Registry › Compare › agentmemory vs ReMe

agentmemory vs ReMe

Both score 88.9/100, so choose on what you weigh most. agentmemory leads on maintenance and adoption.

A agentmemory 88.9

#1 Persistent memory for AI coding agents based on real-world benchmarks

rohitg00/agentmemory · #43 overall · #1 Memory & Knowledge · coverage B (3/5)

Choose agentmemory if maintenance and adoption matter most.

+1.2Adoption: 30k GitHub stars against 3.7k
+0.5Maintenance

A ReMe 88.9

ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.

agentscope-ai/ReMe · #46 overall · #2 Memory & Knowledge · coverage B (3/5)

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

Where they differ

14.4

Transparencyagentmemory +0.4

14.0

20.0

Maintenanceagentmemory +0.5

19.5

15.8

Adoptionagentmemory +1.2

14.6

+0.1

Runtime calibrationReMe +2.1

+2.2

2 dimensions identical: Safety 20.6 · Identity 18.0 · Full evidence table

An independent, evidence-based trust comparison of agentmemory and ReMe, two Memory & Knowledge projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.

Full evidence

Signal	agentmemoryrohitg00/agentmemory	ReMeagentscope-ai/ReMe
HVTrust score	88.9	88.9
Evidence grade	A	A
Coverage grade	B	B
Overall rank	#43	#46
Rank in Memory & Knowledge	#1	#2
GitHub stars	30.0k	3.7k
Last updated	today	today
Build provenance	Yes	Yes
OSSF Scorecard	6.9 / 10	6.5 / 10
License	Apache-2.0	Apache-2.0
Downloads	7k/wk	34k/wk
Trust dimensions (points earned)
Safety / integrity / 25	20.6	20.6
Identity & provenance / 18	18.0	18.0
Transparency / 17	14.4	14.0
Maintenance / 20	20.0	19.5
Adoption / 20	15.8	14.6
Runtime capability surface (full matrix)
MCP server	Implemented	Implemented
External providers	5 — Anthropic, Google Gemini, OpenAI, …	2 — Anthropic, OpenAI
Requires API keys	Yes	Yes
Plugin surface	plugins	plugins
Provenance drift	Match	Match

Open in the live compare tool → agentmemory profile ReMe profile More Memory & Knowledge →

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 →