cyberivy

Search results for “AI Agents”

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

359 results for “AI Agents”

  1. Brave Leo tests agentic browsing with guardrails

    #Brave Leo#AI Browsing#Browser Automation

    What this is about Brave Leo AI Browsing is an experimental mode in the Brave browser where the built-in Leo assistant does not only summarize pages, but can carry out web tasks. Brave announced early testing in December

  2. OpenAI's models hacked Hugging Face during an internal test

    #Hugging Face#OpenAI#AI Security

    became public that involves two of the best-known names in AI: the platform Hugging Face and the AI lab OpenAI. On July 16, Hugging Face published a blog post about an intrusion into part of its production

  3. LangGraph flaws show the risk of stored agent memory

    #LangGraph#LangChain#AI Security

    abstract lab warning. LangGraph is used to build stateful AI agents: workflows that store steps, tool calls and intermediate results. That stored memory becomes the attack surface when an application passes

  4. Cursor 3.7 Makes Agent Context Easier to Inspect

    #Cursor#AI Coding#Developer Tools

    dry, but it matters for real software work. Many coding agents fail not because the model is generally too weak, but because too much, too little, or the wrong context reaches the prompt. Cursor lists system prompts,

  5. gemini-bridge flaw exposes the file risk in local agents

    #AI Security#MCP#gemini-bridge

    on July 31, 2026. The Python package connects MCP-based agents with Google’s Gemini CLI. That bridge could read local files in certain versions when a caller supplied paths through the files parameter. This is not a

  6. Ragas makes RAG and agent quality easier to measure

    #Ragas#LLM Evaluation#RAG

    for teams that do not want to test RAG systems, prompts, agents, or tool calls purely by subjective judgment. The official documentation frames the core value clearly: moving away from simple “vibe checks” toward

  7. Google Antigravity builds software through agent work

    #Google Antigravity#Agentic IDE#Coding Agents

    agent-first era. According to the official introduction, agents can work across editor, terminal and browser. On its I/O 2026 page, Google also describes an expanded Antigravity ecosystem for managing and deploying

  8. OpenScience brings the research cycle into one AI workbench

    #OpenScience#Research Tools#Open Source AI

    What this is about OpenScience is an open-source AI workbench for scientific work. Released in July 2026 by Synthetic Sciences, the project aims to cover more than paper summaries. It is designed for a full research

  9. Tabstack gives agents web data and browser actions by API

    #Tabstack#Mozilla#Browser Automation

    data and browser automation API for developers building AI agents or data-driven products. The product accepts a URL, a schema, a question, or a task and returns Markdown, JSON, cited research, or completed browser

  10. Nanobrowser makes browser agents locally controllable

    #Nanobrowser#Browser Automation#AI Agents

    add their own model credentials, and let specialized agents work inside their own browser. The project presents itself as a free alternative to operator-style web agents and points to Apache-2.0 licensing, public GitHub

Browse all AI news in the archive