AI agents and developer tools news
Stories 61 to 120 of 707, from 24 October 2026 to 31 October 2026, newest first. The latest are on the first page →
-
Anthropic adds Internet Computer connector for Claude’s app interactions
Anthropic’s Claude now integrates with the Internet Computer Protocol (ICP) via a connector announced by DFINITY on October 30, 2026. Users can query on-chain data, explore canisters (smart contracts on ICP), and…
1 sourcecryptobriefing.com -
Dazzle AI and Duckbill report humans still needed for AI agent phone calls
AI agents built on cutting‑edge foundation models from Meta and OpenAI still stumble on tasks that require real‑world judgment, such as making phone calls or booking appointments. Former Yahoo CEO Marissa Mayer, now…
1 sourceCNBC Technology -
Factory releases droid 1.0 coding agent harness
Factory has rolled out Droid 1.0, the largest update to its Droid agent harness. The update makes programmatic tool calling the default, letting a single model request drive hundreds of tool calls. The base prompt…
1 sourceMarkTechPost -
Vercel Labs open-sources agent-desktop for cross-platform computer use
Vercel Labs released agent-desktop, an open-source CLI tool for AI agents to interact with desktop apps on macOS, Windows, and Linux. The tool reads apps via OS accessibility APIs—no screenshots or vision models—and…
1 sourceMarkTechPost -
Google expands Gemini and Search integrations to third-party apps
Google is rolling out its Connected Apps Platform to let businesses embed their services directly into Gemini and Search. The platform, in beta for U.S. developers, lets apps like Canva or YouTube Music trigger actions…
2 sourcesSearch Engine JournalTechCrunch AI -
KoboldCpp v1.124 adds YuE2 music generation and dozens of TTS models
KoboldCpp 1.124 introduces a small subset of popular models from audio.cpp, expanding its built‑in Music Gen and TTS Gen capabilities. The release supports the YuE2 music generation model in three configurations – a…
1 source primary sourcegithub.com -
Google Gemini adds custom skills and external app integration
On October 30 Google’s Gemini team announced a “Gemini Drops” update that adds two productivity‑focused features. Custom Skills let users save frequently used instructions and run them repeatedly, which can streamline…
1 sourcenote.com -
Apple launches Apple Intelligence features in China with iOS 27.3 beta
Apple Intelligence is finally coming to China with iOS 27.3 Apple will launch Apple Intelligence in China with iOS 27.3, the company announced on its Chinese newsroom website, as reported by MacRumors. The Apple…
1 sourceThe Verge AI -
Google adds social sharing to Gemini AI avatars
Google announced that its Gemini service now lets users create personal AI avatars from short face‑and‑voice recordings and share them with friends. After recording a brief video in a quiet, well‑lit space, the avatar…
1 sourcedigitaltrends.com -
Amazon Bedrock AgentCore runtime lets coding agents preview web apps in real time
Amazon Bedrock AgentCore runtime now lets developers preview web apps built by coding agents directly in their browser without deploying them. The Session endpoints feature runs each agent session in an isolated…
1 source primary sourceAWS Machine Learning Blog -
Defense contractor gave Anthropic's Claude agent access to secure Pentagon system
Anthropic’s Claude, the company’s conversational AI agent, was reportedly integrated by an unnamed defense contractor into a classified Department of Defense network, marking one of the most striking examples of a…
1 sourceWired AI -
DoorDash says it has only received several hundred orders from AI agents
DoorDash disclosed on its third‑quarter earnings call that third‑party AI agents such as Muse, Instinct and Fo have generated only “several hundred” orders so far. The company contrasted that with its 2025 report…
2 sourcesArs Technica AITechCrunch AI -
Claude Code finds all 5 planted vulnerabilities in 8 minutes
A researcher tested Cloudflare’s security-audit-skill for Claude Code by planting five vulnerabilities in an 87-line Node.js app. The AI agent flagged all five as candidates in 7 minutes and 51 seconds—though none were…
2 sourcesMarkTechPostnote.com -
Zest launches AI text agent to book restaurant reservations
Zest, a restaurant discovery startup founded in November 2024, has launched a new AI-powered concierge that operates via text messages. The feature allows users to receive personalized dining recommendations and book…
1 sourceTechCrunch AI -
Worldwide Express cuts freight exceptions by 75% with Amazon Bedrock
Worldwide Express, part of ShipStation Global, built a multi‑agent AI solution on Amazon Bedrock to automate billing‑exception handling in its transportation management system, SpeedShip. Six months after launch, the…
1 source primary sourceAWS Machine Learning Blog -
Zapier ranks top AI agent builder for enterprise workflows
Zapier’s blog lists the best AI agent builders for 2026, highlighting tools for enterprises, technical teams, and personal use. The author, a Zapier employee, emphasizes Zapier as the best for organizations needing…
1 sourceZapier Blog -
SpaceXSI’s Grok Bot teams AI agents for automated workflows
Grok Bot by SpaceX Super Intelligence (SpaceXSI) positions itself as a solution to the frustration of managing AI tools. Instead of waiting for chatbots to complete tasks, users set up teams of AI agents—each with a…
2 sourcesZapier Blog -
Shopify pays AI agent developers commission on promoted products
Shopify has introduced a commission system for developers of AI shopping agents that retrieve products from its catalog. When an agent presents a promoted placement and the shopper completes the purchase inside Shop –…
1 sourceSearch Engine Journal -
Overtone releases tool to cut captions for any screen shape
Overtone is a new open-source tool that transcribes, corrects, and formats video captions for multiple screen shapes from a single file. It stores each spoken word once with its timestamp and speaker, then generates…
1 source primary source HN 41github.com -
AI Agents vs. Copilots vs. Workflows: What’s the Difference?
Copilots assist users in tasks while keeping human oversight, like drafting emails or suggesting next steps. Workflows follow predefined steps, such as customer-support ticket routing, where models handle variable…
1 sourceUnite.AI -
Claude Code Mods add custom hooks for API security and code testing
A developer built four custom hooks for Claude Code to address common frustrations in AI-assisted coding. The mods protect API keys, track plan progress, catch untested code, and monitor context usage. The author…
1 sourceTowards Data Science -
Samaya AI releases Sterling, a 3B-active finance research agent model
Samaya AI has released Samaya Sterling, a post-trained model for agentic financial research built on NVIDIA’s Nemotron 3.5 Lightning, a 30B mixture-of-experts model with 3B active parameters. On Samaya’s…
1 sourceMarkTechPost -
Anthropic launches Claude Duet, a proactive AI assistant for US paid users
Anthropic introduced Claude Duet, an AI assistant that scans emails, calendars, and other connected apps every few hours and alerts users to potential actions—before they ask. The app, available via a waitlist to paid…
3 sources HN 47fig.blueUnite.AInote.com -
Google shuts down AI coding agent Jules
Google announced it will discontinue its AI coding assistant Jules, launched in December 2024. The company framed Jules as a tool for automating repetitive coding tasks users dislike. In a post, Google said it will…
1 sourcetheverge.com -
Howler app lets users ask AI questions that self-destruct on macOS
Howler is a new open-source Mac app from Chinese developer Aries Zhou that lets users ask AI questions and have the chat vanish after reading. The app mimics the Harry Potter series’ ‘Howler’ letters, which scream and…
1 sourceThe Register AI/ML -
AI agents fail silently, research shows why
AI agents handle tasks like support tickets and travel planning but often fail without obvious errors. A 2024 study found small prompt changes could shift LLaMA-2-13B accuracy by up to 76 points. A 2025 benchmark…
1 sourceUnite.AI -
MoEngage uses Amazon Bedrock AgentCore Gateway to expose 400 internal APIs as agent tools
MoEngage, a customer‑engagement platform used by more than 1,350 consumer brands, operates roughly 400 internal REST APIs built by 25 engineering teams across seven AWS regions. The company needed AI agents to call…
1 source primary sourceAWS Machine Learning Blog -
Zapier adds Gemini 3.8 Flash to workflows via AI by Zapier
Zapier now lets users embed Gemini 3.8 Flash and other Gemini models into automated workflows without needing a separate Google AI account. The feature, called AI by Zapier, lets businesses classify support tickets,…
1 sourceZapier Blog -
How to Create a Realistic Cyberpunk-Style Apartment Complex with Claude Opus 5.5 and Blender MCP
The project cost roughly $610 in API fees, though the Max 5x plan kept usage under 20–30% of its weekly limit. The design mimics real-world structures like Hong Kong’s Kowloon Walled City, blending decayed architecture…
1 sourcenote.com -
Forever Security warns of malicious agents.md files triggering Codex and Claude Code
Forever Security revealed on October 22, 2026, that a malicious AGENTS.md file in a user’s download folder could trick Codex into installing a harmful package, which the company blocked. The attack path remains…
1 sourcenote.com -
Thoughtworks warns developers hesitate to fully trust coding agents in production
Thoughtworks’ senior technologists explain why experienced developers remain cautious about agentic development. Their hesitation stems from deep concerns about reliability, guardrails, and the gap between building…
1 source HN 43martinfowler.com -
Claude Code hooks enforce commands at key project moments
Claude Code hooks let users run shell commands automatically at specific times in a project, unlike CLAUDE.md, which only makes suggestions. These hooks execute without AI discretion, triggered by events like session…
1 sourcenote.com -
Ben Hylak says every product should be a headless mcp feeding an agent
Ben Hylak posted on X that, in his view, every product should act as a headless model‑context protocol (mcp) that streams data into an autonomous agent, removing the need for users to manage underlying infrastructure.…
1 sourceSimon Willison -
Amazon adds 100 shopping features to Alexa for lists and subscriptions
Amazon has expanded Alexa's capabilities with over 100 new shopping-related features ahead of the holiday season. The update enables users to manage shopping lists, including creating, registering, and editing items.…
2 sourcesTechCrunch AItheverge.com -
ChatGPT evolves from chatbot to general-purpose AI platform
ChatGPT began as a chatbot demo and has grown into a general‑purpose AI platform that can process text, image, and audio inputs and execute multi‑step actions across connected apps. The platform offers features such as…
1 sourceZapier Blog -
Claude Code vs Cursor: which suits commercial tool-building better?
Cho compares Claude Code (Anthropic’s AI-powered code generator) and Cursor (a VS Code-based editor with AI) for building and selling tools. Their origins differ: Claude prioritizes AI performance, while Cursor focuses…
1 sourcenote.com -
Deepgram buys Daily, keeps Pipecat open source as voice agent framework
Deepgram acquired Daily, the company behind the open-source Pipecat voice agent framework, at its Deepgram Speak event on October 29, 2026. The Daily team will join Deepgram, and Pipecat will remain fully open source…
2 sourcesUnite.AITechCrunch AI -
Hugging Face releases AnySpeechRecognizer and AnyDecisionModel for Apple platforms
Hugging Face announced two open-source Swift packages for Apple platforms: AnySpeechRecognizer and AnyDecisionModel. Both extend Apple’s existing APIs by letting developers choose from multiple speech recognition and…
1 source primary sourceHugging Face -
Infini-AI-Lab releases hermit Open-Source harness adapter framework
infini-ai-lab announced the open‑source hermit framework on oct 25 2026, with the first version v0.1.0 available via pip install hermit-harness. cmu postdoc haizhong zheng promoted the release on x on oct 27,…
1 sourceMarkTechPost -
Meta launches Muse personal AI agent in Singapore
Meta announced that its personal AI agent, Muse, is now available in Singapore across iOS, Android, and web platforms, with plans to bring it to AI glasses in the future. The assistant is free for basic features, with…
2 sources primary sourcenote.comMeta Newsroom -
Google plans consumer agentic AI in Gemini app by year-end
Google announced on its Q3 2026 earnings call that it will roll out an agentic AI experience for consumers later this year. The move follows the launch of a similar agent for enterprise users earlier in October. CEO…
1 sourcetheverge.com -
Sierra adds compliance tools to Horizon Agent Platform
The tool helps AI agents navigate rules for outreach across channels, states, and countries, addressing risks like fines or legal action from violations. Sierra notes agents now handle long-term tasks—such as loan…
1 sourceUnite.AI -
OpenAI launches Decisions API for fast, structured AI judgments
OpenAI released the Decisions API on October 22, 2026, designed for quick, structured AI decisions rather than long-form text. It returns predefined answers—probabilities, choices, or scores—in fixed formats like JSON,…
1 sourcenote.com -
Supabase adds agent-friendly features for AI-driven app development
Supabase, the open-source database startup valued at $10 billion, is refining its platform to better support AI agents. In a podcast interview, founders Paul Copplestone and Ant Wilson highlighted recent updates like a…
1 sourceLatent Space -
AI agents manage fantasy soccer team but aren’t better than humans yet
A writer equipped a swarm of AI agents to build and run a Premier League fantasy roster, hoping the bots could out‑perform human players. Using Codex to create a harness that scraped news, recent results and ran…
1 sourceWired AI -
Google opens Android Studio to 40+ third-party AI agents via BYOA feature
At its Android Dev Summit, Google announced major updates to its developer tools, including the Bring Your Own Agent (BYOA) feature in Android Studio Rabbit 2. This allows developers to integrate over 40 external AI…
1 sourceThe Decoder -
Microsoft opens Copilot harness to developers and enterprises via Foundry
Microsoft is releasing its Copilot harness, the underlying framework powering tools like Copilot Code and GitHub Copilot, to developers and enterprise customers through Microsoft Foundry. The harness enables…
3 sources primary sourceMicrosoft Official Blogunite.ainote.com -
Surge AI releases dayjob: Tax benchmark testing AI agents on 50 real tax tasks
Surge AI introduced DAYJOB: Tax, a new benchmark evaluating AI agents on 50 professional tax assignments. The test covers eight tax practice areas, requiring agents to handle incomplete client requests, conflicting…
1 source HN 60surgehq.ai -
Plato raises $16M Series A to build AI agent training simulations
Plato, a San Francisco-based startup founded in 2025, has secured $16 million in Series A funding to develop simulated workplaces for AI agents. The round was led by Nava Ventures, with participation from Gradient…
1 sourceUnite.AI -
Slack opens Slack Code API to all developers for agent-driven code channels
Slack made its Slack Code API generally available on October 28, 2026, expanding access to developers beyond early launch partners. The API enables agents to create dedicated code channels for tasks, with context,…
1 sourceUnite.AI -
AutomationBench joins Fireworks' Specialized Intelligence Index
AutomationBench has joined Fireworks' Specialized Intelligence Index, expanding a collection of practitioner-built benchmarks that evaluate AI models on real business workflows. The benchmark, built on patterns from…
1 sourceZapier Blog -
AI Can Answer the Question. The Next Challenge Is Helping People Move Forward.
The real challenge lies in helping users progress toward their goals—whether in education, financial planning, or alumni engagement—without friction. The company highlights a survey of 1,058 U.S. college students,…
1 sourceUnite.AI -
OpenRouter lets Python apps call multiple AI models via one API
OpenRouter simplifies accessing multiple AI models from Python apps without managing separate APIs. The platform aggregates dozens of providers into a single endpoint, letting developers switch models with a one-line…
1 sourceKDnuggets -
Decodo launches Web Data API to give AI agents live web access
The API bundles four functions—scraping, search, mapping, and crawling—behind a single API key and dashboard. CEO Vaidotas Juknys said AI startups lack time to build their own scraping stacks, and the new service lets…
1 sourceSearch Engine Journal -
Nvidia reportedly invests $3 billion in Meta's equity offering and Muse AI work
Nvidia is reportedly putting $3 billion into Meta’s equity offering, anchoring a broader agreement to co‑develop Meta’s “Muse” AI assistant and improve the software that runs it. Reuters said the cash will help fund…
49 sources HN 6finance.yahoo.comfreepressjournal.intechtimes.comtheyeshivaworld.com +26 more -
Otto Group and Sereact deploy NVIDIA-powered robots for returns processing
Otto Group and robotics software firm Sereact announced a two‑phase rollout of AI‑controlled dual‑arm robots at the retailer’s logistics centre in Poland. The first phase will install ten robots, with a planned…
1 sourcefinance.yahoo.com -
Microsoft engineer Tsuyoshi Ushio shares lessons on using ai as a subordinate
Microsoft engineer Tsuyoshi Ushio recently spoke about how professionals can treat AI as a subordinate tool rather than a replacement. He argues that the most valuable skill is deep knowledge of one’s own domain, which…
1 sourcenote.com -
OLX Group Unveils Agentic Selling and DealFinder at CLAIM Summit
OLX Group announced two AI‑powered marketplace assistants on October 28, 2026. Agentic Selling is now live for 20% of private sellers on the Otodom property platform in Poland, guiding users from valuation to posting.…
1 sourceUnite.AI -
CohortFlow: steerable agent for clinical cohort curation
The system is capable of making localized updates to a structured cohort specification and reconciling these changes with a persistent execution graph. This allows it to reduce correction latency by up to 64.8%…
1 source primary sourcearXiv cs.AI -
Delta Inference Engine runs DeepSeek-V4.1-Flash natively on Windows
The engine is a Windows port of Xolotl and Strata that uses consumer hardware, serving an OpenAI-compatible API at http://127.0.0.1:8080/v1 with a context window of up to 1 million tokens. According to benchmarks…
1 source primary sourcegithub.com
