cybergym

CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on real-world vulnerability analysis tasks.

sunblaze-ucb/cybergym

View on GitHub ↗

CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on real-world vulnerability analysis tasks.

cybergym grew +6.3% in the last 30 days, ranks 131st of 744 in Evaluation & Guardrails, last commit 59 days ago.

Star trajectory

116 days tracked
2026-07-02972 stars today2026-10-26
Momentum

+6.3% in 30d, above the Evaluation & Guardrails median of +1.2%.

Maintenance

Last commit 59 days ago, staler than the median of 14d.

How it compares in Evaluation & Guardrails

cybergym
972
stars
+6.3% 30d
commit 59 days ago
Evaluation & Guardrails median
242.5
stars
+1.2% 30d
commit ~14d ago
Leader · WeKnora
35.5k
stars
+17.6% 30d
commit today

Ranked 131st of 744 by stars.

Language
Python
License
Apache License 2.0
Contributors
2
Forks
118
Watchers
13
Open issues
8
Releases
0
Created
2025-06-02
Stars this week
+13

You've seen where cybergym stands today.

Get the moves before everyone else: the 5 Evaluation & Guardrails repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain cybergym?

Claim this page to add your own call-to-action.

Claim this page