip
0.5.18
indirect
high
1
0.6.0
@opentelemetry/core
1.30.1
indirect
moderate
1
2.8.0
@opentelemetry/core
2.7.1
indirect
moderate
1
2.8.0
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.
Related records
Inspected repositories sharing catalogue tags or ecosystems with ruvnet/agentic-flow. Read them side by side →
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.
