Registry › Compare › Claude Mem vs Vercel Skills

Claude Mem vs Vercel Skills

Both are Grade A and 0.6 points apart, so choose on what you weigh most. Vercel Skills leads on supply-chain integrity and adoption.

A Claude Mem 90.2

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

thedotmack/claude-mem · #4 overall · #4 Agent Skills · coverage B (3/5)

Claude Mem doesn't lead on any scored dimension in this pair.

A Vercel Skills 90.8

The open agent skills tool - npx skills

vercel-labs/skills · #2 overall · #2 Agent Skills · coverage B (3/5)

Choose Vercel Skills if supply-chain integrity and adoption matter most.

+1.7Adoption: 5.0M weekly downloads against 35.5k
+0.6Safety / Integrity: 100% of recent commits signed, against 91%

Where they differ

17.8

Safety / IntegrityVercel Skills +0.6

18.4

12.4

TransparencyVercel Skills +0.1

12.5

20.0

MaintenanceClaude Mem +0.3

19.7

18.2

AdoptionVercel Skills +1.7

19.9

+3.8

Runtime calibrationClaude Mem +1.5

+2.3

1 dimension identical: Identity 18.0 · Full evidence table

An independent, evidence-based trust comparison of Claude Mem and Vercel Skills, two Agent Skills projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.

Full evidence

Signal	Claude Memthedotmack/claude-mem	Vercel Skillsvercel-labs/skills
HVTrust score	90.2	90.8
Evidence grade	A	A
Coverage grade	B	B
Overall rank	#4	#2
Rank in Agent Skills	#4	#2
GitHub stars	115.5k	38.8k
Last updated	today	today
Build provenance	Yes	Yes
OSSF Scorecard	4.6 / 10	4.7 / 10
License	Apache-2.0	MIT
Downloads	36k/wk	5.0M/wk
Trust dimensions (points earned)
Safety / integrity / 25	17.8	18.4
Identity & provenance / 18	18.0	18.0
Transparency / 17	12.4	12.5
Maintenance / 20	20.0	19.7
Adoption / 20	18.2	19.9
Runtime capability surface (full matrix)
MCP server	Implemented	—
External providers	1 — Anthropic	—
Requires API keys	No	No
Plugin surface	plugins	—
Provenance drift	Match	Match

Open in the live compare tool → Claude Mem profile Vercel Skills profile More Agent Skills →

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.4 →