Internal-Safety-Collapse
[NeurIPS 2026] Safety failures in coding agents and frontier LLMs. Reproducible workspaces for studying when AI agents generate unsafe data during task completion.
wuyoscar/Internal-Safety-Collapse
View on GitHub ↗[NeurIPS 2026] Safety failures in coding agents and frontier LLMs. Reproducible workspaces for studying when AI agents generate unsafe data during task completion.
Internal-Safety-Collapse grew +94.2% in the last 30 days, ranks 333rd of 2,587 in Agent SDK / Framework, actively maintained, last commit 2 days ago.
Star trajectory
75 days tracked+94.2% in 30d, above the Agent SDK / Framework median of +1.5%.
Last commit 2 days ago, fresher than the median of 14d.
How it compares in Agent SDK / Framework
Ranked 333rd of 2,587 by stars.
- Language
- Python
- License
- Other
- Contributors
- 2
- Forks
- 345
- Watchers
- 26
- Open issues
- 0
- Releases
- 0
- Created
- 2026-03-01
- Stars this week
- +576
You've seen where Internal-Safety-Collapse stands today.
Get the moves before everyone else: the 5 Agent SDK / Framework repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.