#AI Agent
1119 related articles
AI Assistant 'dots' Real-World Test: It Automatically Saved Me $500/Year in Subscriptions
A user tested AI assistant dots and found it identified ~$500/year in redundant subscriptions — then autonomously handled customer service SMS conversations to cancel them.
DeepSeek Harness Full-Multimodal Desktop Setup Guide: Image Generation, Video, and Remote Control All in One
Step-by-step guide to building a full-multimodal DeepSeek Harness desktop: DSH Desktop client, Agnes free image/video generation, DeepSeek V4.1 Flash vision, AnySearch web search, and Anywhere remote mobile control.
Cloudflare OS: An AI Agent Workspace Built on Workers
Cloudflare open-sources cloudflare-os, an AI Agent Workspace built on Workers that integrates document creation, app building, and agent execution with enterprise systems. Already surpassing 10K GitHub stars.
Hindsight: Inside the AI Agent Memory System That Learns From Experience
Hindsight is an open-source AI Agent memory system that learns from experience. This article analyzes its design philosophy, how it differs from RAG, and its value for Agent developers.
HeyGen Open-Sources Hyperframes: Render Video with HTML, Built for AI Agents
HeyGen open-sources Hyperframes, a TypeScript tool that renders video from HTML — designed for AI agents to generate video content automatically. Already 56K+ GitHub Stars.
We've Been Using MCP Wrong: Its Only Real Value Is Authentication
A developer argues we're misusing MCP: its real value is on-demand authentication and permission isolation, not capability delivery. Here's when MCP actually makes sense.
Replit Agent's New Approach: Let the Model Decide, Not a Router
Replit Agent ditches model routers, letting frontier models autonomously orchestrate sub-agents and allocate tokens. Achieves Pareto-optimal results on DeepSWE and Terminal-Bench, beating sidekick architectures by 11–16 points.
Building an Agent Memory Layer with NVIDIA NeMo Agent Toolkit and S3 Vectors
Learn how to use Amazon S3 Vectors as a persistent memory layer for NVIDIA NeMo Agent Toolkit on Amazon EKS, demonstrated through a multi-agent investment research use case.
Adding Secure Web Search to Claude Desktop with Amazon Bedrock AgentCore
Use Amazon Bedrock AgentCore Gateway with AWS IAM Identity Center and Amazon Cognito to add secure, JWT-authenticated web search to Claude Desktop on Bedrock.
OpenAI Python SDK v3.22.0 Released: Beta Agents Gain Computer Use Capabilities
OpenAI Python SDK v3.22.0 adds computer use to beta agents, letting AI agents control GUIs to complete complex tasks. Learn what this means for developers.
AI Assistants in Your Texts: A Roundup of AI Agents You Can Reach by SMS
A roundup of AI Agents accessible via SMS — from general-purpose assistants to vertical tools for family, travel, and work. Explore the value and challenges of text as an AI entry point.
AI Agent in Action: Building a RealSense Vision App on Jetson in 77 Minutes
A developer tests an AI coding agent building three RealSense vision apps on Jetson Orin NX in 77 minutes — covering video streams, point cloud viewer, and DeepStream+YOLO object detection.
DSH Plugin in Action: Letting AI Agents Automate the Entire Antenna Design Workflow
A Bilibili developer shares the DSH plugin, which bridges CST and MCP to let AI Agents autonomously handle antenna modeling, simulation iteration, and S11 optimization.
Build an AI Coding Agent from Scratch: Create Your Own Command-Line Assistant with Gemini
Boot.dev's hands-on course teaches you to build a Python coding agent from scratch using Google Gemini Flash API — covering tool calling, agent loops, system prompts, and file safety guardrails.
Miso: An AI Travel Assistant That Books Flights and Hotels Over iMessage
Miso is an AI travel assistant embedded in iMessage. Users can search, book, and manage flights and hotels by simply sending a text. A deep dive into its conversational commerce logic, iMessage trade-offs, and trust challenges.
Human Approval in AI Agents Is in the Wrong Place: Do You Need Two Checkpoints?
Where should human approval go in an AI Agent workflow? A FastGPT user's reflection reveals that evidence review and action approval carry different risks — and blindly adding two checkpoints can cause approval fatigue.
AI Agent Beginner's Guide: The Essential Difference Between Agents and Chatbots
What's the difference between chatbots, building platforms, and AI Agents? Learn the 3 core components (brain, memory, tools) and 3 agent types to choose the right tool.
AI Agent for Beginners: What's the Real Difference Between Agents and Chatbots?
Beginner's guide to AI Agents: learn the real difference between agents, chatbots, and tool platforms — plus the three core components and three product types to choose from.
Android CLI New Skills Explained: How AI Agents Are Accelerating App Development
Google brings Device Streaming to Android CLI and launches AI Agent Skills including Play Policy Insights and Android Profiler to boost app compliance, performance tuning, and real-device testing.
How to Choose Your First Genie Agent for Maximum Impact
Learn how to choose your first Genie Agent for maximum business impact — covering high-frequency low-risk scenarios, measurable metrics, and Salesforce Agentforce selection logic.