全部 AI 动态

Building a Memory-Driven Agent with NVIDIA NemoClaw

Enterprise work spans messages, decisions, projects, and obligations that change over time. An AI agent that starts without this context must reconstruct it...

Frontier Reasoning Reaches the Edge: How to Deploy and Optimize Models on NVIDIA Jetson

Running reasoning and agentic AI at the edge has been harder than it needs to be. Until recently, models capable of multi-step reasoning were too large to run...

NVIDIA PAIR Virtual Inference Router Expands Available Compute on Your Local Network

AI agents are learning to do more by working together. A lead agent can break a complex task into smaller jobs and assign those jobs to specialized subagents....

Give Your Coding Agents a Memory You Own

The Economics of Agent Optimization: Context engineering for enterprise AI agents

AI cost optimization goes beyond model selection. Discover how context engineering in Microsoft Foundry helps lower AI costs by improving knowledge retrieval, tool selection, memory, and agent performance at scale. The post The Economics of Agent Optimization: Context engineering for enterprise AI agents appeared first on Microsoft Azure Blog .

Introducing agentic video understanding with Gemini

Building an Adaptive Agentic Cybersecurity System with NVIDIA Nemotron

AI is changing the pace of cybersecurity. Agentic systems can coordinate work and pursue complex objectives over long horizons. Security teams are beginning to...

MCP went stateless: Is your AWS MCP server deployment well-architected?

On July 28, 2026, MCP made its protocol core stateless, removing the initialize handshake and session header. This post maps the MCP 2026-07-28 specification to the AWS Well-Architected Agentic AI Lens, pillar by pillar, and shows why the stateless design lets you delete the sticky sessions and session stores your MCP servers needed on AWS.

AWS Weekly Roundup: Welcome DuckLabs to the team, Agentic Resource Discovery (ARD), and more (August 31, 2026)

The news that interested me the most last week was the DuckLabs acquisition. AWS has signed a definitive agreement to acquire DuckLabs, the Amsterdam-based company behind DuckDB, the popular open source analytical database that runs in-process and executes SQL directly against files like Parquet, CSV, and JSON. DuckDB stays open source under its independent foundation […]

BotBase for Operators: A clearer path to joining Cloudflare's directory of bots and agents

Bot operators now have a home in the Cloudflare dashboard to manage submissions. This update adds submission status tracking, submission editing, and a behavior model so operators can accurately declare how their bots use content.

Closing the AI agent trust gap with graduated autonomy

Most teams give AI agents either full access or read-only, leaving value unused or risk unmanaged. This post describes graduated autonomy, an architectural pattern in which agents earn expanded permissions through sustained reliability and lose them when performance degrades, built on Amazon Bedrock AgentCore, Amazon DynamoDB, and AWS CodePipeline.

Release v5.16.1

Release v5.16.1 This is a special release as we include GLM! (and a few small fixes) GLM-5.3-Flash GLM-5.3-Flash, the first natively multimodal model in the GLM-5 series. With 320B total parameters and just 18B active parameters, it outperforms GLM-5.2 across benchmarks and real-world workloads at one-tenth the price, while approaching Claude Opus 4.8 on coding and agentic benchmarks. GLM-5.3-Flash starts from a newly trained base model, with its architecture and training recipe redesigned around capability and efficiency. For the first time in the GLM series, we introduce a hybrid architecture combining sparse and linear attention, sharply r

AgentHands: Generating interactive hand gestures for spatially grounded agent conversations in XR

Human-Computer Interaction and Visualization

Say it once: introducing Bot Preference Sync

Cloudflare's new Bot Preference Sync automatically aligns your robots.txt file with your AI bot policies for Search, Agent, and Training. Easily manage which bots access your content without maintaining static files.

Build a unified AI agent architecture with DynamoDB and Bedrock

With native vector search in Amazon DynamoDB, you can store vector embeddings alongside your operational data in a single table. This post shows how to build a unified AI agent architecture where an Amazon Bedrock agent uses one DynamoDB table for both structured lookups and semantic search, with a DynamoDB Streams pipeline that keeps embeddings in sync.

How AgentFlo built AI sales agents with Amazon Bedrock AgentCore – Part 2

Part 2: how AgentFlo built trusted, reliable AI sales agents on Amazon Bedrock AgentCore and AWS serverless architecture. Learn the three-layer guardrails, grounded data foundation, and end-to-end observability behind a +12% net revenue uplift, plus what's next for real-time voice and server-side tool execution.

How AgentFlo built AI sales agents with Amazon Bedrock AgentCore – Part 1

Learn how AgentFlo built always-on AI sales agents on Amazon Bedrock AgentCore and the Strands Agents SDK. Part 1 covers three pillars of production-grade agents—velocity, standardization, and scalability—including recipe-based deployment, tool routing through AgentCore Gateway, and elastic, stateful commerce conversations.

AI-powered clinical trial eligibility and safety using Amazon Bedrock AgentCore

AI agents built on Amazon Bedrock AgentCore help clinical trial teams make fast, accurate enrollment decisions while keeping clinicians in control. This post shows how to architect an eligibility and safety screening agent using AWS HealthLake, AgentCore, and AgentCore Evaluations.

How Much Memory Does Your Agent Actually Need?

Consistency is the new latency: AI at the data layer

As AI agents move from chatbots to taking action, their reliability depends on the consistency of the data layer beneath them. This post examines how replication lag poisons an agent's context and shows how to match Amazon Aurora, Amazon DynamoDB, and Amazon Keyspaces replication models to each task's consistency requirements.

Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets

Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS

Release: v5.15.0

Release v5.15.0 New Model additions Meta Muse Glimmer Muse Glimmer, released today, is Meta’s new multimodal model, especially designed for agentic use cases. Distilled from Muse to 30B parameters, and released under the Apache 2.0 license, it can be deployed to local setups for privacy-aware applications such as coding, document analysis, personal assistants, Claw- or Hermes-like setups. Muse Glimmer is a dense 30B parameter model consisting of: 2B ViT-style encoder for vision (Perception Encoder) 28B parameter text decoder We're covering it in the following blogpost: http://hf.co/blog/muse-glimmer GraniteMoeSWA & GraniteSWA Links: Documenta

Meta is back with Muse Glimmer: local, agentic, multimodal, and open source

Runtime instances: persistent compute for production AI agents on Amazon Bedrock AgentCore

Announcing runtime instances in Amazon Bedrock AgentCore—persistent, managed EC2 infrastructure for production AI agents with multi-agent collaboration, GPU support, and sessions lasting up to 14 days.

Orchard: An open framework for scalable agentic AI

Orchard is an open-source framework for the research community to train and evaluate AI agents across task types. It reduces complexity while supporting strong performance from smaller models by enabling researchers to reuse the same infrastructure. The post Orchard: An open framework for scalable agentic AI appeared first on Microsoft Research .

Echoverse: Deep, evolving environments for computer-use agents

Computer-use AI agents struggle with multi-step workflows like email and customer support. Echoverse trains agents in realistic environments rather than simply providing more training tasks, helping them improve as the tasks, tests, and environments evolve. The post Echoverse: Deep, evolving environments for computer-use agents appeared first on Microsoft Research .

SymptomAI: Towards a conversational AI agent for everyday symptom assessment

General Science

Release v5.14.0

Release v5.14.0 New Model additions Inkling (fresh from Thinking Machines): 975B total, 41B active Add Inkling model #47347 by @molbap @Cyrilvallez @eustlb and @zucchini-nlp Inkling is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs. It is intended for use in English and other languages, and across multiple coding languages. The model is designed to be used by developers building AI- powered applications, including agentic and tool-use systems, coding assistants, chatbots, and retrieval-augmented generation systems, and is suitable for general-purpose conversational use, instruction-foll

Release v5.13.0

Release v5.13.0 New Model additions KimiK 2.5, 2.6, and 2.7 This release includes the architecture for Kimi 2.5 which is used by 2.5-2.7: Kimi K2.5 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration. The model was proposed in Kimi K2.5: Visual Agentic Intelligence and further improved in [Kimi K2.6: Advancing Open-Source Coding](Kimi K2.5: Visual Agentic Intelligence). Kimi K2.5 achieves significant improvements on complex, end-to-end coding tasks, generalizing robustly across programming langua