Nanobot

Python Active

Python-native AI agent for research and automation

GitHub

Medium Security

4.8K

Stars

v0.9.3

Latest

~50MB

RAM

~1s

Startup

Overview News Videos Releases Benchmarks Security Community

Composite Score

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

Performance

#7 of 15

Features

#7 of 15

Security

#9 of 15

Momentum

#2 of 15

Cost Efficiency

#6 of 15

Dev Experience

#3 of 15

Cold Start Performance

Time from process launch to first response

Cold start

~1s #2

Warm response

~20ms

Memory Usage

Peak RSS during standard workload

Idle RSS

~50MB

Active RSS (10 tools)

85MB

Peak (stress test)

142MB

Token Efficiency

Tokens consumed per equivalent task completion

Simple Q&A

~160

Multi-step task

~600

Tool calling

~120

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.