PicoClaw

Go Active

AI agent for edge devices and IoT

GitHub

Medium Security

12K

Stars

v2.0.1

Latest

<10MB

RAM

~1s

Startup

Overview News Videos Releases Benchmarks Security Community

Composite Score

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

Performance

#3 of 15

Features

#12 of 15

Security

#10 of 15

Momentum

#1 of 15

Cost Efficiency

#1 of 15

Dev Experience

#8 of 15

Cold Start Performance

Time from process launch to first response

Cold start

~1s #5

Warm response

~8ms

Memory Usage

Peak RSS during standard workload

Idle RSS

<10MB

Active RSS (10 tools)

18MB

Peak (stress test)

32MB

Token Efficiency

Tokens consumed per equivalent task completion

Simple Q&A

~95

Multi-step task

~380

Tool calling

~65

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.