# Agent Browser

Agent browsers are web browsers or browser engines designed to be driven by AI agents, exposing programmatic interfaces such as HTTP APIs, MCP servers, and CDP endpoints.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## WebAgents: Unbundling Agent Creation, Hosting, and Execution for an Agent-Native Web

DevFeed: [WebAgents: Unbundling Agent Creation, Hosting, and Execution for an Agent-Native Web](<https://devfeed.tech/articles/webagents-unbundling-agent-creation-hosting-and-execution-for-an-agent-native-web-139941.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21978>)

Author: Dario Fenoglio, Martin Gjoreski, Marc Langheinrich, Pradyumna Chari, Ramesh Raskar

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Cryptography](<https://devfeed.tech/topics/cryptography.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-behavior](<https://devfeed.tech/tags/agent-behavior.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [api](<https://devfeed.tech/tags/api.md>), [authorization](<https://devfeed.tech/tags/authorization.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-agents](<https://devfeed.tech/tags/autonomous-agents.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [execution](<https://devfeed.tech/tags/execution.md>), [hosting](<https://devfeed.tech/tags/hosting.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [literature](<https://devfeed.tech/tags/literature.md>), [live](<https://devfeed.tech/tags/live.md>), [local](<https://devfeed.tech/tags/local.md>), [models](<https://devfeed.tech/tags/models.md>), [openclaw](<https://devfeed.tech/tags/openclaw.md>), [package](<https://devfeed.tech/tags/package.md>), [packages](<https://devfeed.tech/tags/packages.md>), [permissions](<https://devfeed.tech/tags/permissions.md>), [web](<https://devfeed.tech/tags/web.md>)

### AI overview

WebAgents separates agent creation, hosting, and execution using a signed package of portable workflows, skills, schemas, and resource requirements. An OpenClaw-based browser/runtime verifies the package, obtains user authorization, and connects it at run time to user-controlled models, tools, permissions, and budgets; hosts distribute the public program and may keep private services server-side. The authors report three workflows running unchanged with local and API-backed models. In a controlled suite, the system blocked 716 injected contract violations and accepted 295 matched benign controls, with median automated pre-execution processing below 0.5 seconds for each package. The evidence here is limited to the abstract and page excerpt.

### Source excerpt

arXiv:2611.21978v1 Announce Type: new Abstract: Large language models are moving from isolated assistants toward autonomous agents that can plan, use tools, and coordinate with others, motivating an emerging Agentic Web of independently developed agents and services. Realizing this vision requires agent behavior to move across creators, hosts, and runtimes without coupling publication to a particular execution environment or transferring authority over user resources. We introduce WebAgents, which unbundles these roles through a signed agent.pkg that carries portable workflows, skills, schemas, and resource requirements. An OpenClaw-based agent-native browser/runtime verifies the package, obtains authorization, and binds it at run time to user-controlled models, tools, permissions, and budgets, while hosts distribute the public program and may retain private services server-side. We demonstrate this contract with three unrelated workflows executed unchanged under local and API-backed models, including literature review with live services and a website-published travel agent using semantic tools and user-selected personal resources. In a controlled suite, WebAgents explicitly blocks all 716 injected contract violations while accepting all 295 matched benign controls, with median automated pre-execution processing below 0.5 s for all three packages. We conclude by outlining a path toward NANDA-based discovery and interoperable package ecosystems while retaining execution authority in the user's runtime.

## Agent Vault gives your agents a signed-in browser for websites without APIs

DevFeed: [Agent Vault gives your agents a signed-in browser for websites without APIs](<https://devfeed.tech/articles/agent-vault-gives-your-agents-a-signed-in-browser-for-websites-without-apis-140649.md>)

Original publisher: [Read original article](<https://workos.com/blog/agent-vault>)

Author: WorkOS

Published: 2026-11-17T00:00:00Z

Content type: release

Language: en

Sources: [WorkOS](<https://devfeed.tech/sources/workos-blog.md>)

Topics: [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [agentic browsing](<https://devfeed.tech/topics/agentic-browsing.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>)

Tags: [access-tokens](<https://devfeed.tech/tags/access-tokens.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [api](<https://devfeed.tech/tags/api.md>), [apis](<https://devfeed.tech/tags/apis.md>), [application](<https://devfeed.tech/tags/application.md>), [browser](<https://devfeed.tech/tags/browser.md>), [build](<https://devfeed.tech/tags/build.md>), [connect](<https://devfeed.tech/tags/connect.md>), [hosted](<https://devfeed.tech/tags/hosted.md>), [self-hosted](<https://devfeed.tech/tags/self-hosted.md>), [store](<https://devfeed.tech/tags/store.md>), [users](<https://devfeed.tech/tags/users.md>), [vault](<https://devfeed.tech/tags/vault.md>), [website](<https://devfeed.tech/tags/website.md>), [websites](<https://devfeed.tech/tags/websites.md>), [workos](<https://devfeed.tech/tags/workos.md>)

### AI overview

Agent Vault lets an agent work in a user-authenticated browser on websites without a usable API. Users save logins through a WorkOS widget; Agent Vault handles sign-in and keeps saved passwords out of the agent's prompts and tool responses. Agents connect through MCP to a hosted browser, while users can take over to complete steps such as SSO, CAPTCHA, or passkey checks and return the session. Developers can use the WorkOS-hosted browser or provide one through an existing browser integration; only one browser provider can be chosen per environment. Pipes provides OAuth tokens for supported integrations, while Agent Vault serves browser-only sites, and an application can use both. Access is enabled by the WorkOS team and the product is not generally available.

### Source excerpt

Build agentic products with Agent Vault: store users' website logins and connect agents through a WorkOS-hosted or self-hosted browser. Contact us for access.

## You can now self-host Kitesurf, Cloudflare's open-source browser for AI agents

DevFeed: [You can now self-host Kitesurf, Cloudflare's open-source browser for AI agents](<https://devfeed.tech/articles/you-can-now-self-host-kitesurf-cloudflare-s-open-source-browser-for-ai-agents-134758.md>)

Original publisher: [Read original article](<https://www.helpnetsecurity.com/2026/11/16/cloudflare-kitesurf-open-source/>)

Author: Mirko Zorz

Published: 2026-11-16T07:00:02Z

Content type: news

Language: en

Sources: [Help Net Security](<https://devfeed.tech/sources/help-net-security.md>)

Topics: [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Cloudflare Workers](<https://devfeed.tech/topics/cloudflare-workers.md>), [Cloudflare](<https://devfeed.tech/topics/cloudflare.md>)

Tags: [account](<https://devfeed.tech/tags/account.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [browser](<https://devfeed.tech/tags/browser.md>), [can](<https://devfeed.tech/tags/can.md>), [chromium](<https://devfeed.tech/tags/chromium.md>), [cloudflare](<https://devfeed.tech/tags/cloudflare.md>), [cloudflare-workers](<https://devfeed.tech/tags/cloudflare-workers.md>), [code](<https://devfeed.tech/tags/code.md>), [container](<https://devfeed.tech/tags/container.md>), [copy](<https://devfeed.tech/tags/copy.md>), [deploy](<https://devfeed.tech/tags/deploy.md>), [desktop](<https://devfeed.tech/tags/desktop.md>), [developers](<https://devfeed.tech/tags/developers.md>), [kitesurf](<https://devfeed.tech/tags/kitesurf.md>), [news](<https://devfeed.tech/tags/news.md>), [open](<https://devfeed.tech/tags/open.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [self-host](<https://devfeed.tech/tags/self-host.md>), [software](<https://devfeed.tech/tags/software.md>), [source](<https://devfeed.tech/tags/source.md>)

### AI overview

Kitesurf loads web pages and runs their JavaScript on Cloudflare Workers without a full desktop browser or browser container, and can return screenshots. It supports the Chrome DevTools Protocol (CDP), so clients such as Puppeteer can connect. Its Engine manages sessions and connections, PageScript executes pages, and PageRenderer produces images. The Rust components compile to WebAssembly; Boa runs JavaScript only as a fallback when scripts cannot run in Dynamic Workers. Developers can build locally with pnpm after meeting repository requirements, though the first build takes longer while compiling dependencies. Deploying with `pnpm run deploy` requires a Workers Paid plan because Kitesurf uses Dynamic Workers for page isolation.

### Source excerpt

Kitesurf is Cloudflare's browser for AI agents, built to load web pages and run their JavaScript on Cloudflare Workers without starting up a full desktop browser. Cloudflare has published its source code so developers can inspect it, modify it, test it on their own machines, and deploy a copy to their Cloudflare account. A browser without Chromium Kitesurf needs no browser container, and it can return screenshots of the pages it loads. It supports the ... More -> The post You can now self-host Kitesurf, Cloudflare's open-source browser for AI agents appeared first on Help Net Security.

## Cloudflare Open Sources Kitesurf: Their Web Browser For AI Agents

DevFeed: [Cloudflare Open Sources Kitesurf: Their Web Browser For AI Agents](<https://devfeed.tech/articles/cloudflare-open-sources-kitesurf-their-web-browser-for-ai-agents-133364.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/Cloudflare-Kitesurf-Open-Source>)

Author: Michael Larabel

Published: 2026-11-13T21:07:09Z

Content type: news

Language: en

Sources: [Phoronix](<https://devfeed.tech/sources/phoronix.md>)

Topics: [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Cloudflare](<https://devfeed.tech/topics/cloudflare.md>), [Cloudflare Workers](<https://devfeed.tech/topics/cloudflare-workers.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [apache-2-0](<https://devfeed.tech/tags/apache-2-0.md>), [browser](<https://devfeed.tech/tags/browser.md>), [chromium](<https://devfeed.tech/tags/chromium.md>), [cloudflare](<https://devfeed.tech/tags/cloudflare.md>), [cloudflare-workers](<https://devfeed.tech/tags/cloudflare-workers.md>), [css](<https://devfeed.tech/tags/css.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [github](<https://devfeed.tech/tags/github.md>), [html](<https://devfeed.tech/tags/html.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [linux-benchmarking](<https://devfeed.tech/tags/linux-benchmarking.md>), [linux-hardware-benchmarks](<https://devfeed.tech/tags/linux-hardware-benchmarks.md>), [linux-hardware-reviews](<https://devfeed.tech/tags/linux-hardware-reviews.md>), [linux-how-to](<https://devfeed.tech/tags/linux-how-to.md>), [linux-performance](<https://devfeed.tech/tags/linux-performance.md>), [linux-server-benchmarks](<https://devfeed.tech/tags/linux-server-benchmarks.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [open-source-graphics](<https://devfeed.tech/tags/open-source-graphics.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>)

### AI overview

Cloudflare has open-sourced Kitesurf under the Apache 2.0 license. Built on Cloudflare Workers, it parses HTML, handles CSS, and executes JavaScript without a browser container. Cloudflare describes its goal as giving AI agents a lightweight browser that uses less CPU and memory than a full browser such as Chromium and can scale on demand across its global Workers network.

### Source excerpt

Earlier this year Cloudflare announced Kitesurf as a stateless web browser for AI agents. After building out its features, they have now made good on their word to open-source it...

## Giving AI Agents a Better Way to Debug CSS

DevFeed: [Giving AI Agents a Better Way to Debug CSS](<https://devfeed.tech/articles/giving-ai-agents-a-better-way-to-debug-css-133541.md>)

Original publisher: [Read original article](<https://www.amitmerchant.com/giving-ai-agents-a-better-way-to-debug-css/>)

Author: Amit Merchant

Published: 2026-11-13T00:00:00Z

Content type: tutorial

Language: en

Sources: [Amit Merchant](<https://devfeed.tech/sources/amit-merchant.md>)

Topics: [CSS](<https://devfeed.tech/topics/css.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [Front end](<https://devfeed.tech/topics/frontend.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Web Development](<https://devfeed.tech/topics/web-development.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [browser](<https://devfeed.tech/tags/browser.md>), [chrome-devtools](<https://devfeed.tech/tags/chrome-devtools.md>), [codex](<https://devfeed.tech/tags/codex.md>), [css](<https://devfeed.tech/tags/css.md>), [debug](<https://devfeed.tech/tags/debug.md>), [debugging](<https://devfeed.tech/tags/debugging.md>)

### AI overview

Chrome DevTools MCP lets Codex diagnose CSS using the browser's live style information instead of inferring behavior from source files alone. After connecting the MCP server and starting the app locally, Codex can use `take_snapshot` to locate an element and `get_css_styles` to inspect matched and inherited rules, inline styles, custom properties, applicable context, and overridden declarations. The example explains that `#main .card h2` wins over `.card h2` because it has greater specificity. The article also suggests using the tool to audit potential overrides and investigate dark mode, responsive layouts, and media query conflicts. Findings and proposed changes still need review and browser verification.

### Source excerpt

Have you ever written a CSS rule, only to find out that it doesn't seem to have any effect on the element you're trying to style? You inspect the stylesheet, find the declaration, and everything looks perfectly fine. But the browser has other plans.

## 19 Agent Skills Test Your Web App With Playwright and Real Browsers

DevFeed: [19 Agent Skills Test Your Web App With Playwright and Real Browsers](<https://devfeed.tech/articles/19-agent-skills-test-your-web-app-with-playwright-and-real-browsers-122636.md>)

Original publisher: [Read original article](<https://hackernoon.com/19-agent-skills-test-your-web-app-with-playwright-and-real-browsers?source=rss>)

Author: Quality Assurance Career Development Resources

Published: 2026-11-08T16:00:02Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [Playwright](<https://devfeed.tech/topics/playwright.md>)

Tags: [agent-browser](<https://devfeed.tech/tags/agent-browser.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browsers](<https://devfeed.tech/tags/browsers.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cli](<https://devfeed.tech/tags/cli.md>), [codex](<https://devfeed.tech/tags/codex.md>), [codex-cli](<https://devfeed.tech/tags/codex-cli.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [hackernoon](<https://devfeed.tech/tags/hackernoon.md>), [install](<https://devfeed.tech/tags/install.md>), [playwright](<https://devfeed.tech/tags/playwright.md>), [playwright-agent](<https://devfeed.tech/tags/playwright-agent.md>), [playwright-skill](<https://devfeed.tech/tags/playwright-skill.md>), [plugin](<https://devfeed.tech/tags/plugin.md>), [qa-testing](<https://devfeed.tech/tags/qa-testing.md>), [repo](<https://devfeed.tech/tags/repo.md>), [skills](<https://devfeed.tech/tags/skills.md>), [software-testing](<https://devfeed.tech/tags/software-testing.md>), [test](<https://devfeed.tech/tags/test.md>), [test-your-app-agent](<https://devfeed.tech/tags/test-your-app-agent.md>), [test-your-web-app-agent](<https://devfeed.tech/tags/test-your-web-app-agent.md>), [web-app](<https://devfeed.tech/tags/web-app.md>)

### AI overview

The 19 open-licensed QA skills guide AI agents to write tests, use a real browser to click through web app flows, and report failures. They are packaged in Cuttlefish.MD's QA & Testing plugin and follow the open Agent Skills standard, supporting Claude Code, Codex CLI, and 30+ other tools. Install the plugin with the provided marketplace commands, or copy the skills folder into a compatible agent's skills directory. Skills that use agent-browser require Vercel's agent-browser CLI. Each skill retains its license and attribution.

### Source excerpt

Nineteen open-licensed agent skills let an AI agent test a web app the way a person would: write the test first, open a real browser, & click through the flows.

## Securing Web Agents with the Compile-Then-Execute Paradigm

DevFeed: [Securing Web Agents with the Compile-Then-Execute Paradigm](<https://devfeed.tech/articles/securing-web-agents-with-the-compile-then-execute-paradigm-118697.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.06039>)

Author: Annabella Chow, Jinhao Zhu, Sylvie Venuto, Abdulaziz Alharbi, Basel Alomair, Raluca Popa, David Wagner, Julien Piet

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [prompt injection](<https://devfeed.tech/topics/prompt-injection.md>), [agentic browsing](<https://devfeed.tech/topics/agentic-browsing.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Web](<https://devfeed.tech/topics/web.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [api](<https://devfeed.tech/tags/api.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [compilation](<https://devfeed.tech/tags/compilation.md>), [compiler](<https://devfeed.tech/tags/compiler.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [hijacking](<https://devfeed.tech/tags/hijacking.md>), [planning](<https://devfeed.tech/tags/planning.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>), [python](<https://devfeed.tech/tags/python.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [security](<https://devfeed.tech/tags/security.md>), [web](<https://devfeed.tech/tags/web.md>), [website](<https://devfeed.tech/tags/website.md>)

### AI overview

Baya aims to prevent webpage prompt injections from hijacking a web agent's control flow by compiling the user's request into a Python program before accessing the live site. The planning model does not see live content; the compiled program processes it through a Trusted Website API. Untrusted content can supply values or choose among precompiled branches, but cannot redefine the task or prompt the model to create new website operations at runtime. Across 581 valid WebArena Verified tasks, Baya reported 77.8% aggregate utility, compared with 66.7% for API-enabled ReAct and 55.1% for browser-only ReAct. On WASP, its reported attack success rate was 0%, versus 16.2% and 25.5%, respectively. These are reported benchmark results; the supplied text does not describe evaluation limitations.

### Source excerpt

arXiv:2611.06039v1 Announce Type: new Abstract: Web agents commonly follow the ReAct paradigm, selecting each action from runtime observations that inherently mix trusted and untrusted content. This design makes their control flow vulnerable to prompt injections embedded in webpages. We introduce Baya, a compile-then-execute web agent designed to prevent prompt-injection-driven control-flow hijacking by design. Before accessing the live website, Baya compiles the user's request into an executable Python program that calls a Trusted Website API. The planning model does not observe live website content; only the compiled program processes it. Untrusted data may determine program values or select among branches defined during compilation, but it cannot redefine the user task or cause the model to synthesize new website operations at runtime. The Trusted Website API gives the compiler a unified view of the website's action space, enabling ahead-of-time planning without the stepwise action discovery required by reactive agents. Our evaluation across 581 valid WebArena Verified tasks shows that Baya achieves 77.8% aggregate utility, outperforming browser-only ReAct (55.1%) and API-enabled ReAct (66.7%). On WASP, a security benchmark for web agents, Baya achieves 0% attack success rate, compared with 16.2% for API-enabled ReAct and 25.5% for browser-only ReAct.

## We Stopped Feeding LLMs Raw HTML: Cutting Agent Scraping Costs by 74% Across 10,000 Targets

DevFeed: [We Stopped Feeding LLMs Raw HTML: Cutting Agent Scraping Costs by 74% Across 10,000 Targets](<https://devfeed.tech/articles/we-stopped-feeding-llms-raw-html-cutting-agent-scraping-costs-by-74-across-10-000-targets-117857.md>)

Original publisher: [Read original article](<https://hackernoon.com/we-stopped-feeding-llms-raw-html-cutting-agent-scraping-costs-by-74percent-across-10000-targets?source=rss>)

Author: Hamed Hosseini

Published: 2026-11-04T21:41:41Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Bot](<https://devfeed.tech/topics/bot.md>), [performance-optimization](<https://devfeed.tech/topics/performance-optimization.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [HTML](<https://devfeed.tech/topics/html.md>), [Markdown](<https://devfeed.tech/topics/markdown.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [403](<https://devfeed.tech/tags/403.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-scraping-agents](<https://devfeed.tech/tags/ai-scraping-agents.md>), [all](<https://devfeed.tech/tags/all.md>), [api](<https://devfeed.tech/tags/api.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [automation](<https://devfeed.tech/tags/automation.md>), [bot](<https://devfeed.tech/tags/bot.md>), [costs](<https://devfeed.tech/tags/costs.md>), [data](<https://devfeed.tech/tags/data.md>), [fail](<https://devfeed.tech/tags/fail.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [html](<https://devfeed.tech/tags/html.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [llms](<https://devfeed.tech/tags/llms.md>), [production](<https://devfeed.tech/tags/production.md>), [proxy](<https://devfeed.tech/tags/proxy.md>), [raw](<https://devfeed.tech/tags/raw.md>), [routing](<https://devfeed.tech/tags/routing.md>), [scraping](<https://devfeed.tech/tags/scraping.md>), [token](<https://devfeed.tech/tags/token.md>), [web-scraping](<https://devfeed.tech/tags/web-scraping.md>)

### AI overview

The article reports that a three-tier scraper raised success across 10,000 bot-protected URLs from 36.4% to 99.4% while cutting cost per 10,000 operations from $184.20 to $47.50. It tries free direct HTTP/2 first, uses Bright Data Web Unlocker for blocked or challenged requests, and reserves Bright Data Scraping Browser for pages needing client-side rendering. A preprocessing pipeline harvests JSON-LD product data without an LLM call when available; otherwise it removes low-value markup and formats dense content as Markdown tables. The reported changes also reduced worker memory from 640 MB to 38 MB, median latency from 14.8 to 2.6 seconds, and tokens per call from 14,200 to 1,650. Remaining issues included session lockouts, WebGL challenges, and cascading retries; the authors addressed these with session pinning, selective cloud-browser use, and backoff with cached snapshots.

### Source excerpt

Most AI scraping agents fail in production from anti-bot walls, token-burning HTML dumps, and proxy costs. A tri-tier routing architecture that fixed all three.

## How We Optimized Browser Use for Deep Agents

DevFeed: [How We Optimized Browser Use for Deep Agents](<https://devfeed.tech/articles/how-we-optimized-browser-use-for-deep-agents-116377.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/how-we-optimized-browser-use-for-deep-agents>)

Author: LangChain Accounts

Published: 2026-11-03T22:30:50Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [agentic browsing](<https://devfeed.tech/topics/agentic-browsing.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>), [browser](<https://devfeed.tech/topics/browser.md>), [Selenium](<https://devfeed.tech/topics/selenium.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [api](<https://devfeed.tech/tags/api.md>), [apis](<https://devfeed.tech/tags/apis.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browser-agents](<https://devfeed.tech/tags/browser-agents.md>), [browser-tools](<https://devfeed.tech/tags/browser-tools.md>), [browserbase](<https://devfeed.tech/tags/browserbase.md>), [browsers](<https://devfeed.tech/tags/browsers.md>), [browsing](<https://devfeed.tech/tags/browsing.md>), [cdp](<https://devfeed.tech/tags/cdp.md>), [chrome](<https://devfeed.tech/tags/chrome.md>), [chrome-devtools](<https://devfeed.tech/tags/chrome-devtools.md>), [claude](<https://devfeed.tech/tags/claude.md>), [evals](<https://devfeed.tech/tags/evals.md>), [langsmith](<https://devfeed.tech/tags/langsmith.md>), [traces](<https://devfeed.tech/tags/traces.md>)

### AI overview

The team selected Browserbase's Stagehand after comparing seven browser toolsets, then used LangSmith traces and evals to refine it. In their benchmarks, Stagehand passed 90% of WebVoyager tasks for $1.98 total, while Playwright MCP passed 78% for $26.71 and took three times as long per task. Stagehand's code-based `run` batches browser actions, keeping intermediate page data out of the model context; its `snapshot` returns a compact accessibility tree with IDs for interactive elements; and running actions in the browser reduces round trips. A separate harness change made fixed waits end once the page had been quiet for 500 ms. On HardBench, combined with structured answers and a model-call timeout, this reduced median time from 182 to 124 seconds while accuracy stayed within noise. The reported results cover the stated benchmarks and setups; the suggested optimization process is to inspect traces, change tools or harness behavior, and check changes with evals.

### Source excerpt

We compared seven browser toolsets for Deep Agents, picked Stagehand from Browserbase, and tuned it with LangSmith traces and evals. Here's what we learned.

## My vacation agent is struggling: how AI-ready are services?

DevFeed: [My vacation agent is struggling: how AI-ready are services?](<https://devfeed.tech/articles/my-vacation-agent-is-struggling-how-ai-ready-are-services-115723.md>)

Original publisher: [Read original article](<https://blog.postman.com/my-vacation-agent-is-struggling-how-ai-ready-are-services/>)

Author: Anthony Viard

Published: 2026-11-03T16:00:12Z

Content type: article

Language: en

Sources: [Postman](<https://devfeed.tech/sources/postman-blog.md>)

Topics: [API Economy](<https://devfeed.tech/topics/api-economy.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [protocols](<https://devfeed.tech/topics/protocols.md>), [Postman](<https://devfeed.tech/topics/postman.md>), [Documentation](<https://devfeed.tech/topics/documentation.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [api](<https://devfeed.tech/tags/api.md>), [api-design](<https://devfeed.tech/tags/api-design.md>), [booking](<https://devfeed.tech/tags/booking.md>), [general](<https://devfeed.tech/tags/general.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [model-context-protocol](<https://devfeed.tech/tags/model-context-protocol.md>), [protocols](<https://devfeed.tech/tags/protocols.md>), [question](<https://devfeed.tech/tags/question.md>), [rest](<https://devfeed.tech/tags/rest.md>), [rest-api](<https://devfeed.tech/tags/rest-api.md>), [sites](<https://devfeed.tech/tags/sites.md>), [types](<https://devfeed.tech/tags/types.md>)

### AI overview

In a one-time vacation search, a browser agent spent about 33 tool calls per provider and could not retrieve pet policies for four of five offers. A lastminute.com MCP search took about 15 calls and exposed typed hotel data, including a `pets_allowed` boolean; checking details changed the ranking because one top browser result did not allow pets and another did. The author's main finding is that machine-readable, well-typed fields matter more than the protocol: REST with accurate types, an SDK, or predictable command-line output could also serve agents. The comparison is a single campaign with different providers and inventory; costs and timings are estimates, and no ordinary REST API was tested.

### Source excerpt

Scraped sites, a REST API, and an MCP server, all asked one question by my booking agent. What separated them was field types, not protocols. The post My vacation agent is struggling: how AI-ready are services? appeared first on Postman Blog.

## WAAA! Web Adversaries Against Web Agents

DevFeed: [WAAA! Web Adversaries Against Web Agents](<https://devfeed.tech/articles/waaa-web-adversaries-against-web-agents-108991.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.05509>)

Author: Sohom Datta, Alex Nahapetyan, William Enck, Alexandros Kapravelos

Published: 2026-10-30T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [LLM security](<https://devfeed.tech/topics/llm-security.md>), [agentic browsing](<https://devfeed.tech/topics/agentic-browsing.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [AI Bots](<https://devfeed.tech/topics/ai-bots.md>), [prompt injection](<https://devfeed.tech/topics/prompt-injection.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-browsing](<https://devfeed.tech/tags/agentic-browsing.md>), [agents](<https://devfeed.tech/tags/agents.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browsers](<https://devfeed.tech/tags/browsers.md>), [components](<https://devfeed.tech/tags/components.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [failure](<https://devfeed.tech/tags/failure.md>), [indirect-prompt-injection](<https://devfeed.tech/tags/indirect-prompt-injection.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [llms](<https://devfeed.tech/tags/llms.md>), [security](<https://devfeed.tech/tags/security.md>), [social-engineering](<https://devfeed.tech/tags/social-engineering.md>), [social-engineering-attacks](<https://devfeed.tech/tags/social-engineering-attacks.md>), [taxonomy](<https://devfeed.tech/tags/taxonomy.md>), [threats](<https://devfeed.tech/tags/threats.md>), [web](<https://devfeed.tech/tags/web.md>)

### AI overview

The paper argues that agentic browser security models miss traditional web social engineering, leaving agents vulnerable when they cannot distinguish user task steps from malicious page content. It extends the See->Act model to cover browser components, defines 20 attacks across web and LLM threats, and implements 18. The authors report that 10 traditional web threats can reappear in amplified forms and that 14 attacks reproduced across four major LLM models from multiple vendors. They identify five failure modes and argue that agentic browsers need architectural changes before they are ready for the current web.

### Source excerpt

arXiv:2605.05509v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly being integrated into web browsers to create agentic browsing systems that execute actions on behalf of the user. Prior work considering the security of agentic browsers focuses on indirect prompt-injection attacks. However, by failing to consider traditional web attacks, previous agentic browser threat models have a blind spot to web social engineering attacks originally designed to trick humans. In this paper, we propose the first web-focused threat model for agentic browsers and use it to derive a taxonomy of 20 attacks across both the web and LLM space, and implement 18 of the attacks. Our threat model extends the original See$\rightarrow$Act browser agent model to account for all components of a browser, and frames the agent as a confused deputy unable to distinguish task steps from traditional web attacks. We show that 10 web threats can reemerge often in amplified forms once an agent can be influenced by untrusted page content. We further conduct a generalizability study on 14 of the 20 attacks, showing that our attacks reproduce across 4 major LLM models spanning multiple vendors. We show that agentic browsers exhibit five major failure modes when facing traditional and LLM web threats, demonstrating the need to rearchitect agentic browsers before they are ready for the current web.

## Daytona runs the code, Notte runs the browser

DevFeed: [Daytona runs the code, Notte runs the browser](<https://devfeed.tech/articles/daytona-runs-the-code-notte-runs-the-browser-109773.md>)

Original publisher: [Read original article](<https://www.daytona.io/dotfiles/daytona-runs-the-code-notte-runs-the-browser>)

Author: Lucas Giordano Co-founder; CTO; Notte

Published: 2026-10-30T00:00:00Z

Content type: article

Language: en

Sources: [Dotfiles Insider](<https://devfeed.tech/sources/dotfiles-insider.md>)

Topics: [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [browser](<https://devfeed.tech/topics/browser.md>), [Chromium](<https://devfeed.tech/topics/chromium.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [Web app](<https://devfeed.tech/topics/webapp.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [bot](<https://devfeed.tech/tags/bot.md>), [bot-detection](<https://devfeed.tech/tags/bot-detection.md>), [bot-protection](<https://devfeed.tech/tags/bot-protection.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browser-based-ide](<https://devfeed.tech/tags/browser-based-ide.md>), [browser-ide](<https://devfeed.tech/tags/browser-ide.md>), [captchas](<https://devfeed.tech/tags/captchas.md>), [cdp](<https://devfeed.tech/tags/cdp.md>), [chromium](<https://devfeed.tech/tags/chromium.md>), [cli](<https://devfeed.tech/tags/cli.md>), [cloud-coding](<https://devfeed.tech/tags/cloud-coding.md>), [cloud-dev-environment](<https://devfeed.tech/tags/cloud-dev-environment.md>), [cloud-development-environment](<https://devfeed.tech/tags/cloud-development-environment.md>), [cloud-editor](<https://devfeed.tech/tags/cloud-editor.md>), [cloud-ide](<https://devfeed.tech/tags/cloud-ide.md>), [cloud-programming](<https://devfeed.tech/tags/cloud-programming.md>), [cloudflare](<https://devfeed.tech/tags/cloudflare.md>), [code](<https://devfeed.tech/tags/code.md>), [code-in-cloud](<https://devfeed.tech/tags/code-in-cloud.md>), [code-on-web](<https://devfeed.tech/tags/code-on-web.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [coding-environment](<https://devfeed.tech/tags/coding-environment.md>), [computer](<https://devfeed.tech/tags/computer.md>), [computer-use](<https://devfeed.tech/tags/computer-use.md>), [cookies](<https://devfeed.tech/tags/cookies.md>), [daytona](<https://devfeed.tech/tags/daytona.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [desktop](<https://devfeed.tech/tags/desktop.md>), [guide](<https://devfeed.tech/tags/guide.md>), [here](<https://devfeed.tech/tags/here.md>), [ide-editor-online](<https://devfeed.tech/tags/ide-editor-online.md>), [ide-in-browser](<https://devfeed.tech/tags/ide-in-browser.md>), [ide-online](<https://devfeed.tech/tags/ide-online.md>), [online-code-editor](<https://devfeed.tech/tags/online-code-editor.md>), [online-ide](<https://devfeed.tech/tags/online-ide.md>), [online-programming](<https://devfeed.tech/tags/online-programming.md>), [online-web-dev-ide](<https://devfeed.tech/tags/online-web-dev-ide.md>), [online-web-development-ide](<https://devfeed.tech/tags/online-web-development-ide.md>), [sde](<https://devfeed.tech/tags/sde.md>), [standardised-development-environment](<https://devfeed.tech/tags/standardised-development-environment.md>), [stories-insights](<https://devfeed.tech/tags/stories-insights.md>), [web-based-coding](<https://devfeed.tech/tags/web-based-coding.md>), [web-ide](<https://devfeed.tech/tags/web-ide.md>)

### AI overview

Daytona's bundled Chromium is the simplest choice for testing an agent's app or browsing unprotected pages: it reaches sandbox localhost directly, but shares memory with the code. Five reference pages used about 600 MB; five news or shopping pages used 1,030-1,170 MB, for which the text recommends a 2 GiB sandbox. Notte runs the browser remotely, keeping sandbox use around 85-115 MB in the described runs and offering persistent login profiles, residential proxy routing, captcha solving, and session viewing and replay. The agent drives it through the Notte CLI or Playwright over CDP, which requires outbound access to Notte's API. For a sandbox app, Daytona's guide serves the app on a port, obtains a signed preview URL, then tests it with a Notte session; the remote browser needs no auth header for that URL. The guide requires Daytona and Notte API keys and the Notte CLI. The text describes this split as useful when agents both test their own apps and work with other sites.

### Source excerpt

Agents in Daytona sandboxes can run Chromium beside their code or use a Notte browser for bot checks, captchas and logins. A Daytona guide shows how.

## Managed Deep Agents v0.10: Browser Use and Async Subagents

DevFeed: [Managed Deep Agents v0.10: Browser Use and Async Subagents](<https://devfeed.tech/articles/managed-deep-agents-v0-10-browser-use-and-async-subagents-107265.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/managed-deep-agents-browser-use-and-asynchronous-subagents>)

Author: LangChain Accounts

Published: 2026-10-29T17:03:39Z

Content type: release

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Slack](<https://devfeed.tech/topics/slack.md>)

Tags: [accessibility](<https://devfeed.tech/tags/accessibility.md>), [account](<https://devfeed.tech/tags/account.md>), [actions](<https://devfeed.tech/tags/actions.md>), [added](<https://devfeed.tech/tags/added.md>), [agents](<https://devfeed.tech/tags/agents.md>), [api](<https://devfeed.tech/tags/api.md>), [async](<https://devfeed.tech/tags/async.md>), [background](<https://devfeed.tech/tags/background.md>), [background-work](<https://devfeed.tech/tags/background-work.md>), [browser](<https://devfeed.tech/tags/browser.md>), [can](<https://devfeed.tech/tags/can.md>), [deep](<https://devfeed.tech/tags/deep.md>), [managed](<https://devfeed.tech/tags/managed.md>), [sign](<https://devfeed.tech/tags/sign.md>), [sign-in](<https://devfeed.tech/tags/sign-in.md>), [sites](<https://devfeed.tech/tags/sites.md>), [subagents](<https://devfeed.tech/tags/subagents.md>), [window](<https://devfeed.tech/tags/window.md>), [with](<https://devfeed.tech/tags/with.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

Managed Deep Agents v0.10 adds browser tools for sites without APIs and asynchronous subagents for long-running delegated work. Browsers run in LangSmith sandboxes: thread scope gives each conversation a fresh browser, while user scope carries logins across that person's conversations. At login or two-factor prompts, `browser_handoff` lets a person use the remote window; handoff links expire after 15 minutes, and the agent resumes after control is returned. Async subagents run on their own threads in the shared sandbox, while the orchestrator remains available to the user and can check, update, or cancel tasks. Results reach the agent during a run, wake it when idle, or wait until an approval is answered. The release also routes replies to the originating Slack thread and adds run cancellation there. Breaking changes include removing `connectors.mcp()` and the `connectors/` layout; MCP servers now go in `tools/mcp.ts` or `tools/mcp.py`. For `LANGSMITH_*` variables, shell environment values now take precedence over project `.env` values.

### Source excerpt

Managed Deep Agents v0.10 adds browser use, so agents can work on sites with no API and hand you the window to sign in, and async subagents for background work.

## Browser Use in Managed Deep Agents

DevFeed: [Browser Use in Managed Deep Agents](<https://devfeed.tech/articles/browser-use-in-managed-deep-agents-107264.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/browser-use-in-managed-deep-agents>)

Author: LangChain Accounts

Published: 2026-10-29T16:45:29Z

Content type: release

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Selenium](<https://devfeed.tech/topics/selenium.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [Web app](<https://devfeed.tech/topics/webapp.md>)

Tags: [accessibility](<https://devfeed.tech/tags/accessibility.md>), [acme](<https://devfeed.tech/tags/acme.md>), [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-sandbox](<https://devfeed.tech/tags/agent-sandbox.md>), [agent-tools](<https://devfeed.tech/tags/agent-tools.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [all](<https://devfeed.tech/tags/all.md>), [also](<https://devfeed.tech/tags/also.md>), [api](<https://devfeed.tech/tags/api.md>), [browser](<https://devfeed.tech/tags/browser.md>), [can](<https://devfeed.tech/tags/can.md>), [context](<https://devfeed.tech/tags/context.md>), [deep](<https://devfeed.tech/tags/deep.md>), [managed](<https://devfeed.tech/tags/managed.md>), [sign](<https://devfeed.tech/tags/sign.md>), [sign-in](<https://devfeed.tech/tags/sign-in.md>), [tools](<https://devfeed.tech/tags/tools.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

Managed Deep Agents provides a remote browser and tools for agents to interact with rendered pages when an API cannot cover a task, and to test apps running in the agent's sandbox. Add it by exporting `define_browser` from `browser.py`; `scope="thread"` starts a clean session for each thread, while `scope="user"` shares browser state and logins across a user's threads, with a separate window per thread. Sessions stop after the configured idle timeout. When sign-in is needed, `browser_handoff` lets a person use the same browser and return it to the agent without sharing a password in model messages. Tools include accessibility snapshots, batched actions or Playwright-style code, screenshots, and handoff. For app testing, a private `localhost` bridge lets the remote browser reach the app in the agent sandbox. On 100 WebVoyager tasks, the authors report a 90% pass rate for $1.98 total, compared with 89% for Browserbase's MCP server at nine times the cost; this is the reported result of their toolset comparison.

### Source excerpt

Managed Deep Agents now runs a browser for your agent, with tools tuned for context-efficient browser use and a handoff so you can sign in yourself.

## 3 Ways AI Agents Already Operate in Your Browser

DevFeed: [3 Ways AI Agents Already Operate in Your Browser](<https://devfeed.tech/articles/3-ways-ai-agents-already-operate-in-your-browser-106423.md>)

Original publisher: [Read original article](<https://www.bleepingcomputer.com/news/security/3-ways-ai-agents-already-operate-in-your-browser/>)

Author: Sponsored by Keep Aware

Published: 2026-10-29T14:00:10Z

Content type: article

Language: en

Sources: [BleepingComputer](<https://devfeed.tech/sources/bleepingcomputer.md>)

Topics: [AI Bots](<https://devfeed.tech/topics/ai-bots.md>), [agentic browsing](<https://devfeed.tech/topics/agentic-browsing.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>), [shadow AI](<https://devfeed.tech/topics/shadow-ai.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [api](<https://devfeed.tech/tags/api.md>), [applications](<https://devfeed.tech/tags/applications.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browsers](<https://devfeed.tech/tags/browsers.md>), [computer-help](<https://devfeed.tech/tags/computer-help.md>), [computer-security](<https://devfeed.tech/tags/computer-security.md>), [computers](<https://devfeed.tech/tags/computers.md>), [control](<https://devfeed.tech/tags/control.md>), [corporate](<https://devfeed.tech/tags/corporate.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [data](<https://devfeed.tech/tags/data.md>), [employees](<https://devfeed.tech/tags/employees.md>), [infosec](<https://devfeed.tech/tags/infosec.md>), [keep-aware](<https://devfeed.tech/tags/keep-aware.md>), [linux](<https://devfeed.tech/tags/linux.md>), [mac](<https://devfeed.tech/tags/mac.md>), [malware](<https://devfeed.tech/tags/malware.md>), [malware-removal](<https://devfeed.tech/tags/malware-removal.md>), [security](<https://devfeed.tech/tags/security.md>), [security-tools](<https://devfeed.tech/tags/security-tools.md>), [sensitive-data](<https://devfeed.tech/tags/sensitive-data.md>), [spyware](<https://devfeed.tech/tags/spyware.md>), [support](<https://devfeed.tech/tags/support.md>), [tech-support](<https://devfeed.tech/tags/tech-support.md>), [technical-support](<https://devfeed.tech/tags/technical-support.md>), [tools](<https://devfeed.tech/tags/tools.md>), [users](<https://devfeed.tech/tags/users.md>), [virus](<https://devfeed.tech/tags/virus.md>), [virus-removal](<https://devfeed.tech/tags/virus-removal.md>), [windows](<https://devfeed.tech/tags/windows.md>)

### AI overview

AI agents can operate in authenticated browsers through external control using Chrome DevTools Protocol (CDP), browser extensions or agentic browsers, and emerging website-exposed tools under WebMCP. CDP lets external applications control debuggable Chromium browsers, including tabs with corporate sessions. Extensions can read pages and interact with tabs using permissions such as scripting and debugger access; agentic browsers may fall outside existing extension controls. In both cases, actions may appear under the employee's identity, and agents can be influenced by instructions embedded in untrusted content. WebMCP lets agents invoke structured tools supplied by websites instead of interpreting pages and simulating clicks; its specification is evolving, and tool definitions can themselves be misleading or malicious. The article recommends organizations assess which agents and debuggable browsers can access corporate sessions, what data agents can send to website tools, and whether their activity is visible and controllable. It argues existing endpoint, network and application controls may not reveal what an agent reads or does inside an authenticated tab.

### Source excerpt

AI agents can control authenticated browsers, interact with corporate applications, and access sensitive data while appearing to act as legitimate employees. Keep Aware examines three ways agents operate inside browsers and why traditional security tools may struggle to distinguish their activity from human users. [...]

## Best Browser.lol Alternatives for Web Testing in 2026

DevFeed: [Best Browser.lol Alternatives for Web Testing in 2026](<https://devfeed.tech/articles/best-browser-lol-alternatives-for-web-testing-in-2026-107250.md>)

Original publisher: [Read original article](<https://testgrid.io/blog/browser-lol-alternatives/>)

Author: Yogesh Solanki

Published: 2026-10-29T11:44:38Z

Content type: comparison

Language: en

Sources: [TestGrid](<https://devfeed.tech/sources/testgrid-blog.md>)

Topics: [browser](<https://devfeed.tech/topics/browser.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Selenium](<https://devfeed.tech/topics/selenium.md>), [Firefox](<https://devfeed.tech/topics/firefox.md>), [Firefox extension](<https://devfeed.tech/topics/firefox-extension.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [staging](<https://devfeed.tech/topics/staging.md>), [Google Chrome](<https://devfeed.tech/topics/google-chrome.md>), [Edge](<https://devfeed.tech/topics/edge.md>), [Internet Explorer](<https://devfeed.tech/topics/internet-explorer.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [alternatives](<https://devfeed.tech/tags/alternatives.md>), [automated](<https://devfeed.tech/tags/automated.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [best](<https://devfeed.tech/tags/best.md>), [blog](<https://devfeed.tech/tags/blog.md>), [browser](<https://devfeed.tech/tags/browser.md>), [browser-lol-alternatives](<https://devfeed.tech/tags/browser-lol-alternatives.md>), [can](<https://devfeed.tech/tags/can.md>), [cd](<https://devfeed.tech/tags/cd.md>), [ci](<https://devfeed.tech/tags/ci.md>), [ci-cd](<https://devfeed.tech/tags/ci-cd.md>), [ci-cd-pipeline](<https://devfeed.tech/tags/ci-cd-pipeline.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cross-browser-testing](<https://devfeed.tech/tags/cross-browser-testing.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [deployment-flexibility](<https://devfeed.tech/tags/deployment-flexibility.md>), [device](<https://devfeed.tech/tags/device.md>), [flexibility](<https://devfeed.tech/tags/flexibility.md>), [testing](<https://devfeed.tech/tags/testing.md>), [web](<https://devfeed.tech/tags/web.md>)

### AI overview

Browser.lol provides isolated remote browser sessions, but the text says its limited sessions and browser choices, beta saved profiles, and lack of broader testing features can constrain QA teams. The alternatives serve different needs: Kasm Workspaces and Cloudflare Browser Isolation focus on secure remote browsing; Multilogin, Sendwin, and Firefox Multi-Account Containers separate account profiles; Browserling supports live manual checks across desktop browsers; TestGrid offers cloud cross-browser and mobile testing, parallel runs, Selenium Grid, and CI/CD integrations; Steel and Browserless provide programmable browser infrastructure for automation and agents; Hyperbrowser supports prompt-driven web workflows and reusable session state. Tradeoffs named include setup or learning effort, performance issues, privacy risks, and costs. The text recommends choosing by testing coverage, automation, security, deployment, and budget, but provides no independent comparative test results.

### Source excerpt

Browser.lol can be a great platform for QA engineers and software testers who need quick access to isolated browser sessions to assess website behavior. However, Browser. lol lacks automated regression testing, broad real-device coverage, CI/CD pipeline integrations, persistent browser profiles, multi-browser testing, and deployment flexibility. In this blog, we'll look at the best alternatives to [...]

## Lightpanda: Jev picks login fields in 0.53s

DevFeed: [Lightpanda: Jev picks login fields in 0.53s](<https://devfeed.tech/articles/lightpanda-jev-picks-login-fields-in-0-53s-104327.md>)

Original publisher: [Read original article](<https://jevdaily.com/issues/2026-10-28>)

Author: Jev Daily

Published: 2026-10-28T12:34:48.658127Z

Content type: news

Language: en

Sources: [Jev Daily](<https://devfeed.tech/sources/jev-daily.md>)

Topics: [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [ads](<https://devfeed.tech/tags/ads.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [api](<https://devfeed.tech/tags/api.md>), [browser](<https://devfeed.tech/tags/browser.md>), [built-with-it](<https://devfeed.tech/tags/built-with-it.md>), [claude-haiku-5-5](<https://devfeed.tech/tags/claude-haiku-5-5.md>), [cost](<https://devfeed.tech/tags/cost.md>), [discount](<https://devfeed.tech/tags/discount.md>), [experiment](<https://devfeed.tech/tags/experiment.md>), [fields](<https://devfeed.tech/tags/fields.md>), [jev](<https://devfeed.tech/tags/jev.md>), [login](<https://devfeed.tech/tags/login.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [measurement](<https://devfeed.tech/tags/measurement.md>), [meta-ads](<https://devfeed.tech/tags/meta-ads.md>), [password](<https://devfeed.tech/tags/password.md>), [router](<https://devfeed.tech/tags/router.md>), [someone-measured-it](<https://devfeed.tech/tags/someone-measured-it.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

Lightpanda reports that Jev selected the username and password fields and submit button on a login page in 0.53 seconds using 2 calls. It compares this with 7.83 seconds and 8 browser-tool calls for Claude Haiku 5.5. The excerpt does not specify how many pages or sites were tested, so the figures do not establish performance across broader workloads.

### Source excerpt

Lightpanda put Jev on the login step of its browser agent and posted 0.53 seconds and 2 calls against 7.83 seconds and 8 tool calls for Claude Haiku 5.5. One...

## I Broke a Browser Agent on Purpose. Spotting the Fault Was Not the Same as Fixing It

DevFeed: [I Broke a Browser Agent on Purpose. Spotting the Fault Was Not the Same as Fixing It](<https://devfeed.tech/articles/i-broke-a-browser-agent-on-purpose-spotting-the-fault-was-not-the-same-as-fixing-it-102453.md>)

Original publisher: [Read original article](<https://towardsdatascience.com/i-broke-a-browser-agent-on-purpose-spotting-the-fault-was-not-the-same-as-fixing-it/>)

Author: Abdullahi Dattijo

Published: 2026-10-27T15:30:00Z

Content type: article

Language: en

Sources: [Towards Data Science](<https://devfeed.tech/sources/towards-data-science.md>)

Topics: [Browser Automation](<https://devfeed.tech/topics/browser-automation.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [browser](<https://devfeed.tech/topics/browser.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2026](<https://devfeed.tech/tags/2026.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [actions](<https://devfeed.tech/tags/actions.md>), [added](<https://devfeed.tech/tags/added.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [ai-safety](<https://devfeed.tech/tags/ai-safety.md>), [ai-tool](<https://devfeed.tech/tags/ai-tool.md>), [browser](<https://devfeed.tech/tags/browser.md>), [clicks](<https://devfeed.tech/tags/clicks.md>), [embedded](<https://devfeed.tech/tags/embedded.md>), [first](<https://devfeed.tech/tags/first.md>), [half](<https://devfeed.tech/tags/half.md>), [i](<https://devfeed.tech/tags/i.md>), [inside](<https://devfeed.tech/tags/inside.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [llm-evaluation](<https://devfeed.tech/tags/llm-evaluation.md>), [model](<https://devfeed.tech/tags/model.md>), [playwright](<https://devfeed.tech/tags/playwright.md>), [simple](<https://devfeed.tech/tags/simple.md>)

### AI overview

A browser check can identify an action fault without enabling the agent to recover when the parser or executor keeps sending the same wrong action. In a small experiment, the author replayed 80 previously successful Claude Haiku 5.5 decisions through four deliberately broken browser paths. Generic page-state checks missed half of wrong clicks and falsely warned on every successful embedded-frame click; screenshot comparison found few corrupted searches and warned on every working search. Outcome checks, tailored to each requested result, detected all injected faults without false alarms in this setup. Yet retries through unchanged broken code still failed on searches and clicks. Checks helped when the agent could use new evidence: they prevented unnecessary frame clicks and prompted another chart observation, raising chart completion from 56/60 to 60/60, though the estimated gain ranged from 0 to 15 percentage points. The study used one simple site, one model and prompt, and 20 layouts for completion; its counts do not establish performance on other websites. The practical lesson is to log the model's request, image and viewport dimensions, action sent, target state, and resulting;

### Source excerpt

I replayed correct model decisions through four broken browser actions. A simple page check missed half of the wrong clicks, and raised a false alarm on every click that worked inside an embedded page. The post I Broke a Browser Agent on Purpose. Spotting the Fault Was Not the Same as Fixing It appeared first on Towards Data Science.

## Claude Desktop v2.0: You Don't Need VS Code Anymore!

DevFeed: [Claude Desktop v2.0: You Don't Need VS Code Anymore!](<https://devfeed.tech/articles/claude-desktop-v2-0-you-don-t-need-vs-code-anymore-91218.md>)

Original publisher: [Read original article](<https://www.productcompass.pm/p/claude-desktop-code-tab>)

Author: Paweł Huryn

Published: 2026-10-20T15:12:41Z

Content type: tutorial

Language: en

Sources: [The Product Compass](<https://devfeed.tech/sources/the-product-compass.md>)

Topics: [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Visual Studio Code](<https://devfeed.tech/topics/visual-studio-code.md>), [generative-ai-tools](<https://devfeed.tech/topics/generative-ai-tools.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [codex](<https://devfeed.tech/topics/codex.md>)

Tags: [agentic-systems](<https://devfeed.tech/tags/agentic-systems.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agents-md](<https://devfeed.tech/tags/agents-md.md>), [ai](<https://devfeed.tech/tags/ai.md>), [analyze](<https://devfeed.tech/tags/analyze.md>), [apps](<https://devfeed.tech/tags/apps.md>), [artifacts](<https://devfeed.tech/tags/artifacts.md>), [automate](<https://devfeed.tech/tags/automate.md>), [claude](<https://devfeed.tech/tags/claude.md>), [code](<https://devfeed.tech/tags/code.md>), [collections](<https://devfeed.tech/tags/collections.md>), [courses](<https://devfeed.tech/tags/courses.md>), [desktop](<https://devfeed.tech/tags/desktop.md>), [features](<https://devfeed.tech/tags/features.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-servers](<https://devfeed.tech/tags/mcp-servers.md>), [servers](<https://devfeed.tech/tags/servers.md>), [skills](<https://devfeed.tech/tags/skills.md>), [v2](<https://devfeed.tech/tags/v2.md>), [vs-code](<https://devfeed.tech/tags/vs-code.md>)

### AI overview

The article recommends Claude Desktop's Code tab as a lower-friction way for Product Managers to prototype and build with Claude Code without VS Code. It describes local project folders with AGENTS.md instructions, connector and permission setup, reusable skills, and a built-in browser for running apps and reviewing changes. The author says Cowork lacks app previews, project-specific skills and connections, guardrails, and AGENTS.md support, and reports that its 10 GB virtual machine limit became restrictive in their tests. Other described features include artifacts, scheduled tasks, remote control, cloud sessions, and session compaction. Code access requires a paid Pro, Max, Team, or Enterprise subscription; the article's model and usage recommendations reflect the author's experience.

### Source excerpt

How to start, the features that matter for PMs, and why I now recommend the Code tab. Plus my collections of skills, MCP servers, free courses, and AGENTS.md snippets.

## WebMCP -- browser-native tools for agents

DevFeed: [WebMCP -- browser-native tools for agents](<https://devfeed.tech/articles/webmcp-browser-native-tools-for-agents-89093.md>)

Original publisher: [Read original article](<https://specification.website/spec/agent-readiness/webmcp/>)

Author: Joost de Valk

Published: 2026-10-16T00:00:00Z

Content type: tutorial

Language: en

Sources: [The Website Specification](<https://devfeed.tech/sources/the-website-specification.md>)

Topics: [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>)

Tags: [agent-readiness](<https://devfeed.tech/tags/agent-readiness.md>), [ai](<https://devfeed.tech/tags/ai.md>), [browser-agents](<https://devfeed.tech/tags/browser-agents.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [optional](<https://devfeed.tech/tags/optional.md>), [webmcp](<https://devfeed.tech/tags/webmcp.md>)

### AI overview

The article explains how WebMCP lets web pages expose structured JavaScript tools to AI agents running in the browser. It covers feature detection, deferred script loading, schema and safety annotations, error handling, and matching browser tools with server-side MCP tools. The API is still early, so the article recommends treating it as optional until a major browser supports it without a flag.

### Source excerpt

WebMCP lets a page register tools that an in-browser AI agent can call directly, using the `document.modelContext` JavaScript API. It turns a site into an agent surface without server-side MCP plumbing.

## Building agents that transact with Anchor Browser and AgentCore payments

DevFeed: [Building agents that transact with Anchor Browser and AgentCore payments](<https://devfeed.tech/articles/building-agents-that-transact-with-anchor-browser-and-agentcore-payments-86370.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/building-agents-that-transact-with-anchor-browser-and-agentcore-payments/>)

Author: Cher Simon

Published: 2026-10-13T20:10:33Z

Content type: tutorial

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [agentic browsing](<https://devfeed.tech/topics/agentic-browsing.md>)

Tags: [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [automation](<https://devfeed.tech/tags/automation.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [x402](<https://devfeed.tech/tags/x402.md>)

### AI overview

The article describes an integration that lets AI agents access x402-protected web pages and APIs by handling payment challenges within an Anchor Browser session. Amazon Bedrock AgentCore payments checks session budgets, signs transactions through a configured wallet provider, and keeps wallet credentials out of the agent runtime. It also walks through setup, payment flow, and spending controls.

### Source excerpt

Learn how the AWS Generative AI Innovation Center Partner Agent Factory and Anchor Browser built AI agents that autonomously pay for x402-protected web resources and APIs. Amazon Bedrock AgentCore payments checks budgets, signs transactions, and retries requests without exposing wallet credentials to the agent runtime.

## How we built the Redis Docs MCP for agents

DevFeed: [How we built the Redis Docs MCP for agents](<https://devfeed.tech/articles/how-we-built-the-redis-docs-mcp-for-agents-84245.md>)

Original publisher: [Read original article](<https://redis.io/blog/how-we-built-the-redis-docs-mcp-for-agents/>)

Author: Vishal Bala

Published: 2026-10-09T00:00:00Z

Content type: article

Language: en

Sources: [Redis Blog](<https://devfeed.tech/sources/redis-blog-2.md>), [Redis Blog](<https://devfeed.tech/sources/redis-blog.md>)

Topics: [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Redis](<https://devfeed.tech/topics/redis.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>), [database-optimization](<https://devfeed.tech/topics/database-optimization.md>)

Tags: [autoscaling](<https://devfeed.tech/tags/autoscaling.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineering-ai](<https://devfeed.tech/tags/engineering-ai.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [redis](<https://devfeed.tech/tags/redis.md>)

### AI overview

The Redis team describes building Redis Docs MCP, a public server that lets MCP clients search and fetch Redis documentation or ask questions through a retrieval and language model pipeline. The article explains the service architecture, anonymous access and privacy constraints, design review practices for agent-assisted development, citation handling, and retrieval evaluation. It reports improvements in recall for simple lookups and hybrid search, while noting tradeoffs in multi-hop precision and top-result ranking.

### Source excerpt

Ask a coding agent how to configure eviction in Redis 8 and you'll usually get an answer. Less often than we'd like, that answer comes from authoritative docs. The agent either recalls something from pretraining, or it scrapes the rendered HTML off re...

## The road to the agentic browser: A Kitesurf update

DevFeed: [The road to the agentic browser: A Kitesurf update](<https://devfeed.tech/articles/the-road-to-the-agentic-browser-a-kitesurf-update-60800.md>)

Original publisher: [Read original article](<https://blog.cloudflare.com/kitesurf-update/>)

Author: Celso Martinho

Published: 2026-09-28T13:00:00Z

Content type: release

Language: en

Sources: [Cloudflare Blog](<https://devfeed.tech/sources/cloudflare-blog.md>)

Topics: [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [agentic browsing](<https://devfeed.tech/topics/agentic-browsing.md>), [Web](<https://devfeed.tech/topics/web.md>), [Cloudflare Workers](<https://devfeed.tech/topics/cloudflare-workers.md>), [Web platform](<https://devfeed.tech/topics/web-platform.md>), [WebSocket](<https://devfeed.tech/topics/websocket.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [birthday-week](<https://devfeed.tech/tags/birthday-week.md>), [cloudflare](<https://devfeed.tech/tags/cloudflare.md>), [cloudflare-workers](<https://devfeed.tech/tags/cloudflare-workers.md>), [iframe](<https://devfeed.tech/tags/iframe.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [json](<https://devfeed.tech/tags/json.md>), [remote-browser-isolation](<https://devfeed.tech/tags/remote-browser-isolation.md>), [web-platform](<https://devfeed.tech/tags/web-platform.md>), [webmcp](<https://devfeed.tech/tags/webmcp.md>), [workers](<https://devfeed.tech/tags/workers.md>)

### AI overview

Cloudflare reports updates to Kitesurf, its browser for AI agents running on Cloudflare Workers. The update adds WebMCP support and browser API capabilities, including URL-based module resolution, JSON modules, and import map handling. It also describes improved iframe behavior and expanded Web Platform Tests coverage.

### Source excerpt

We've updated Kitesurf, our Workers-based browser for AI agents, with WebMCP support, improved DOM performance, and terminal-based rendering. With over 730,000 Web Platform subtests passing, agents can now navigate complex sites faster.

## Local AI Weekly #2: Agents Everywhere

DevFeed: [Local AI Weekly #2: Agents Everywhere](<https://devfeed.tech/articles/local-ai-weekly-2-agents-everywhere-48035.md>)

Original publisher: [Read original article](<https://feed.itsfoss.com/link/24361/17463615/local-ai-weekly-2>)

Author: Abhishek Prakash

Published: 2026-09-16T15:01:03Z

Content type: article

Language: en

Sources: [It's FOSS](<https://devfeed.tech/sources/it-s-foss.md>)

Topics: [Local AI](<https://devfeed.tech/topics/local-ai.md>), [Developer Tools](<https://devfeed.tech/topics/developer-tools.md>), [debugging](<https://devfeed.tech/topics/debugging.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [Continuous integration](<https://devfeed.tech/topics/continuous-integration.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [open webui](<https://devfeed.tech/topics/open-webui.md>)

Tags: [agent-inspect](<https://devfeed.tech/tags/agent-inspect.md>), [agents](<https://devfeed.tech/tags/agents.md>), [agntcon](<https://devfeed.tech/tags/agntcon.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-automation](<https://devfeed.tech/tags/ai-automation.md>), [ai-labs](<https://devfeed.tech/tags/ai-labs.md>), [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [alibaba](<https://devfeed.tech/tags/alibaba.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [browser](<https://devfeed.tech/tags/browser.md>), [debuggers](<https://devfeed.tech/tags/debuggers.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [local](<https://devfeed.tech/tags/local.md>), [local-ai](<https://devfeed.tech/tags/local-ai.md>), [local-ai-weekly](<https://devfeed.tech/tags/local-ai-weekly.md>), [memory](<https://devfeed.tech/tags/memory.md>), [newsletter](<https://devfeed.tech/tags/newsletter.md>), [tool](<https://devfeed.tech/tags/tool.md>), [weekly](<https://devfeed.tech/tags/weekly.md>)

### AI overview

This issue surveys local AI tools focused on agent oversight and operation: agent-inspect shows TypeScript agent runs as execution trees and can fail CI checks; AutoMem adds locally hosted persistent memory through MCP; Tencent's BrowserSkill uses a visible agent window, asks to borrow an open browser tab, and returns control for captchas or logins. The Rust tool llmfit detects system hardware and ranks open models by size, speed, quality, and context, with optional Ollama downloads. For Ollama users, extending OLLAMA_KEEP_ALIVE can avoid reload delays after idle periods; the default five-minute unload can still help when sharing a GPU among several large models. The issue also notes Linux transcription in closed-source LM Studio, previews Unsloth without endorsing its performance claims, and summarizes several MoE model releases with varying hardware needs.

### Source excerpt

Debuggers, memory, and a browser for your agents. And a tool that finally tells you what your hardware can run.

[Next page](<https://devfeed.tech/topics/agent-browser.md?cursor=WyIyMDI2LTA5LTE2VDE1OjAxOjAzKzAwOjAwIiwgIjAzMmY1OTcwLThjNmQtNDQ5NS04ZDQ1LWRjMmNhNGYzYzcwYiJd>)