Technology & AI
AI coding agent defense cuts malware severity 83%
SkillShield bakes security skills into the system prompt, dropping malware severity from 3.37 to 0.58 across six models while refusing just 0.14% of benign
AI Agents
91 stories
Technology & AI
StepGuard blocks AI agent attacks 77% before they run
StepGuard from Shanghai AI Lab checks AI agent tool calls before execution, cutting attack success 77% while losing just 2.8 points of utility.
Technology & AI
Vibe coding: security prompt halves AI app flaws
An arXiv preprint found adding security requirements to AI coding prompts cut confirmed flaws from 51 to 24 across six web apps, with zero critical issues.
Technology & AI
Google Gemini CLI hits 106,000 stars with free 1,000-request daily tier
Google's Gemini CLI offers 1,000 free AI requests daily in the terminal, with a 1M token context window and Gemini 3 models. Now 106,000 stars.
Technology & AI
NVIDIA Groq 3 LPX hits full production at 3,400 tokens/second
NVIDIA's Groq 3 LPX inference accelerator is now in full production, delivering a record 3,400 tokens/second for agentic AI workloads.
Technology & AI
Nakama AI agent platform trends on GitHub at 259 stars
The TypeScript AI agent platform landed on GitHub's daily trending list on 22 August, pitching multi-tenant team features the bigger names lack.
Technology & AI
Tencent AI-Infra-Guard: 5,200-star AI red team tool trends
Tencent Zhuque Lab's open-source tool scans AI agents, MCP servers and LLM jailbreaks. It has 5,200+ stars and a README that explicitly asks for them.
Technology & AI
Claude Code v2.1.239 adds cost tracking, hits 142k stars
Anthropic's Claude Code crossed 142,000 GitHub stars as v2.1.239 adds cost estimates with a 1.1x US-only inference premium for data-residency users.
Technology & AI
GxP-Agent hits 100% on clinical trial coding benchmark
GxP-Agent encodes regulatory steps as a graph, turning 0% failure into 100% structural match on a new FDA-pilot clinical trial benchmark.
Technology & AI
DeAR: AI agents reason peer-to-peer without a central boss
A new arXiv paper proposes DeAR, a framework where AI agents coordinate reasoning without a central orchestrator, tested across nine benchmarks.
Technology & AI
Looped LLMs improve multi-step AI tool calling, study finds
Cambridge researchers find looped language models improve at multi-step API tool calling, with adaptive inference offering the best compute-performance
Technology & AI
Agentic AI review on arXiv as OpenAI agent repo nears 29,000 stars
A new arXiv preprint surveys agentic AI from working principles to adoption factors, as developer frameworks signal explosive real-world traction.