Browser Agent

Vital signs

Why it's on the table

On the table, Browser Agent (Bu) is seat 11 of 58, in the Agents & Automation family. It is an experimental element — promising, volatile, and worth a contained experiment rather than a commitment. Budget curiosity, not dependence. It is optional: plenty of companies run without it — until a specific trigger (scale, regulation, cost, or customers) makes it essential for them. It sits in the lowest paid band — lunch money against the hours it returns.

Browser Agent: the top 5 — v2026.Q3

Edition v2026.Q3 · ranking, pricing and status verified 2026-08-06.

1. 1Claude in ChromeAnthropic

   Included in paid Claude plans (Pro $17–20/mo · Max $100–200/mo · Team/Enterprise) · beta

   Best for Founders and teams who want an agent working inside their real, logged-in browser — inbox triage, form filling, dashboard extraction, scheduled recurring tasks — with admin-managed site controls.

   The safety-engineering leader in a category defined by prompt-injection risk: Anthropic published red-team numbers (123 cases, 29 attack scenarios; success rate 23.6%→11.2% after mitigations, 35.7%→0% on four browser-specific attacks) and shipped org-wide allowlists/blocklists when it expanded from Max-only to all paid plans (Dec 18, 2025). It is also the best-integrated: hands for Claude Code (build in terminal, verify in browser) and Cowork, plus multi-tab work, background tasks, and cron-style scheduled browsing.

   Watch Still labeled beta with 'unique risks' — Anthropic itself tells you to keep it away from financial transactions and passwords. Chrome-desktop-only, no API surface: this is an assistant, not infrastructure you can build a product on.

   Prompt-injection attack success 23.6%→11.2% after mitigations; 35.7%→0% on four browser-specific attack types (Aug 2025 red-team, 123 cases) [src] · Expanded from 1,000-user Max pilot (Aug 2025) to all Max (Nov 24, 2025) to Pro/Team/Enterprise with admin site allowlists (Dec 18, 2025) [src] · Scheduled recurring browser tasks, multi-tab groups, background runs, Claude Code integration (verified Aug 2026) [src]
   Site →Docs →

2. 2Browser-useBrowser Use (YC W25, MIT)

   OSS free (MIT) + your LLM tokens · Cloud: browsers $0.02/hr metered by minute, hosted agents from $0.36/M input · $1.44/M output tokens

   Best for Engineers building their own browser automation — the open-source library that turns any LLM into a web agent, with a usage-priced cloud when you outgrow localhost.

   The open-source standard: 107k GitHub stars (Aug 2026), MIT-licensed, Python + TypeScript, any model provider — it is the layer Manus and 20+ YC startups were built on. Its DOM-to-text approach (parse interactive elements instead of screenshots) made agents cheaper and more reliable than vision-first designs, and the repo claims #1 on the Odysseys long-horizon benchmark (87.4% across 200 web tasks). $17M seed led by Felicis (Mar 2025) with Paul Graham participating.

   Watch Quality is whatever model you plug in, and long agent runs burn tokens fast. The cloud business is young and the space is crowded with better-capitalized infra (Browserbase); benchmark claims are self-reported.

   107.1k GitHub stars, MIT license, ~9.9k commits (Aug 2026) [src] · $17M seed led by Felicis, with Paul Graham, A Capital, Nexus (Mar 23, 2025) [src] · Self-reported #1 on Odysseys leaderboard: 87.4% avg across 200 long-horizon web tasks (repo, Aug 2026) [src]
   Site →Docs →

3. 3Browserbase + StagehandBrowserbase

   Free tier · Developer $20/mo (100 browser-hrs, $0.12/hr after) · Startup $99/mo · Enterprise custom; Stagehand SDK free (MIT)

   Best for Production browser automation at scale — headless browser fleets with proxies, captcha solving, session replay, and Stagehand's self-healing act/extract/observe primitives on top.

   The infrastructure pick: $40M Series B at a $300M valuation (Jun 2025), ~50M sessions served in 2025, and marquee production users — Airtable built its Hyperagent platform on it (Jul 2026), Amplitude runs sales automation on it. Stagehand (MIT, ~23k stars, TypeScript + Python) is the most credible middle path between brittle Playwright selectors and fully autonomous agents, and the Jun 30, 2026 'Browserbase Agents' launch added fully managed prompt-to-agent runs.

   Watch Costs compound at volume (browser-hours + proxies + agent runs are metered separately). The captcha/anti-bot arms race means reliability on hostile sites is never guaranteed, and its new managed Agents put it in competition with its own customers.

   $40M Series B at $300M valuation (Jun 2025); ~50M sessions in 2025 [src] · Airtable's Hyperagent built on Browserbase (customer story, Jul 2, 2026); Browserbase Agents launched Jun 30, 2026 [src] · Stagehand: MIT, act/extract/observe/agent primitives, TS + Python, self-healing automations (verified Aug 2026) [src]
   Site →Docs →

4. 4Perplexity CometPerplexity

   Free · Comet Plus $5/mo · Pro $20/mo · Max $200/mo (background assistants) · Enterprise from $40/seat

   Best for A free, full agentic browser for research-heavy individual work — summarize, compare across tabs, handle email, shop — on Mac, Windows, iOS, and Android.

   The distribution winner among standalone AI browsers — and after Atlas's retirement, effectively the last one standing at scale: free worldwide since Oct 2025, Android (Nov 2025) and iOS (Mar 2026) apps, enterprise MDM deployment since Mar 2026. Its assistant works inside your logged-in sessions, which is exactly why Amazon sued — making Comet the test case for whether user agents may act in authenticated accounts.

   Watch The Amazon CFAA litigation (preliminary injunction Mar 2026, stayed pending Ninth Circuit appeal) could constrain logged-in commerce agents for everyone. Security researchers keep landing hits (CometJacking; a sub-4-minute phishing demo, Mar 2026). Consumer product, no developer API.

   Launched Jul 9, 2025 (Mac/Windows); free worldwide Oct 2025; Android Nov 20, 2025; iOS Mar 18, 2026 [src] · Amazon legal demand over agentic shopping in logged-in accounts (Nov 2025); Perplexity refused — 'users have a right to employ AI agents' [src] · Free tier + Comet Plus $5/mo + Pro $20/mo + Max $200/mo with autonomous background assistants (2026 pricing) [src]
   Site →Docs →

5. 5Playwright MCPMicrosoft

   Free, Apache-2.0 · your LLM tokens only

   Best for Giving any MCP-speaking agent (Claude Code, Cursor, VS Code, Cline) deterministic browser hands — testing your own app, verifying agent-built UIs, automating cooperative sites.

   The dev-loop default by sheer volume: 6.3M npm downloads per week (Aug 2026) and 35.5k stars. Its accessibility-snapshot approach — structured a11y trees instead of screenshots — is fast, cheap, and works without vision models, with 60+ tools covering navigation, network mocking, and trace recording. If your coding agent needs to see and click what it just built, this is the free, boring, correct answer.

   Watch A tool server, not an agent — you bring the loop and the judgment. No stealth, proxies, or captcha handling, so it struggles on hostile third-party sites; snapshot-heavy sessions get token-expensive on long tasks (Microsoft itself notes CLI workflows are more token-efficient at high throughput).

   6.30M weekly npm downloads (week of Jul 30–Aug 5, 2026) [src] · 35.5k GitHub stars, Apache-2.0, 60+ tools (Aug 2026) [src] · Accessibility snapshots over screenshots — no vision model required, deterministic tool application [src]
   Site →Docs →

Browser Agent: the top 8 compared

Edition v2026.Q3 · ranking, pricing and status verified 2026-08-06.

How to choose your browser agent

If the site has an API or MCP server

Use it and skip this element — browser agents are for the long tail without APIs. They are slower, costlier, and more brittle than any real integration, and the vendor may sue (see Amazon v. Perplexity).

If you want an agent doing your browsing — inbox, dashboards, forms, recurring chores — under your eyes

Claude in Chrome on your existing paid plan; keep 'ask before acting' on for anything sensitive and let admins pin the site allowlist.

If you are building browser automation into your product

Prototype on Browser-use (free, MIT, any model); move to Browserbase + Stagehand when you need proxies, captcha solving, concurrency, and replay in production.

If the browser work is your own app — E2E tests, verifying what your coding agent just built

Playwright MCP. Free, deterministic, no stealth needed on sites you control, and every coding agent already speaks MCP.

If you automate other companies' logged-in sites at commercial scale

Get counsel before code. The Amazon v. Perplexity injunction fight (Ninth Circuit, argued Jun 11, 2026) is deciding whether authenticated agent access is a CFAA violation — and 4 of 7 agentic browsers failed a Jul 2026 same-origin security audit.

Browser Agent: the whole field

21 more tools tracked in this category, including 9 dead, renamed, or sunsetting — a reference that hides the graveyard isn't one. Verified 2026-08-06.

Browser Agent: the category in numbers

Edition v2026.Q3 · ranking, pricing and status verified 2026-08-06.

• The Great Consolidation: in ~60 days OpenAI announced Atlas's retirement (Jul 9 → dead Aug 9, 2026), Microsoft folded Copilot Mode into Edge (May 13), and Google folded Mariner into Gemini/Chrome (May) — agents are disappearing into surfaces people already use [src]
• Manus — the viral agent built on Browser-use — is 'now part of Meta' (site banner, 2026): big tech is buying the layer, not just building it [src]
• Amazon v. Perplexity is the first federal appellate test of whether AI agents may act in users' authenticated accounts: demand Nov 2025, preliminary injunction Mar 10, 2026 (stayed), Ninth Circuit argued Jun 11, 2026 [src]
• Security is the binding constraint: 4 of 7 agentic browsers let attackers bypass same-origin policy (Univ. of Washington, Jul 3, 2026); the safest (Firefox AI) was also the least capable [src]
• Money kept flowing to infra: Browser-use $17M seed (Mar 2025), Browserbase $40M Series B at $300M (Jun 2025), Genspark $160M at $530M — while consumer AI browsers died or were acquired (Atlas, TBC/Dia $610M) [src]
• Standards arriving: Playwright MCP at 6.3M weekly npm downloads (Aug 2026); WebMCP — sites exposing tools directly to agents — in Chrome 149 origin trial (Jun 2026), backed by Google and Microsoft via W3C [src]

Browser Agent: method & sources

Ranking criteria: production-worthiness for a small AI-led company (safety controls, reliability, price) over raw autonomy demos; assisted browsing and programmatic automation are both in-scope jobs. Atlas retirement caveat: the Aug 9, 2026 shutdown (announced Jul 9) is confirmed by two independent secondary sources citing an OpenAI help-center article ('Evolving Atlas into ChatGPT'), but we could not fetch that primary page directly — re-verify. Conflict resolved: Anthropic's support doc still says Max-only beta while claude.com and the Dec 18, 2025 blog say all paid plans — we follow the newer product page. Amazon-injunction dates (Mar 10, 2026; Ninth Circuit Jun 11) are single-source (nohacks.co); the underlying dispute is primary-verified via Perplexity's Nov 2025 post. Browserbase's '50M sessions in 2025' is from a Firecrawl roundup, not Browserbase's own pages. Browser-use's Odysseys #1 is self-reported in its README; no neutral browser-agent leaderboard has category authority in Aug 2026 (WebVoyager numbers float 85–89% across vendors, all self-run). Adjacent elements: scraping/data-extraction APIs (Firecrawl) and computer-use model APIs belong with their model/data elements, not here; workflow tools that merely trigger browsers → Wf; agent loops you build yourself → Ag; MCP servers generally → Mc. Comet user counts: Perplexity has never published Comet MAU — treat any figure as modeled. Ranking criteria: verified commercial traction, independent satisfaction surveys, agent benchmarks, and founder-fit (price floor, lock-in, surfaces). Editorial, never paid — the charter. Machine-readable twin: bu.json.

Our take

Powerful, brittle, improving monthly. Use for the long tail; use real APIs everywhere one exists.

Combines with