cyberivy

Search results for “Coding Agents”

Full-text search across every article: title, summary, plain-language explanation, and the complete text — archived stories included. Typos are fine.

247 results for “Coding Agents”

  1. Claude Fable Could Bring Mythos Out of the Security Lab

    #Anthropic#Claude Fable#Claude Mythos

    Mythos Preview as a frontier model with unusually strong coding, agentic, and reasoning capabilities. Its cyber strength follows from that wider ability: a model that deeply understands complex software can find bugs,

  2. Onyx brings team knowledge and AI search into one system

    #Onyx#Enterprise Search#Open Source AI

    Users can ask questions about company knowledge, create agents, search the web, and analyze data with a code interpreter. The tool is not new, but it remains relevant: many companies spread knowledge across wikis,

  3. VoltAgent brings observability to TypeScript agents

    #VoltAgent#AI Agents#TypeScript

    VoltAgent is an open-source TypeScript framework for AI agents plus a console for observability, automation, deployment, evaluation, and guardrails. That matters because many agent prototypes are easy to build, but hard

  4. Check Point warns AI is becoming an attack operator

    #AI Security#Check Point#Prompt Injection

    shift concrete: one developer allegedly used a commercial coding environment to create an approximately 88,000-line command-and-control framework in less than a week. That does not prove AI can build flawless malware

  5. SkillSpector scans agent skills before installation

    #NVIDIA SkillSpector#AI Security#Agent Skills

    NVIDIA's open-source scanner checks agent skills for prompt injection, data exfiltration, and risky permissions. It can run locally or in CI pipelines.

  6. Muse Glimmer brings a 30B AI agent to local computers

    #Meta AI#Muse Glimmer#Open Weights

    under the Apache 2.0 license. It is designed for local AI agents that call tools, work with code, and process both images and text. Meta says a quantized version fits in under 20 GB. That does not target ordinary office

  7. Browser MCP: AI agents control the real browser locally

    #Browser MCP#AI Browser Agent#MCP

    concrete AI tool because it solves a real problem for many agents: they can write code, but often cannot see whether the web interface actually works. Browser MCP brings agents closer to the real usage context without

  8. OfficeCLI gives agents access to Word, Excel, and PowerPoint

    #OfficeCLI#Developer Tools#AI Agents

    is about OfficeCLI is an open-source office suite for AI agents. It targets a very concrete problem: agents can often edit code well, but they struggle with Word, Excel, and PowerPoint files because they lack a reliable

  9. agent-browser gives AI agents a fast browser CLI

    #agent-browser#Vercel Labs#Browser Automation

    by Vercel Labs is a command-line tool that lets AI agents control a real Chrome or Chromium browser. It is not another chatbot and not a general model announcement, but a concrete developer tool for navigation, clicks,

Browse all AI news in the archive