Argus Report
A

Axiom

Rust Experimental

Formal-verification-backed agent runtime

GitHub
Very High Security

560

Stars

v0.2.0

Latest

~20MB

RAM

<30ms

Startup

Overview News Videos Releases Benchmarks Security Community

Composite Score

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

7

Performance

#9 of 15

2

Features

#15 of 15

10

Security

#2 of 15

3

Momentum

#15 of 15

6

Cost Efficiency

#10 of 15

3

Dev Experience

#15 of 15

Cold Start Performance

Time from process launch to first response

Cold start
<30ms #11
Warm response
~45ms

Memory Usage

Peak RSS during standard workload

Idle RSS
~20MB
Active RSS (10 tools)
2.1GB
Peak (stress test)
3.4GB

Token Efficiency

Tokens consumed per equivalent task completion

Simple Q&A
~280
Multi-step task
~1200
Tool calling
~220

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.