Browser Automation & Computer Use
Agents that drive browsers, desktops and terminals. As of 2026-11-21, 884 indexed products match this category (378 with full profiles); 423 were published in the last 90 days, against 170 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, Browser Use leads, holding 7% of the stars of the 750 products here with their own repository. The most common form is MCP servers (84% of indexed products).
CategorySegment label: Lagging the catalogue DER
Segment statistics
Whole catalogue (all 884 indexed products, not only profiled ones). Calculated 2026-11-21.
Lagging the catalogue. Mid-sized for its level, with launches growing more slowly than the catalogue’s. Size is ranked against the other category nodes; momentum compares this node’s launches in the last 90 days with the 90 before, relative to the whole catalogue’s ratio (score 62 or more = faster, 38 or less = slower; below 5 dated launches it is not measured and the label uses size alone).
Concentration. The Herfindahl–Hirschman index (HHI) adds up each project’s squared share of stars. At 0.032, attention is spread as if across about 32 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is unconcentrated. Stars measure attention, not usage or quality.
Which product forms serve it
The same need is met by MCP servers, agent skills, plugins, extensions and frameworks. This counts each form across the whole catalogue.
| Product type | Indexed | Share | With a profile |
|---|---|---|---|
| MCP servers | 743 | 84.0% | 249 |
| Agent skills | 52 | 5.9% | 51 |
| Plugins | 25 | 2.8% | 17 |
| Agent projects | 25 | 2.8% | 25 |
| Infrastructure | 14 | 1.6% | 14 |
| Frameworks | 10 | 1.1% | 9 |
| Rules packs | 3 | 0.34% | 1 |
| IDE extensions | 3 | 0.34% | 3 |
| Platforms | 2 | 0.23% | 2 |
| Libraries | 2 | 0.23% | 2 |
| Developer tools | 2 | 0.23% | 2 |
| Agent SDKs | 1 | 0.11% | 1 |
| Automation platforms | 1 | 0.11% | 1 |
| AI APIs | 1 | 0.11% | 1 |
2 subcategories
Indexed = whole catalogue; profiled = products with their own page. A product can sit in several, so the rows do not add up to the total.
| Subcategory | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Browser ControlProgrammatic and agentic browser control. | 634 | 262 | 305 | Lagging the catalogue |
| Computer UseControlling desktops, apps and shells like a person would. | 296 | 140 | 143 | Thin |
Top 40 products by GitHub stars
Search the directoryProfiled products only (378 of 884), ranked by the stars of their own repository. Products that live in a subfolder of a larger repository (common for skills) show that whole repository's stars and are ranked after them; products without a repository come last. Stars are popularity, not quality or installs.
| # | Product | Type | Publisher | Capabilities | GitHub stars | Last push | Licence | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | Browser UsePython library that lets LLM agents control a Playwright/CDP browser by reading page state and issuing actions, with a hosted cloud option. | Library | browser-use | 122k | today | MIT | ||
| 2 | Scrapling MCP ServerWeb scraping with stealth HTTP, real browsers, and Cloudflare bypass. CSS selectors supported. | MCP server | D4Vinci | 105k | 4d ago | BSD-3-Clause | ||
| 3 | HyperFrames by HeyGenOfficial HyperFrames by HeyGen: the best AI video editor in chat. Captions, motion graphics, MP4. | MCP server | heygen.com | 88k | today | Apache-2.0 | ||
| 4 | hyperframesHyperFrames by HeyGen. Write HTML, render video. Compositions, GSAP and runtime adapter animations, captions, voiceovers, audio-reactive visuals, and website-to-video capture for HyperFrames. | Plugin | heygen.com | 88k | today | Apache-2.0 | ||
| 5 | Crawl4AIOpen-source async web crawler that outputs LLM-ready Markdown and structured extraction, running headless browsers locally. | Library | unclecode | 88k | 1d ago | Apache-2.0 | ||
| 6 | anything-llmStop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience | Agent project | Mintplex-Labs | 68k | today | MIT | ||
| 7 | Chrome DevTools MCPMCP server that lets coding agents drive and inspect a live Chrome instance: navigation, console, network and performance traces. | Developer tool | Google (Chrome DevTools) | 59k | 1d ago | Apache-2.0 | ||
| 8 | Chrome DevTools MCPMCP server for Chrome DevTools | MCP server | ChromeDevTools | 59k | 1d ago | Apache-2.0 | ||
| 9 | chrome-devtools-mcpControl and inspect a live Chrome browser from your coding agent. Record performance traces, analyze network requests, check console messages with source-mapped stack traces, and automate browser actions with Puppeteer. | Plugin | ChromeDevTools | 59k | 1d ago | Apache-2.0 | ||
| 10 | cherry-studioYour AI workspace for models, agents, and productivity. | Agent skill | CherryHQ | 54k | today | AGPL-3.0 | ||
| 11 | herdrthe runtime your coding agents live on | Agent project | herdrdev | 52k | 2d ago | Apache-2.0 | ||
| 12 | LightpandaHeadless browser written in Zig for automation and agents, with CDP compatibility and low memory use. | Infrastructure | Lightpanda | 42k | today | AGPL-3.0 | ||
| 13 | Playwright MCPMCP server that exposes Playwright browser control to agents using accessibility-tree snapshots instead of screenshots. | Developer tool | microsoft | 40k | 3d ago | Apache-2.0 | ||
| 14 | CloakBrowserStealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 50+ tests passed. | Agent project | CloakHQ | 33k | 1d ago | MIT | ||
| 15 | CuaOpen-source infrastructure for computer-use agents: sandboxed macOS, Linux and Windows VMs plus an agent SDK. | Infrastructure | Cua | 33k | today | MIT | ||
| 16 | AIHawkAI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions. | MCP server | feder-cr | 33k | 1d ago | MIT | ||
| 17 | OpenAI APIAPI for GPT and reasoning models via the Responses and Chat Completions endpoints, with built-in tools such as web search, file search, code interpreter and computer use. | API | openai | 32k | 1d ago | Apache-2.0 | ||
| 18 | OpenCLIMake Any Website into CLI & Use your logged-in browser by AI agent. | Agent project | jackwener | 31k | 14d ago | Apache-2.0 | ||
| 19 | page-agentJavaScript in-page GUI agent. Control web interfaces with natural language. | Agent project | alibaba | 30k | 3d ago | MIT | ||
| 20 | Kilo Code: AI Coding Agent, Copilot, and AutocompleteOpen Source AI coding agent that generates code from natural language, automates tasks, and runs terminal commands. Features inline autocomplete, browser automation, automated refactoring, and custom modes for planning, coding, and debugging. Supports 500+ AI models including Claude (Anthropic), Gemini, Grok, GPT, Codex and GLM. | IDE extension | kilocode | 28k | today | MIT | ||
| 21 | OpenMausBotOpen-source Grok Bot alternative with a virtual machine that bots can use | Agent project | milind-soni | 26k | today | Apache-2.0 | ||
| 22 | StagehandBrowser automation SDK that mixes Playwright-style code with natural-language act, extract and observe primitives and an agent mode. | SDK | browserbase | 26k | today | MIT | ||
| 23 | agent-desktopComputer use CLI for AI agents | Agent project | vercel-labs | 26k | today | Apache-2.0 | ||
| 24 | moliBest headless browser for AI agents. Lite, Fast, High-Compatibility. Built in Rust | Agent project | lexmount | 24k | today | Apache-2.0 | ||
| 25 | ego-liteThe fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero config. | Agent skill | citrolabs | 24k | today | MIT | ||
| 26 | SkyvernAutomates browser workflows using vision LLMs that read pages and act without site-specific selectors; self-hosted or cloud. | Automation platform | Skyvern | 23k | today | AGPL-3.0 | ||
| 27 | docker-androidAndroid in docker solution with noVNC supported, video recording, mcp server and AI-agent | MCP server | budtmo | 16k | 2d ago | — | ||
| 28 | cc-haha本地优先的跨平台 Claude Code / AI Agent 桌面工作台:多 Agent 协作、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、桌面宠物;支持微信、飞书、钉钉及 H5 等远程访问。 | Local-first Claude Code / AI Agent desktop workspace: multi-agent teams, Git worktrees, diffs, skills marketplace, multi-model, Computer Use, task-aware desktop pets; remote via WeChat, Feishu, DingTalk, Telegram, WhatsApp & H5. | Agent project | NanmiCoder | 16k | 1d ago | — | ||
| 29 | BrowserOS🌐 The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia. | Agent project | browseros-ai | 14k | today | AGPL-3.0 | ||
| 30 | nanobrowserOpen-source AI agent for web automation. Use your real, logged-in browser to automate daily tasks. | Agent project | nanobrowser | 14k | 4d ago | Apache-2.0 | ||
| 31 | SeleniumBase MCPStealthy browser automation, testing, and web-scraping via CDP Mode. | MCP server | seleniumbase | 13k | today | MIT | ||
| 32 | OpenBotThe open, self-hostable alternative to closed AI bots. Production-ready, fully customizable, and plugs into every stack: any agent, any model, any tool. | Agent project | CopilotKit | 13k | today | MIT | ||
| 33 | Agent-SAgent S: the state-of-the-art open source computer use agents | Agent project | simular.ai | 13k | today | Apache-2.0 | ||
| 34 | Windows-MCPAn MCP Server for computer-use in Windows OS | MCP server | CursorTouch | 12k | 1d ago | MIT | ||
| 35 | nopecha-extensionAutomated CAPTCHA solver for your browser. Works with Selenium, Puppeteer, Playwright, and more. | Agent project | NopeCHALLC | 11k | 1mo ago | MIT | ||
| 36 | openbrowserLet AI agents browse the web. An autonomous toolkit for browser-based AI agents. | Agent project | ntegrals | 9.6k | 7mo ago | MIT | ||
| 37 | openrigBuild your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work. | Agent skill | mvschwarz | 8.9k | today | Apache-2.0 | ||
| 38 | SteelOpen-source browser API for agents with session management, proxies and CAPTCHA handling, self-hosted or Steel Cloud. | Infrastructure | Steel | 8.0k | today | Apache-2.0 | ||
| 39 | UpsonicBuild autonomous AI agents in Python. | MCP server | Upsonic | 8.0k | 5mo ago | MIT | ||
| 40 | mcpBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser | MCP server | BrowserMCP | 7.4k | 9d ago | Apache-2.0 |
Most common integrations
Third-party services named by products in this node, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| Playwright | 84 | 9.5% |
| Android | 20 | 2.3% |
| Selenium | 8 | 0.9% |
| GitHub | 7 | 0.8% |
| Puppeteer | 7 | 0.8% |
| 6 | 0.7% | |
| Figma | 5 | 0.6% |
| X (Twitter) | 5 | 0.6% |
| Xcode / iOS | 5 | 0.6% |
| Google Analytics | 2 | 0.2% |
| Jira | 2 | 0.2% |
| PostgreSQL | 2 | 0.2% |
| 2 | 0.2% | |
| SAP | 2 | 0.2% |
| Shopify | 2 | 0.2% |
Launches per month
New Browser Automation & Computer Use products per monthSRC
Whole catalogue, by publication month, 2024-11 to 2026-11. The last month is partial; undated products are excluded.
Show the data as a table
| Products published (products) | |
|---|---|
| 2024-11 | 2 |
| 2024-12 | 3 |
| 2025-03 | 6 |
| 2025-04 | 1 |
| 2025-05 | 3 |
| 2025-06 | 1 |
| 2025-07 | 1 |
| 2025-08 | 3 |
| 2025-09 | 15 |
| 2025-10 | 11 |
| 2025-11 | 5 |
| 2025-12 | 11 |
| 2026-01 | 13 |
| 2026-02 | 28 |
| 2026-03 | 41 |
| 2026-04 | 46 |
| 2026-05 | 42 |
| 2026-06 | 47 |
| 2026-07 | 59 |
| 2026-08 | 69 |
| 2026-09 | 114 |
| 2026-10 | 178 |
| 2026-11 | 118 |
Related opportunities
Opportunity radarScored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.
| Opportunity | Competition | Confidence | Score |
|---|---|---|---|
| Coverage gap: Form FillingForm Filling | High | Low | 57.8 |
| Coverage gap: Screen UnderstandingScreen Understanding | Medium | Low | 57.7 |
| Coverage gap: Robotic Process AutomationRobotic Process Automation | High | Low | 56.7 |
| Coverage gap: DevTools DebuggingDevTools Debugging | High | Low | 52.0 |
| Coverage gap: Browser AgentsBrowser Agents | High | Low | 51.8 |
Limits of these numbers
- Products are placed here by whole-word keyword rules on their name, description and repository topics, and inherit every ancestor of a matched node. Products that do this without naming it are missed; ambiguous words cause false matches. Methodology
- About half of the catalogue matches no node at all, so absolute counts understate every category.
- Launch counts use the publication date each source reports; for auto-discovered repositories that is the repository’s creation date.
- Stars and concentration cover only products with their own repository (not a subfolder of a larger one). They measure attention, not adoption.
Page data last updated .