Argus Report
m

memU

TypeScript Active

Persistent memory layer for AI agents

GitHub
Medium Security

6.9K

Stars

v1.4.0

Latest

varies

RAM

n/a

Startup

Overview News Videos Releases Benchmarks Security Community

Composite Score

Argus Report scoring across six dimensions (1-10 scale)

5

Performance

#10 of 15

5

Features

#8 of 15

6

Security

#7 of 15

7

Momentum

#7 of 15

6

Cost Efficiency

#9 of 15

6

Dev Experience

#9 of 15

Cold Start Performance

Time from process launch to first response

Cold start
n/a #7
Warm response
n/a

Memory Usage

Peak RSS during standard workload

Idle RSS
varies
Active RSS (10 tools)
varies
Peak (stress test)
varies

Token Efficiency

Tokens consumed per equivalent task completion

Simple Q&A
~200
Multi-step task
~700
Tool calling
~150

Methodology

Benchmarks are run weekly on standardized hardware (AWS c7g.xlarge, 4 vCPU, 8GB RAM, Ubuntu 24.04). Token efficiency is measured using equivalent prompts across Claude 4.5 Sonnet. All results are averages of 10 runs with cold cache. Last updated: Feb 17, 2026.