Item detail
github.com

MADEVAL/FerryAI

MADEVAL/FerryAI is a code repository that RepoRadar is tracking in its Local inference section, currently rated Silver tier with a 'worth watch' verdict. It is written primarily in PHP. Its strongest signal is open-source/build quality, scored 8.4 out of 10.

Score7.5
Popularity56.0
Riskconditional
TierSilver
Score breakdown
Usefulness7.6
Novelty8.0
Momentum6.8
Maturity6.2
Open-source/build8.4
Evidence7.2
Workflow potential7.9
Setup ease4.2

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

FerryAI is a useful lower-star pick because PHP teams are often left out of local LLM and embedding infrastructure. The repo is early but unusually concrete: MIT license, tagged v0.1.x builds, Composer metadata, docs, examples, PHPStan/Psalm checks, and a large test count claimed in the README. It should be treated as worth_watch until the API settles and more users validate the FFI/runtime path.

Who should use it

PHP teams prototyping embeddings or local model inference without adding a Python service Developers comparing ONNX and GGUF runtime paths inside an existing PHP app RAG builders who want vector search and inference examples in a Composer-installable package

Who should skip it

Skip MADEVAL/FerryAI for now if your priority is a tool you can use today without configuring a build pipeline or development environment.

About this signal

MADEVAL/FerryAI is tracked by RepoRadar as a code repository in the Local inference section. First seen 2026-07-11; the source record was last checked on 2026-07-11. The current verdict is 'worth watch' with a Silver tier and hard setup difficulty. Across RepoRadar's eight signals, MADEVAL/FerryAI is strongest on open-source/build quality (8.4) and novelty (8.0) and weakest on setup ease (4.2) — a profile worth weighing against your own priorities. This page summarizes the public evidence on the linked source page and states where additional review is still needed.

How this item is evaluated

The MADEVAL/FerryAI record combines a 7.5/10 composite score with separate popularity (56.0), risk (conditional), and setup (hard) signals. See the scoring methodology for the current weights and evidence definitions.

Putting this into practice? Read How to evaluate an AI tool before you adopt it for the checklist behind this score.

Risk explanation

Native FFI and model runtimes load local libraries inside the PHP process; test dependency paths, memory use, and crash behavior before production use; The project is an early v0.1.x runtime with a still-stabilizing API; pin versions and expect interface changes before 1.0.

Evidence links
Closest alternatives / related signals
php local-inference onnx gguf llama-cpp embeddings rag vector-search
Verification record

What RepoRadar actually verified

Discovered

Automated discovery and source capture. Last checked 2026-08-13T20:20:15Z.

No editorial or hands-on review is claimed. This record remains at Discovered.

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

26 dated snapshots retained from 2026-07-11 through 2026-08-13; see the snapshot index for explicit coverage gaps. Stars, version, release, pricing, integration, risk, maintenance, verdict, score, and momentum fields remain explicit even when a source has not reported them. Repository momentum is a normalized 0–10 RepoRadar signal; GitHub stars appear only where the popularity monitor retained exact timestamped observations.

RepoRadar score7.5 current · +0.0 net
Repository momentum7.5 current · +0.7 net
GitHub stars (observed)40 current · -16 net
GitHub stars40 exact observation
Versionv0.1.0
Last release2026-07-07T22:02:20Z
Maintenanceactive
Current riskconditional
Current verdictworth watch
Pricing baselineNo structured commercial pricing baseline
Pricing checkedNot applicable or not recorded
Pricing freshnessNo dated commercial pricing review
Integrations baselineNo structured integrations recorded

Recent dated points

DateScoreMomentumStarsRiskVerdictMaintenance
2026-08-137.57.540conditionalworth watchactive
2026-08-127.57.540conditionalworth watchactive
2026-08-117.57.540conditionalworth watchactive
2026-08-107.57.540conditionalworth watchactive
2026-08-097.57.540conditionalworth watchactive
2026-08-087.59.040conditionalworth watchactive
2026-08-077.59.040conditionalworth watchactive
2026-08-067.56.8Not recordedconditionalworth watchnot recorded
2026-08-057.56.8Not recordedconditionalworth watchnot recorded
2026-08-047.59.040conditionalworth watchactive
2026-08-037.59.040conditionalworth watchactive
2026-08-027.59.040conditionalworth watchactive

Why the record changed

No material star, version, pricing, risk, integration, maintenance, verdict, or score change is recorded yet.