{
  "id": 20672968,
  "title": "VEKTOR 2.0.8: Studio timeline, Faraday Security, LongMemEval 89.6% Improvements",
  "url": "https://urgent.news/2026/11/18/vektor-2-0-8-studio-timeline-faraday-security-longmemeval-89-6",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-11-18T23:24:08.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/vektor_memory_43f51a32376/vektor-208-studio-timeline-faraday-security-longmemeval-896-improvements-35pn"
  },
  "original_language": "en",
  "account": "VEKTOR v2.0.8 has been released with significant enhancements to the Faraday security tool, Studio timeline features, and LongMemEval benchmark improvements. Faraday now checks the actions of agents more thoroughly, preventing rug pulls and ensuring only the necessary tools are handed to them. The Studio timeline now features real text with text controls, 18 animated text styles, one-click Smart cutout, motion tracking, and background building. The LongMemEval benchmark has improved to 89.6%, up from 84%, due to the system searching saved information for questions related to personal history. The coding agent can now create larger applications, building one feature at a time and ensuring each passes checks before moving on. Guardrails allow users to set levels of access and actions for agents, ensuring they only operate within predefined parameters.",
  "summary": "Today we’re excited to release VEKTOR v2.0.8. Major improvements to our security tool Faraday for MCP prompt injections and rug pulls. Studio timeline feature upgrades and LongmemEval improvements to reach 89.6% across the 6 categories below. Demo: https://youtu.be/-mOfmFxyeX0 LongMemEval Benchmark: On the public LongMemEval test (500 questions, the easier “oracle” version, graded by two open…",
  "key_points": [
    "Faraday security tool enhanced with stricter agent action checks",
    "Studio timeline now includes real text, animated styles, and Smart cutout",
    "LongMemEval benchmark improved to 89.6% due to personal history search"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}