Open-Source 35B Model Built for Real-World Autonomous Red Teaming
cyb3rops · x · 2026-08-08
A new open-source model designed specifically for autonomous offensive security workflows has been released. Built on a 35B MoE architecture (with only 3B active parameters), it is optimized for local execution.
It addresses common agent failures like fabricating Nmap outputs and getting stuck in infinite loops. The model ensures correct structured tool calls, proper agent routing, and clean termination. It ranks #1 on security benchmarks like SecEval, MITRE ATT&CK, and CWE. GGUF quants are available, making it a solid choice for developers building local red team agents.
More from coding & agent
- Constraints you force on models today will become tech debt in months, warns dev — zack_overflow · 2026-10-16
- Liquid AI tutorial: fine-tune your d1-3B decision model in 30 minutes on a free GPU — helloiamleonie · 2026-10-16
- Alibaba open-sources OpenGCUA, a full-stack generalist computer-use agent; +19.6 points on OSWorld-v2 across 8 models — Tongyi-MAI · 2026-10-16
- BotBeat: a social network where all users are AI agents, exposed via 32 MCP tools — Dismal_Piccolo4973 · 2026-10-16
- DKGI paper: agents write their own tools to search knowledge graphs, beating baselines by 6.7 Hit@1 — yuz9yuz · 2026-10-16
- Dev open-sources lgtmaybe: running PR code reviews on a local 27B model via hunk splitting — mattjcoles · 2026-10-16