What did Hlido score shenmintao/marginalia?

shenmintao/marginalia scored 82/100 (STEADY) in Hlido's independent, hands-on review.

How much does shenmintao/marginalia cost?

Hlido recorded the pricing model as: Open source. Derived from evidence Hlido holds, not vendor-supplied; verify current prices on the vendor's pricing page.

Does any vendor pay Hlido for placement?

No. Hlido takes no money from the agents it rates — scoring weights stay private and the evidence behind every verdict is public.

shenmintao/marginalia

Name: shenmintao/marginalia review
Item: shenmintao/marginalia
Rating: 82
Author: Hlido Editor

Productivity · tested 2026-09-30 · by the Hlido desk, not the vendor

In short: Tidy, fully-passing PKM system with LLM agents and a library-science bent — agent-consumable, but AGPL-3.0 constrains commercial reuse.

10 PASS · 0 FAIL of 10 public-surface claims

Visit shenmintao/marginalia → scorecard.json

Quick answer

shenmintao/marginalia scores 82/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-09-30). STEADY (82) on a clean, fully-passing checklist and steady maintenance. Pricing: Open source (free entry point documented).

Hlido Editor · 2026-09-30

marginalia is a personal knowledge-management system inspired by library science, with LLM agents layered over an interlinked note store. On the repository signals it is a clean project — 211 stars, actively maintained, releases present, CI in place, and it passes every checklist item including agent-consumable. The library-science framing is more than branding: PKM tools live or die on how well they impose structure on messy inputs, and a cataloguing mindset is a promising foundation for that. The single most important thing a buyer should notice is not a defect but a licence: marginalia is AGPL-3.0, not MIT like most of its neighbours, which meaningfully constrains commercial and networked reuse — anyone embedding it in a hosted product needs to understand the copyleft obligations before adopting. Beyond that, the usual repo-surface caveat holds: we have not hands-on tested retrieval quality or how the agents behave over a large, real knowledge base, so the intelligence of the system is asserted rather than verified. As a personal or open-source PKM it is a credible, well-kept option; check the AGPL terms against your intended use first.

Why STEADY

STEADY (82) on a clean, fully-passing checklist and steady maintenance. Held below VITAL by the repo-surface ceiling (retrieval and agent quality untested hands-on); the AGPL-3.0 licence is flagged not as a quality defect but as a material adoption constraint.

Public-surface checklist

PASS Repo reachable (required) — GH API 200 for shenmintao/marginalia
PASS Readme present (required) — README length 21823
PASS License present (required) — AGPL-3.0
PASS Install documented (required) — install/usage section found in README
PASS Active 12mo (required) — last push 8d ago
PASS Releases present — latest v0.3.3
PASS Community traction — 211 stars
PASS Ci or tests — 2 workflow file(s)
PASS Recent commit 90d — last push 8d ago
PASS Agent consumable — MCP server markers in README

What we saw

1 screenshot captured by the Hlido engine during the reviewed run (run-fba57003d3b9cf39-github-com). Our own captures — not vendor marketing material.

shenmintao/marginalia — run screenshot 1 (home.png) — home.png

What it does well

Passes every checklist item, including agent-consumable
Actively maintained with releases and CI present
Library-science structuring is a sound foundation for knowledge management
Clear niche and coherent design for personal / open-source use

What it fails at

AGPL-3.0 licence materially constrains commercial and networked reuse — check obligations before embedding
Not hands-on tested: retrieval quality and agent behaviour over a large knowledge base are unverified
Modest traction (211 stars) — a smaller community to lean on

Best for

Individuals wanting a structured, agent-assisted personal knowledge base
Open-source projects compatible with AGPL-3.0
Users who value a cataloguing-first approach to notes

Not recommended for

Commercial products that cannot accept AGPL-3.0 copyleft obligations
Buyers who need verified retrieval-quality guarantees
Teams wanting a large ecosystem and support community

Pricing & access

ModelOpen source
Free entry pointYes — a free tier or open-source edition is documented

Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-07-16.

Agent relevance

No programmatic surfaces

LLM agents operate over the note store; documented as agent-consumable. AGPL-3.0 is the gating consideration for any embedded or hosted use.

Agent-friendly score: 5/10

Evidence

— source
— source
— source

scorecard.json · transparency passport · registry · methodology

More: compare agents · best of · developer tools · incident registry

Verdict by Hlido Editor, our automated editorial system · Method: repo-surface-signals+editorial-narrative-v2 · Methodology version 2026.05 ·

How this page was produced. The scores, claim verdicts and evidence come from automated hands-on testing of the product’s public surface. The written analysis is drafted by an AI system, and pages publish without a person reviewing each one. Hlido publishes this record and answers for it — tell us if anything here is wrong and we will correct it.

Embed this trust badge

Live, always-current independent score — free to embed on your site or README. No vendor pays for placement.

Markdown

[![Hlido trust score](https://hlido.eu/badge/shenmintao-marginalia.svg)](https://hlido.eu/check/?agent=shenmintao-marginalia)

HTML

<a href="https://hlido.eu/check/?agent=shenmintao-marginalia"><img src="https://hlido.eu/badge/shenmintao-marginalia.svg" alt="Hlido trust score"></a>