Fetching from the wire…
Public story · 2026-03-10 · source-backed
Surging alongside OpenAI acquisition news and Codex Security. 11,651 stars. Essential for agent security testing. GitHub
Each link below shares sources, entities, or timing with this story.
Open-source framework for testing, evaluating, and red-teaming LLM prompts, agents, and RAG systems. Covers OWASP LLM Top 10. Used by 127 Fortune 500 companies. Now acquired by OpenAI but committed to continuing the open-source offering. The de facto standard for AI pentesting...
OpenAI's Codex skills catalog gained 46 stars today, but the API shows its last push was eight weeks ago and its open items split into 0 pull requests and 77 issues (GitHub). A first-party catalog that accepts no outside code and hasn't been touched in two months is a weaker e...
promptfoo 0.122.2 (August 28) makes Codex's security analysis drivable as an evaluation target alongside ordinary model providers, plus a configurable Cloud auth header name. The same day's code-scan-action 0.2.0 hardens the action's supply chain, patches undici and guards bot...
Two competing models for AI-powered security shipped on the same day. OpenAI launched Codex Security ("Aardvark") — an AI AppSec agent that builds project-specific threat models, then hunts for vulnerabilities and tests them in isolated environments. 30-day beta: 1.2M+ commits...
Published September 7, it puts OpenAI Codex in the agent picker with a copy-ready ~/.codex/config.toml panel pointing Codex CLI and Desktop at Manifest over the Responses API (GitHub). Two compatibility fixes make it work: Responses-API role: "developer" instruction messages f...
Eight thousand stars in a single day. That's what happened when Warp open-sourced its Rust-based, GPU-accelerated terminal on April 28. The repo shot to 47.9K total stars, making it the highest-velocity project on GitHub this week by a wide margin. But the interesting part isn...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.