Registry › Compare › Claude Mem vs ffmpeg-skill

Claude Mem vs ffmpeg-skill

Both are Grade A and 0.5 points apart, so choose on what you weigh most. Claude Mem leads on adoption; ffmpeg-skill leads on supply-chain integrity and transparency.

A Claude Mem 90.5

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 · #3 overall · #3 Agent Skills · coverage B (3/5)

Choose Claude Mem if adoption matters most.

+4.5Adoption: 100.5k weekly downloads against 9.5k

A ffmpeg-skill 90.0

Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.

kajisho5/ffmpeg-skill · #4 overall · #4 Agent Skills · coverage B (3/5)

Choose ffmpeg-skill if supply-chain integrity and transparency matter most.

+2.5Transparency: OSSF Scorecard 7.5 against 4.6
+1.9Safety / Integrity: OSSF Scorecard 7.5 against 4.6

Where they differ

17.7

Safety / Integrityffmpeg-skill +1.9

19.6

12.4

Transparencyffmpeg-skill +2.5

14.9

19.9

Maintenanceffmpeg-skill +0.1

20.0

18.8

AdoptionClaude Mem +4.5

14.3

+3.7

Runtime calibrationClaude Mem +0.5

+3.2

1 dimension identical: Identity 18.0 · Full evidence table

An independent, evidence-based trust comparison of Claude Mem and ffmpeg-skill, 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	ffmpeg-skillkajisho5/ffmpeg-skill
HVTrust score	90.5	90.0
Evidence grade	A	A
Coverage grade	B	B
Overall rank	#3	#4
Rank in Agent Skills	#3	#4
GitHub stars	117.2k	5.6k
Last updated	1d ago	today
Build provenance	Yes	Yes
OSSF Scorecard	4.6 / 10	7.5 / 10
License	Apache-2.0	MIT
Downloads	100k/wk	9k/wk
Trust dimensions (points earned)
Safety / integrity / 25	17.7	19.6
Identity & provenance / 18	18.0	18.0
Transparency / 17	12.4	14.9
Maintenance / 20	19.9	20.0
Adoption / 20	18.8	14.3
Runtime capability surface (full matrix)
MCP server	Implemented	Implemented
External providers	1 — Anthropic	2 — Anthropic, Google Gemini
Requires API keys	No	No
Plugin surface	plugins	plugins
Provenance drift	Match	Match

Open in the live compare tool → Claude Mem profile ffmpeg-skill 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 →