#产品更新

Show HN: Browserr – An MCP-first browser for AI agents (one Rust binary)

Browserr is an MCP-first browser for AI agents built on the Servo engine, distributed as a single ~120 MB Rust binary with a 22-command JSON-over-loopback protocol and 42 MCP tools. It emphasizes agent-first design—structured extraction, stable refs, fail-closed interception, built-in adblock, and evidence logging—plus human handoff via a native window with headed:true. It is free and open source, with packages for Windows x64, Linux x64/ARM64, and macOS Apple Silicon, requiring Python 3.10+ for the SDK and MCP server.

Show HN: Open-Source Version of Cyclon: Phone where AI is the interface?

OpenCyclone is a free, open-source AI agent for stock Android that reads your apps on a hidden display, decides what to tap, and asks for approval before any irreversible action. It requires Android 12 or later, a one-time setup script on a computer, and a model provider account, and is built and tested on a Pixel 7. The project is Apache-2.0 licensed, unaffiliated with Cyclon or Y Combinator, and its benchmark results are not yet published.

ChipAgents – The agentic foundation for semiconductor design (AI for IC design)

ChipAgents presents itself as an agentic foundation for semiconductor design, offering full-flow autonomy for digital and analog chip design and a path to tapeout backed by Meet IC-star. The page cites 200+ semiconductor enterprise deployments, 50% design cycle reduction, a 20,000+ global user community and 40% annual LLM spending savings, and includes a founder story video with Founder & CEO William Wang. It also states enterprise-grade security, including SOC 2 Type II, with sensitive design IP kept in place.

Anthropic Upgrades Claude Code Projects to Run Parallel AI Workers Hands-Free

Anthropic updated Claude Code Projects with proactive coordinator messages, read-only thread sharing, reminders, /btw and /fork branching commands, and improved artifact navigation, reducing the monitoring needed when several cloud sessions run in parallel. Each project is a long-running conversation whose coordinator assigns work to threads, each an independent Claude Code cloud session with its own repository copy and Git branch. The public beta, launched September 17 for waitlisted Pro and Max subscribers, has no separate fee but draws on existing Claude Code allowances, with a 200-new-thread daily limit per account.

Doc-foundry – AI writes Security detection rules, then proves they work

Doc-foundry is an adversarial multi-agent detection-engineering workflow (LangGraph, Pydantic, FastMCP, Claude) that turns a threat such as a CVE, CISA KEV entry, incident writeup or ATT&CK technique into a validated first-version Sigma detection rule, a threat report with round-by-round convergence history, and a proof bundle containing a positive corpus, benign baseline, adversarial mutation set and a computed coverage label (real-coverage/brittle/broken) with FP/FN numbers and a reproducibility hash. Four LLM agents (Threat Analyst, Blue Detection Engineer, Telemetry, Red-Team Adversary) propose, while a deterministic referee handles FP/FN evaluation, adversarial evasion, the coverage verdict, red-team verification and the deployment gate, so the same input yields the same verdict and hash. A second pipeline, the Review Chain, runs draft → Red Team → revision → SOC Lead → final rule and produces a reviewed but explicitly unvalidated rule with the full trail of findings that shaped it.

QuAIA: An open-source team of AI agents that handles the whole test process

QuAIA (Quality Assurance with Intelligent Agents) is an open-source multi-agent system under AGPL-3.0 in which an orchestrator coordinates specialized agents for requirements review, test design, UI and API test execution, and defect reporting, connected to tools like Jira, Confluence, and Zephyr via the A2A and MCP standards. The UI agent operates keyboard and mouse from the screen without test scripts, runs on multilingual models, and learns workflows from expert demonstration, with self-hosted models and in-infrastructure deployment supported. Several features, including agent memory, self-hosted model support, and desktop support, are marked as prototypes.

0.171.0-alpha.5

This GitHub Changelog entry is titled "0.171.0-alpha.5" and lists only the site's navigation menu, covering Platform, Copilot, Actions, Code Quality, Codespaces, Secure Code, Secret Protection, Build with Copilot, Integrations, Changelog, Add-ons, and Pricing. The material contains no details about the release itself.

Faster Scientific Simulations with New FP64 Algorithms in NVIDIA cuBLAS

Many scientific simulations, from molecular chemistry to materials science, spend most of their execution time on high-precision dense general matrix multiplications (GEMM), called DGEMM for real 64-bit floating-point numbers and ZGEMM for complex 64-bit floating-point numbers. cuBLAS is widely used by HPC and AI applications to accelerate GEMM and other Basic Linear Algebra Subprograms operations.

Advancing science & engineering with Antigravity’s /teamwork

Google describes how multi-agent workflows in Antigravity's /teamwork, built on Gemini 4 models, produced results on open problems including a full proof of the 2013 Courtade–Kumar conjecture formalized in Lean 4, a machine-checked formalization of the Weil conjectures spanning about 1.8 million lines of Lean, and 95% top-1 accuracy on molecular structure determination from NMR data. The post also reports engineering gains such as a memory-safe Rust rewrite of the Zircon microkernel adding about 800,000 lines, a libgav1 Rust port that became 20-30% faster than the original C++, and fleet-wide memory savings surpassing initial estimates of 1 PiB. Google says the tools are available to external researchers and developers in Antigravity today, with 10,000 academic researchers offered six months of free access to its highest usage tier.

Introducing Forward Deployed Creatives in ElevenCreative

ElevenLabs introduces Forward Deployed Creatives, creative professionals who work with teams in ElevenCreative or produce finished creative end to end, addressing brand consistency, fragmented tools, and creative control. Enterprises can enable their own creative team on the platform, build reusable workflows with Forward Deployed Engineers and Creatives, or extend their team with end-to-end creative services from strategy to localized ads. Localized content is reviewed by trained linguists and audio professionals, and ElevenLabs also offers end-to-end production services for dubbing, voiceovers, subtitles, audio description, and custom brand voices.

v2.1.325

Claude Code v2.1.325 fixes a zstd response-decoding security issue and a broad set of bugs across permissions, sandboxing, MCP, subagents, sessions, sign-in and Windows/Linux behavior. It also changes defaults so sandboxed Bash commands follow the normal permission flow unless sandbox.autoAllowBashIfSandboxed is set, and adds VS Code prompt suggestions and a Console sign-in that creates no API key.

Run GPU-Powered Black Hole Interferometry with NVIDIA cuPhoton

NVIDIA describes the challenge of black hole imaging: M87*'s observed ring spans just 42 microarcseconds, and since black holes emit no light, telescopes capture radio emission from superheated gas swirling outside the event horizon, with the black hole's gravity bending light paths to shape the bright ring. The material introduces running GPU-powered black hole interferometry with NVIDIA cuPhoton.

Rainshare: Mutual aid for AI coding plans and usage limits

Rainshare is presented as a mutual aid service for AI coding plans and usage limits, according to its site at rainshare.dev. The item was posted to Hacker News with 1 point and no comments.

Show HN: Free AI Image Gallery

Skynett Images is a free collection of AI-generated portraits, fashion, travel, beach, arts and fantasy scenes that users can browse by category, save favorites on their device, and download in PNG, JPG or WebP. The images may be used and edited for free in personal and commercial projects, with credit appreciated but not required, though users may not present them as real photos, use them to impersonate or deceive, create hateful, harmful, sexual or illegal content, or resell them as-is as their own stock collection. Where AI content must be labelled, such as under India's IT Rules, the images should remain labelled as AI-generated, and they are provided as is without warranty.

ChatGPT Wallet lets OpenAI’s Dots agents make purchases for you

OpenAI is rolling out ChatGPT Wallet for ChatGPT Pro subscribers in the US aged 18 and older with a US billing address and eligible US-issued American Express, Chase, Mastercard and Visa cards. Dots agents can use the wallet to buy things in response to prompts, but they check in with the user before checkout, and every purchase requires biometric verification such as Face ID or a fingerprint scan. OpenAI says card details are replaced with a payment token, and it expects users will eventually be able to delegate purchases entirely by setting parameters like spending limits, purchase categories or time periods and pre-approving them.

Kitesurf is now open source

Cloudflare has open-sourced Kitesurf, its stateless browser for AI agents that runs entirely on Workers, under the Apache 2.0 license on GitHub. The repository includes the engine, PageScript, PageRenderer, and CLI, built on Rust-to-WebAssembly projects like Blitz, Stylo, Boa, and Linebender libraries, and supports the Chrome DevTools Protocol for clients such as Puppeteer. Developers can run it locally or deploy their own instance to Cloudflare Workers, which requires a Workers Paid plan because it uses Dynamic Workers.

OpenAI rebuilt AI shopping from scratch with ChatGPT Wallet

OpenAI has launched ChatGPT Wallet, which lets AI agents pay on behalf of users, after scrapping its earlier Instant Checkout feature for being insufficiently flexible. At launch it is US-only through Dots, requires a ChatGPT Pro subscription and an eligible US bank card, and uses payment tokens from American Express, Mastercard and Visa so neither the agent nor the store sees real card details. OpenAI also released a Commerce Partner Playbook to help merchants adjust firewalls and work with payment providers so agent-driven purchases go through.

OpenAI launches ChatGPT Wallet, AI agents pay for purchase

Reuters reports that OpenAI launched ChatGPT Wallet, a feature that lets AI agents pay for purchases. The article link is https://www.reuters.com/technology/openai-launches-chatgpt-wallet-letting-ai-agents-pay-purchases-2026-11-13/.

Featured coverage of this story: 《Introducing ChatGPT Wallet》

The Green Agent POV: Formulating the Fix for an Exposed Container with Sensitive Data Access

Wiz describes how its Green Agent investigated a critical Issue involving an internet-facing EKS container with CVE-2026-111497 ("Broccoli2Shell"), an overprivileged IAM role, and S3 buckets holding over 5,000 unmasked PII and credit card records. The agent validated each link in the attack path, traced runtime assets back to their Dockerfiles, Terraform, and GitOps manifests to identify owners, and produced Mitigate and Fix plans while rejecting strategies like deleting the ingress that would cause a production outage.

Show HN: AI Juggler – Orchestrate your desktop Claude and Codex apps

AI Juggler is a free, open-source (MIT), local-first macOS app that shows which AI coding sessions are open across the Claude app, terminals, the Codex app and Cursor, lets you jump to any of them in one step, and reports usage and limits per account. It works with tools you already use, never proxies their traffic, never signs in for you and never stores your credentials, and it requires macOS 14 Sonoma or later plus at least one of Claude Code or Codex installed and signed in.

0.171.0-alpha.4

This page is a GitHub Changelog entry titled "0.171.0-alpha.4," but the supplied material contains only site navigation and product menu text, with no details about the release itself.

Oxford spent years studying how women build companies. Now this research can speak.

Oxford Saïd Business School's Inspiring Female Founders initiative has turned its interview research into SOFIA for Business, a voice agent built on ElevenAgents and supported by the ElevenLabs Impact Program, launched at the Oxford Saïd Entrepreneurship Forum. SOFIA lets founders learn from previously interviewed women and also interviews new founders itself, adding each consented conversation to the research. It was co-founded by Pinar Ozcan, Amanda Slavin and Arabella Nyffenegger, with ElevenLabs providing free tool access through its Impact Program × Professors.

Releasing Personal Agent Protocol 1.0

Poppy (Personal Agent Protocol) v1.0 is now available, with Shopify enabling it for every merchant on its platform, Mercury, Synchrony and Turkish Airlines going live as design partners, and Muse, Meta's AI agent, checking for Poppy first on every site it visits. The protocol, built largely on existing standards like MCP, OpenAPI and UCP with OAuth authentication, defines how personal agents connect with companies, and now has more than 100 design partners after 60 new companies joined. Shopify co-authored Poppy's commerce extension linking it to UCP, and an implementation kit with a validator is available for any company to adopt the protocol.

Adapt Human Motion for Robots with NVIDIA SOMA Retargeter

Human motion can serve as a starting point for teaching humanoid robots to move, since human demonstrations capture the coordination and timing behind natural movement. However, a robot cannot simply copy the same joint motion from a human because its proportions, joint structure, and range of motion differ, so the movement must be adapted to fit. NVIDIA's SOMA Retargeter is presented as a tool for this adaptation.

Anthropic's Claude for Manufacturing plugs AI directly into factory software to automate industrial workflows

Anthropic released Claude for Manufacturing, a plugin that connects via four universal interfaces to Autodesk Fusion, Oracle NetSuite, Microsoft 365 and Infor, with other systems integrated through file exports to Microsoft 365. Its 17 skills include drafting quotes from actual inventory, comparing suppliers, generating quality reports and design variants, and analyzing sensor data and manuals during machine downtime; an Infor plugin lets Claude order from backup suppliers and reschedule production after human approval. Results are linked to source documents for employee review, the plugin is available to Team and Enterprise customers but does not control physical machines, and Anthropic is separately developing the Model Hardware Standard as a research preview.

Introducing ChatGPT Wallet

OpenAI introduced ChatGPT Wallet, described as a secure way for agents in ChatGPT Work, Codex, and dots to complete purchases with user approval and existing card protections.

ChatGPT’s new Wallet lets AI agents shop and check out for you

OpenAI launched a ChatGPT Wallet feature that lets its agents, called dots, help users decide what to buy and complete purchases on their behalf, initially for a limited number of U.S. ChatGPT Pro subscribers aged 18 and up with a U.S.-issued Visa, Mastercard, or American Express. Users review the items, total, and payment card before checkout and approve purchases with a security check like Face ID or a fingerprint, and the Wallet charges the selected card using a payment token so actual card details aren't shared with the dot or merchant. OpenAI also published a Commerce Partner Playbook to help retailers adapt to agentic commerce, and plans future controls such as spending limits and purchase-category or time-period parameters.

OpenAI and Databricks: Enterprise AI on your governed data

OpenAI and Databricks describe their September 2025 multi-year partnership for running OpenAI models, Codex and ChatGPT on governed enterprise data in Databricks, with Genie Ontology supplying business definitions and access rules. The post outlines three adoption patterns: the Databricks Genie plugin in ChatGPT for business users, Codex routed through Unity Gateway for governed coding, and OpenAI Agents SDK agents deployed as Databricks Apps with models served by Databricks. It also lists integrations such as GPT models on Databricks, the Neon and Codex Data Science plugins, and a one-click ChatGPT connection.

Show HN: Leetsys – Practice system design interviews with an AI interviewer

Leetsys lets users work through system design prompts, sketch architectures on an interactive whiteboard, and explain trade-offs via voice or chat to receive AI feedback before a real interview. It offers realistic mock interviews with feedback that adapts to the user's seniority level, plus a library of prompts such as URL shorteners, rate limiters, and file storage.

Show HN: Viral Video AI – Short videos from text, photos and video references

Viral Video AI generates 4–30-second vertical social clips for TikTok, Reels, or Shorts from a text prompt, up to 9 photos (Basic) or 30 (Pro), or one reference video, with Basic offering 4–15 s at 480p/720p and Pro extending to 30 s and 1080p. Users can paste a public TikTok, YouTube, or Instagram URL to preview a clip as a reference, and the tool shows a credit quote that updates with media and settings before generation. The page states no exact match to references is guaranteed and notes platform disclosure rules for realistic AI content.

OpenAI enters the cybersecurity market with two Daybreak products

OpenAI launched two security products under its Daybreak brand: Daybreak Red Team, in Early Access, uses AI agents to probe web applications for vulnerabilities by analyzing source code and app context, verify reported flaws, and test patches; Daybreak Defense Factory scans a company's codebase for vulnerabilities and generates ready-to-deploy pull requests with fixes and tests for developer approval. Both run on OpenAI's latest cyber model, GPT-6 Cyber.

Meta's Muse now calls businesses for you, but many companies might just hang up on the AI

Meta's AI agent Muse can now place calls to US businesses on behalf of users, available to all paying Muse subscribers in the US after a September test. Meta AI chief Alexandr Wang said the agent, with more than 10 million users, handles calls to cable companies, the DMV and restaurants, and will soon get a free email address. Many businesses hang up when they detect an AI on the line, which forced Meta to temporarily test human operators for Muse in September, echoing Google's Duplex experience where one in four launch calls was handled by a human.

Show HN: Langfuse AI Gateway, open source rust gateway to trace every LLM call

Langfuse AI Gateway is a standalone Rust gateway that exposes OpenAI and Anthropic native APIs under /openai/v1 and /anthropic/v1 namespaces, relaying provider JSON or SSE without rewriting bytes while capturing each finalized generation and uploading it to Langfuse via OTLP. It resolves gateway keys to trusted provider connections through Web, adds request IDs and trace/observation IDs to responses, and emits operational OpenTelemetry traces and metrics. Configuration is environment-based, with pnpm dev or cargo run for local use and no real provider credentials needed for building and testing.

Migrate Effortlessly to the Databricks Lakehouse with Genie Migrate, now Generally Available

Databricks announced that Genie Migrate for Lakehouse, a coding agent built on Genie Code, is now generally available and converts SQL from seven data warehouses—Microsoft SQL Server, Azure Synapse, Teradata, Oracle, Snowflake, Amazon Redshift, and Google BigQuery—to open ANSI SQL. It organizes migrations into projects with lineage review, parallel conversion, and side-by-side comparison, and converted more than 90% of files correctly on benchmarks for all seven sources. MIXI reported that about 85% of tested BigQuery files ran without manual edits, with the rest needing only one-line fixes.

ElevenLabs’ new app combines meeting note-taking and dictation for teams

ElevenLabs released an experimental app called ElevenAI, currently in preview with sign-up required for early access, that combines meeting note-taking, dictation in over 90 languages, and agent integration. It can take notes across meetings, notify participants of recording, let users query data across meetings, and allow companies to integrate ElevenAgent for follow-up actions such as drafting emails from notes. The company also launched its v3 series of Scribe speech-to-text models with live transcription and fine-tuning on companies' own data.

llama.cpp v1.0.0 : A stronger foundation for the local AI ecosystem

llama.cpp released libraries v1.0.0, marking a commitment to stable public APIs for downstream developers, with both llama.cpp and ggml now reflecting API and ABI incompatibilities through major-version bumps. The project states it supports more than 150 architecture variants and all mainstream speculative decoding methods, and distributes pre-release artifacts across Linux, macOS, Windows, Android and iOS plus channels including Docker, Homebrew, conda-forge, MacPorts, Winget and XCFramework. It also describes continued investment in CI infrastructure and self-hosted runners with hardware support from NVIDIA, AMD, Qualcomm, Arm, IBM and Intel.

Mandat – Authorization, delegation and audit for AI agent actions

Mandat is an MCP-first tool that checks a policy on every AI agent tool call (e.g., refunds ≤ €50 allowed, €50–500 require a human, > €500 denied), issues short-lived single-task tokens carrying the human → agent → sub-agent chain, and records each call in a tamper-evident audit log exportable to a SIEM. It also ships a scanner for authentication and supply-chain mistakes in MCP servers and client configs, and is installable via npm or pip with an Apache-2.0 license.

Show HN: Practice coding with AI on real tickets

This Show HN post introduces an AI coding practice platform where users work through 30 tickets across five codebases (Python in Seasons 0–3, JavaScript/Node.js in Season 4), each based on a small business scenario. Users ask a client questions, direct an AI teammate that writes code and runs tests while making realistic mistakes, then deliver and get scored on asking, directing, verifying, protecting, and performance. The first ticket is free with 25 AI replies, and paid plans or credit packs (100 credits for $19.99, 300 for $49.99) add more.

Show HN: Aisync exits 3 when two AI agents claim the same file

Aisync is a tool whose collab.py module exits with status code 3 when two AI agents claim the same file. The submission links to the source on GitHub and to its Hacker News discussion.

Introducing Spend Management: Spending limits and alerts for Cloudflare

Cloudflare has launched Spend Management in Beta for pay-as-you-go customers, starting with Workers and Durable Objects, letting users set spending thresholds and have Cloudflare pause activity when limits are reached. Limits can be configured via the dashboard, cf CLI, or REST API, with email alerts at chosen thresholds and near real-time (under 10 minutes) cost visibility. Enforcement is asynchronous, propagating caps through Quicksilver so requests never wait on the Rating Engine, and more products plus application- and agent-based budgets are planned.