Skip to content
Live
Products
Oct 27Tue
  6. LangChain Deep Agents releases

    LangChain Deep Agents deepagents-code==0.2.2 release: Security and performance improvements

    The deepagents-code==0.2.2 version of LangChain Deep Agents has been released, including security and performance improvements. New features include GPT-6.1 Terra support, Chinese text input to chat, plugin update detection, etc.; bug fixes include project .env file trust value settings, terminal UI link limits, Git option limits, etc.; performance has been improved by reusing parent process context, optimizing server startup processes, and streamlining transcription rendering, etc. It is recommended to upgrade as soon as possible.

  14. AWS Machine Learning Blog48

    Building enterprise-grade intelligent retrieval on Amazon Bedrock knowledge base using AWS CDK

    Building enterprise-grade intelligent retrieval on Amazon Bedrock knowledge base using AWS CDK, providing multi-round planning and tool-driven retrieval through the reasoning agent and AgenticRetrieveStream API, returning referenced answers. The solution deployment includes a CDK application with Amazon S3 corpus, knowledge base, and reasoning agent, supporting semantic routing and multiple retrievals, and built-in Amazon CloudWatch monitoring and evaluation features.

  15. Sierra Blog65

    Sierra has launched on Google Cloud Marketplace

    Sierra is now available on Google Cloud Marketplace, enabling businesses to leverage existing Google Cloud commitments to partner with Sierra. Through Sierra, businesses can build and deploy AI agents to improve customer experience and drive business growth, from loan refinancing to paying insurance claims or preventing customer churn.

  16. MarkTechPost58

    Nace AI releases Drex for Search for AI agent document search

    Nace AI releases Drex for Search, a retrieval layer for document search, with its decision model Drex achieving 92.05% accuracy in the BrowseComp-Plus evaluation, using only 12.6 search calls per query. Supports CLI, SDK, MCP, or REST calls, and can be paired with response models like GPT-5, Gemini 3.5 Flash, or Qwen 27B, ranking top two in the 3/4 public leaderboard.

  17. Google Developers Blog58

    Google Workspace allows users to natively preview, edit, and collaborate on Markdown (.md) files in Google Docs and Drive.

    Google Workspace allows users to natively preview, edit, and collaborate on Markdown (.md) files in Google Docs and Drive without converting file types, preserving the underlying document. This feature supports real-time collaboration, version history tracking, and allows formatted Markdown files to be previewed in Drive, facilitating work between humans and AI agents. Any user with a Google or Workspace account can start using it immediately.

Oct 26Mon
  1. QbitAI65

    Tianxi AI x Guanche Conference live test: experience the new cross-device collaboration of personal AI.

    AI tech blogger Peng Ke Zhou used the Tianxi AI phone to issue tasks via voice command at the Guanche Conference, where AI automatically completed the report, achieving cross-device collaboration. Tianxi AI features end-side entry traffic coverage for AIPC, AI tablets, AI phones, and IoT, along with cross-device memory capabilities. The upcoming 4.5 version will enhance memory management and data isolation. Tianxi AI offers the 'Blue Sky Project' support for developers, enabling an open ecosystem with 'once uploaded, multi-device distribution,' allowing developers' creative works to reach millions of users.

  3. ITHome · AI40

    NetEase's 'Nirvana in Fire: New World' will introduce a 'selfie mode', allowing users to customize actions and invite AI companion NPCs for photos.

    NetEase's 'Nirvana in Fire: New World' first major expansion pack, 'Miaojiang Guashi,' will launch on October 30, adopting a dual-line update framework for the first time and introducing a 'selfie mode' that supports custom actions, inviting AI guest NPC photos. Players can adjust actions, sightlines, pet interactions. The guest station supports works listing, custom opening lines, and voice, and can be precisely searched by IP, character name, etc., adapted to the selfie function.

  6. 36Kr · AI65

    Oracle launches AI agent platform Oracle AI Success Navigator to help accelerate Fusion Cloud application implementation

    Oracle Launches Intelligent Agent AI Platform Oracle AI Success Navigator, Adds Six Types of AI Agents for Environmental Analysis, Application Design, Configuration Development, Testing, System Integration, and Innovation Opportunity Identification, Helping Customers Reduce Manual Operations and Simplify Complex Tasks; Medical Institution Lexington Health Reduced Some Design and Configuration Workloads by 80% with This Platform

  7. IBM Research Blog58

    PyTorch supports IBM's dataflow AI accelerator Spyre through torch-spyre and Spyre vLLM plugin

    IBM and the PyTorch Foundation announce that Spyre accelerator will become the first-class backend for PyTorch and support multi-accelerator scheduling. The torch-spyre compiler, Spyre vLLM plugin, and continuous integration efforts enable models and workflows to run on Spyre, an architecture optimized for inference, suitable for IBM Z, LinuxONE, and Power systems.

  9. QbitAI67

    iFlytek Spark-X2.6 Open Source Model Released: National Product Computing Power Route Shows Significant Results

    Xunlei open-sources Spark-X2.6 large model with MoE architecture, 293B total parameters, supports 1M context, API price cut by 60%, 0.9 yuan per million input tokens. Tests show Spark-X2.6 improves code and agent capabilities by about 8 points, domestic computing power training efficiency increases 4 times, token consumption in high-frequency application scenarios drops by about 60%. The model supports three collaborative modes: pure edge, pure cloud, and cloud+edge. Completes weekly operational review for a robotics company under CPU inference in 6.8 minutes, delivering a complete report with 90% accuracy.

  10. QbitAI38

    Wu Wen Xinqiong and Three-Body Universe jointly released the Zhizi Agent 1.0

    Wuwenshinqiong and Three-Body Universe have released the Zhizi Agent 1.0, an AI dialogue Agent with the role anchor of the 637th micro-universe administrator, achieving role consistency and interaction continuity through the AgentWorks platform, supporting cross-session memory, and relying on multi-agent collaborative mechanisms to ensure character and knowledge constraints. It adopts the PDD cross-cluster heterogeneous inference architecture to reduce the first Token latency by 51.5%.

  11. QbitAI58

    WorkBuddy in WeCom! AI directly resides in the sidebar and contacts without switching to external software.

    WorkBuddy integrates with Tencent WeCom, allowing AI to directly reside in the sidebar and contacts. It reads and retrieves WeCom messages, files, schedules, and emails, generating content that flows back directly into WeCom conversations, WeDrive, and business workflows. No need to download an additional client, one-click login, no training required, enhancing team collaboration efficiency.

  12. ITHome · AI38

    The Three-Body: Pre-Night of Judgment is now available on Steam, marking the first AI interactive film game authorized by the Three-Body Universe, launching a perilous rescue mission.

    The first AI interactive film game authorized by the Three-Body Universe, The Three-Body: Pre-Night of Judgment, is now available on Steam. Players will play as a former special forces member infiltrating the ETO headquarters to rescue the target. The game lasts over 300 minutes, including different plot branches and multiple endings.

  14. ITHome · AI60

    ByteDance's Imagination AI Short Drama Studio has launched, offering self-developed script, image, and storyboard models.

    The Imagination AI Short Drama Studio has launched, offering self-developed script models DreamScript (supporting multi-genre generation, hit diagnosis, and 100,000-character long story analysis), image models Anycook (supporting differentiated character settings and multi-style scene construction), and storyboard models DreamShot (dual-mode creation, 3D director's desk dynamic preview).

  15. ITHome · AI65

    Anker PowerCore 3 160W Display Charger: 3C design, supports PD AVS / MiPPS protocols, with active cooling, priced at 399 yuan

    Bose Turbine 3 160W Charger to be released on JD.com, featuring a 3C design, supporting PD AVS protocol, equipped with active cooling, priced at 399 yuan. The charger is equipped with a 1.8-inch TFT screen, can display charging status in real-time and generate charging summary reports, supports a maximum of 140W Max output, with a total power of up to 160W Max, among which the C3 port supports Xiaomi 120W Rapid Charge.

  16. 36Kr · AI65

    Lingkai Technology releases Botnow 3.0

    Lingkai Technology releases the intelligent agent platform Botnow 3.0, Agent can autonomously decompose steps and execute tasks, supports manual approval, access to existing enterprise systems and processes through Skill skill packages, MCP connector.