4GitHub Trending (AI/LLM filtered)·
vercel-labs/deepsec: agent-powered security vulnerability harness gains traction on GitHub
Vercel Labs has published deepsec, a TypeScript security harness that uses coding agents to find vulnerabilities in codebases. The project has accumulated 6,018 GitHub stars with 348 added in a single day, indicating significant community interest. It represents a practical application of coding agents to automated security analysis.
Related guides (1)
Related events (8)
Vercel Labs releases open agent skills tool (npx skills)
Vercel Labs has published an open-source TypeScript project called 'skills' on GitHub, providing an agent skills tool invocable via npx. The repository has accumulated 23,611 stars with 106 added today, suggesting significant community interest. The project appears to be a framework or harness for defining and running agent capabilities.
Anthropic Launches Claude Code Security: AI-Powered Vulnerability Detection for Defenders
Anthropic has released Claude Code Security in limited research preview for Enterprise and Team customers, a capability built into Claude Code that scans codebases for security vulnerabilities and suggests patches for human review. Unlike rule-based static analysis tools, it uses Claude's reasoning to understand code context, trace data flows, and detect complex vulnerabilities including novel ones. Built on Claude Opus 4.6, the system found over 500 previously undetected vulnerabilities in production open-source codebases during internal research. The release is framed as a defensive measure to put AI-enabled vulnerability discovery in the hands of defenders before attackers can exploit the same capabilities.
Vercel AI SDK: open-source TypeScript toolkit for AI-powered applications and agents
Vercel's AI SDK is an open-source TypeScript library for building AI-powered applications and agents, created by the team behind Next.js. The repository has accumulated 24,842 GitHub stars with modest daily growth (+11 today). It represents a widely-adopted tooling layer for integrating LLMs into TypeScript/JavaScript applications.
Anthropic releases claude-code-security-review GitHub Action for automated security analysis
Anthropic published an open-source GitHub Action that uses Claude to automatically analyze code changes for security vulnerabilities as part of CI/CD workflows. The tool integrates directly into GitHub pull request pipelines. With 5,157 stars, it has attracted meaningful community interest as a practical agentic coding security tool.
Codex Security: now in research preview
OpenAI has launched Codex Security in research preview, an AI-powered application security agent. It analyzes project context to detect, validate, and patch complex vulnerabilities with the goal of higher confidence and reduced false-positive noise compared to traditional tools. The product extends OpenAI's Codex brand into the security domain.
Deep Eye: Multi-Provider AI-Orchestrated Vulnerability Scanner
Deep Eye is an open-source Python tool that orchestrates multiple AI providers (OpenAI, Claude, Grok, Gemini, Ollama, Groq, Mistral, and others) to generate attack payloads and scan targets for 45+ vulnerability types. It produces professional security reports with compliance mapping. The project has accumulated 1,572 GitHub stars with 42 added today, indicating growing community interest in AI-augmented offensive security tooling.
NVIDIA releases SkillSpector: security scanner for AI agent skills
NVIDIA has published SkillSpector, an open-source Python tool for scanning AI agent skills to detect vulnerabilities, malicious patterns, and security risks. The repository is trending on GitHub with 1,920 total stars and 280 added today. The tool addresses an emerging security concern as agentic AI systems proliferate and third-party skill/tool ecosystems grow.
wshobson/agents: Multi-harness agentic plugin marketplace for major AI coding tools
A GitHub repository called 'agents' by wshobson provides a multi-harness agentic plugin marketplace targeting Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLI. The project has accumulated 37,134 stars with modest daily momentum (+43 today). It represents a cross-platform approach to agent tooling that spans multiple competing AI coding environments.