Cohort of 68 admitted agents tagged capability:browsing. Composite below is the cohort's average AgentScore.
| Cmp | Rank | Agent | 24h | Score | Δ24h | Watch |
|---|---|---|---|---|---|---|
| #32 | browser-use mitbrowser-use: ???? Make websites accessible for AI agents. Automate tasks online with ease. | 13 | 49.0 | +1.08 | ||
| #59 | omnigent apache-2.0omnigent: Run a coding or knowledge-work agent on your laptop, pick it back up from your phone, and share the live session with a teammate. One command stands up a local agent server with a terminal UI and a web UI — so the same session is reachable from your terminal, your browser, and... | 45.3 | +0.13 | |||
| #76 | gptme mitcligptme: Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top! | 43.2 | -0.06 | |||
| #88 | solidcraft apache-2.0mcp-serversolidcraft: An open-source, clean-room reimplementation of Autodesk Fusion 360 in pure Rust. Parametric 3D CAD for desktop, browser, and AI agents via MCP. | 1 | 42.0 | -0.04 | ||
| #112 | cline apache-2.0ide-plugincline: Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way. | 11 | 40.3 | -0.62 | ||
| #149 | dots mitdots: Open-source dots for the web: an AI agent with its own browser, one that does not get blocked. | 3 | 37.1 | +0.47 | ||
| #174 | GenericAgent mitGenericAgent: Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption | 4 | 35.7 | 0.00 | ||
| #175 | fastbrowse mitfastbrowse: A fast browser agent: Jev picks each action from what is on the page, an LLM reads and plans, and every claim in an answer cites a quote from the page. | 4 | 35.6 | +0.07 | ||
| #244 | hermes-jev-skills mithermes-jev-skills: Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex). | 3 | 33.2 | +0.00 | ||
| #254 | jev-ultrafast mitjev-ultrafast: Fastest and cheapest web agent. | 4 | 32.7 | -0.00 | ||
| #306 | grill-with-ui mitgrill-with-ui: Agent-agnostic skill: run a grilling design interview on a local browser page instead of the terminal. | 7 | 31.3 | +0.50 | ||
| #320 | jev-browser mitmcp-serverjev-browser: Browser automation where an LLM plans and Jev (Typesafe System One) decides. Library, CLI and MCP server. | 27 | 30.8 | +0.82 | ||
| #329 | ai-newtab mitai-newtab: Claude generates a daily new tab page based on your browser history. | 10 | 30.7 | +0.01 | ||
| #339 | Awesome-CUA Awesome-CUA: Open, source-backed catalog of computer-use agents: reviewed papers, GUI models, datasets, benchmarks, tools, and reusable JSONL/SQLite data. | 302 | 30.4 | +4.55 | ||
| #342 | threejs-game-skills mitthreejs-game-skills: Agent skills for building playable, polished Three.js browser games with gameplay, AAA-style graphics, UI, QA, and optional AI-generated 3D, image, and audio assets. | 10 | 30.4 | +0.02 | ||
| #371 | open-3d-skills mitide-pluginopen-3d-skills: Eight agent skills for 3D and animated websites: three.js scenes from code, scroll films, transparent video, cursor rigs, exploded views, AI motion assets, browser checks and 60 fps recording. Claude Code, Codex, Cursor, Gemini CLI. | 64 | 29.7 | -1.16 | ||
| #391 | vulnerator-ai mitmcp-servervulnerator-ai: Autonomous OODA-loop pentesting agent. Hermes brain, Kali + Playwright tools over MCP, ATT&CK as the Orient language. | 18 | 29.3 | -0.24 | ||
| #402 | Lilo mitmcp-serverLilo: A Mac browser on WebKit, not another Chromium, that still runs Chrome extensions. Arc-style Spaces, terminal tabs, and a built-in MCP server so your AI agents browse beside you. MIT, no account. | 161 | 29.0 | +2.30 | ||
| #409 | system1-agents apache-2.0mcp-serversystem1-agents: System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics. | 3 | 28.9 | -0.01 | ||
| #411 | locoagent mitlocoagent: AI-powered social media agent with real browser automation. | 1 | 28.9 | 0.00 | ||
| #434 | leaningtech/browsercode leaningtech/browsercode: discovered AI agent. | 1 | 28.5 | +0.17 | ||
| #458 | anansi apache-2.0mcp-serveranansi: A self-healing web scraper built for hostile sites: selectors repair themselves, browser rendering kicks in when needed, and Chrome TLS fingerprinting evades bot detection. Ships with an MCP server so any LLM can drive a full crawl through conversation. | 13 | 28.1 | 0.00 | ||
| #488 | agent-screenplay mitmcp-serveragent-screenplay: Beautiful screen recordings, made by your favorite AI agent. | 11 | 27.8 | +0.13 | ||
| #501 | bux mitbux: A 24/7 Claude Code agent with Browser Harness, on any box you own. | 13 | 27.6 | +0.00 | ||
| #537 | touri apache-2.0touri: touri: open-source desktop app for AI agent bots (Codex, Claude, OpenCode) with isolated VMs, browser and computer use. | 15 | 27.2 | -0.03 | ||
| #575 | imshaikot/browsentic imshaikot/browsentic: discovered AI agent. | 91 | 26.7 | -0.93 | ||
| #633 | Notion-AI-to-OpenAI-Compatible mitNotion-AI-to-OpenAI-Compatible: OpenAI-compatible HTTP API that routes chat requests to Notion AI (`runInferenceTranscript`) using your Notion browser session. | 17 | 26.1 | 0.00 | ||
| #697 | WebsiteBench apache-2.0libraryWebsiteBench: Can AI agents rebuild websites through browser exploration?. | 5 | 25.6 | +0.13 | ||
| #739 | deepcloak mitmcp-serverdeepcloak: Local-first deep research agent that reads the whole web — even pages behind Cloudflare, Datadome, Turnstile & reCAPTCHA. Stealth fetch + cited reports. MCP-native, MIT. | 1061 | 25.2 | +10.00 | ||
| #753 | ZeroScript-Free gplmcp-serverZeroScript-Free: ZeroScript Free: Turn DeepSeek into a Roblox Studio agent. Browser extension + local bridge. Read/edit scripts, run Luau, generate assets all from DeepSeek chat. Robust agentic. No terminal needed. | 70 | 25.1 | -0.45 | ||
| #760 | Kaze Kaze: A calm, quick browser for macOS, with an agent that works in your tabs. | 94 | 25.0 | +1.02 | ||
| #786 | agent-chrome-relay mitbrowser-extensionagent-chrome-relay: Let your AI agents use your Chrome, signed in as you, in background tabs. By Alexey Indeev · blog: read.aindeev.com · X: @AlexeyIndeev | 25 | 24.8 | -0.01 | ||
| #809 | snapgent-connector gplmcp-serversnapgent-connector: Free, open-source AI agent connecting chat to Roblox Studio and VS Code via MCP. | 26 | 24.6 | -0.01 | ||
| #810 | bughunter-ai mitmcp-serverbughunter-ai: Autonomous Bug Bounty Hunting Framework powered by Claude Code. 20 AI agents, state-machine orchestration, Burp Suite MCP, credential vault, LLM security track. Type 'hunt target.com' and let AI find the bugs. | 24 | 24.6 | 0.00 | ||
| #898 | model:openjev/openjev model:openjev/openjev: discovered AI agent. | 1 | 23.7 | +0.07 | ||
| #904 | guizang-social-card-skill agplguizang-social-card-skill: 🪧 Claude Code / Codex skill — generate Xiaohongshu carousels & WeChat 21:9+1:1 cover pairs. Editorial × Swiss visual systems, 28 layouts, 10 themes, single-file HTML → PNG. 小红书图文 + 公众号封面对 | 15 | 23.7 | -0.01 | ||
| #916 | tweetytweets mittweetytweets: Autonomous X/Twitter posting pipeline for your AI agent. No API key, no paid scrapers: researches your niche, writes in your voice, publishes through a real browser, and verifies its own posts. | 13 | 23.6 | 0.00 | ||
| #940 | agent-vision mitmcp-serveragent-vision: Eyes for AI coding agents 👁️ — render → perceive → report → fix → re-render. A machine-graded visual feedback loop (DOM/contrast/OCR-grounded + optional vision LLM) agents consume to self-correct before claiming done. | 9 | 23.3 | 0.00 | ||
| #971 | justram/pi-serini ide-pluginjustram/pi-serini: Does a lexical retriever suffice as large language models (LLMs) become more capable in an agentic loop? This question naturally arises when building deep research systems. We revisit it by pairing BM25 with frontier LLMs that have better reasoning and tool-use abilities. To s... | 14 | 23.1 | 0.00 | ||
| #988 | awesome-agent-rl-environments awesome-agent-rl-environments: A curated list of training & evaluation environments for LLM/VLM agents (SWE-Gym, GEM, RAGEN, AgentGym, WebArena, OSWorld, ToolBench…). Updated weekly. | 12 | 23.0 | 0.00 | ||
| #1000 | imnotarobot mitmcp-serverimnotarobot: I am not a robot — a captcha solver for macOS: local model, Gemini vision, a stealth browser for checkbox captchas, RuCaptcha as the last resort. 2Captcha-compatible API and an MCP server. | 11 | 22.9 | 0.00 | ||
| #1010 | x-scraper-no-api gplsaasx-scraper-no-api: Free, self-hosted X (Twitter) scraper no API key, no credits. Uses your own browser session via Playwright. Export tweets, search results & timelines as LLM-ready JSON/CSV/Markdown. Ships an AI agent Skill for OpenClaw & Hermes. | 12 | 22.8 | 0.00 | ||
| #1017 | Silbercue/public-browser Silbercue/public-browser: discovered AI agent. | 56 | 22.7 | -0.39 | ||
| #1035 | pixiebrix/agent-browser-shield pixiebrix/agent-browser-shield: discovered AI agent. | 7 | 22.6 | 0.00 | ||
| #1051 | reanimate mitreanimate: A Claude Code skill that reverse-engineers any animation frame by frame, then proves the copy moves the same. | 233 | 22.5 | -1.83 | ||
| #1078 | astra-ai-automation-agent libraryastra-ai-automation-agent: Playwright Python test framework with an AI agent that generates tests from Jira/Excel tickets using RAG + GPT-4o. | 9 | 22.3 | 0.00 | ||
| #1123 | awesome-self-hosted-agents saasawesome-self-hosted-agents: AI agents and services for agents that run on your own box: a Linux server, a Raspberry Pi or a Mac mini. | 6 | 21.9 | 0.00 | ||
| #1189 | mcp-man mitmcp-servermcp-man: Postman for MCP servers — inspect tools, test live, browse 150+ servers. | 163 | 21.4 | +1.51 | ||
| #1265 | res mitsaasres: Agent skill to reverse engineer a SaaS product through the browser into a knowledge base for rebuilding it: screens, rules, data model, design tokens and production barriers, without touching production data. | 149 | 20.7 | -1.30 | ||
| #1270 | canary canary: QA harness built for Claude Code | E2E testing with screen recordings, console logs, network HARs, and Playwright traces. | 5 | 20.6 | +0.00 | ||
| #1395 | agent-shopping-safe-checkout agent-shopping-safe-checkout: Safe-checkout pattern for AI agents (Hermes/Claude Code/Codex): isolated Chrome + Browser Harness + virtual card + human gate. | 14 | 19.7 | 0.00 | ||
| #1474 | KabakaWilliam/known_actions ide-pluginKabakaWilliam/known_actions: As LLM-based agents increasingly browse the web on users' behalf, a natural question arises: can websites passively identify which underlying model powers an agent? Doing so would represent a significant security risk, enabling targeted attacks tailored to known model vulnerab... | 9 | 18.9 | 0.00 | ||
| #1584 | agent-gpu-calculator mitagent-gpu-calculator: Single-file GPU/RAM sizing calculator for LLM agent sessions on vLLM: KV-cache offload to RAM, prefix caching, MLA/DSA and hybrid models, TP chosen per model × GPU pair (H100–B300). Runs in the browser, no dependencies. | 4 | 18.1 | 0.00 | ||
| #1612 | ia-security-skill libraryia-security-skill: IA Security Skill — auditoria de segurança defensiva pré-entrega para projetos Claude Code. 24 análises universais · 18 linguagens · 34 frameworks · mobile (MASVS) · desktop · browser extensions · 21 áreas especializadas. Score, attack chains e fixes copy-paste. | 6 | 17.9 | 0.00 | ||
| #1624 | invisible_dots mitmcp-serverinvisible_dots: Open-source, self-hosted alternative to OpenAI Dots, Grok Bot. Built to be undetectable by anti-bot systems. | 13 | 17.8 | +0.13 | ||
| #1632 | hanwenliu6825/DAGent ide-pluginhanwenliu6825/DAGent: Deep research tasks require agents to navigate large knowledge spaces, synthesize evidence across many sources, and adapt their plans as findings emerge. Directed acyclic graph (DAG)-based multi-agent systems suit this setting because they support parallel execution and isolat... | 181 | 17.8 | -1.25 | ||
| #1762 | scout apache-2.0scout: Scout: the open-source browser agent, by Outcrawl. Mirrored automatically from Outcrawl's own repository. | 247 | 16.8 | -1.84 | ||
| #1880 | google-ai-mode-mcp mitmcp-servergoogle-ai-mode-mcp: Google AI Mode for Claude and any MCP client: cited AI answers from your own browser in ~3 s, no tabs, no API keys. | NEW | 13.6 | — | ||
| #1916 | lll-web-agent lll-web-agent: ??????????????? LLM Agent SDK ??? ?????? API Key ?????????. | 298 | 12.9 | +3.28 | ||
| #1923 | browser-agent mitbrowser-agent: Invisible browser control for LLM agents — real Chrome via CDP, no JS injection, no screenshots, token-efficient. | 53 | 12.7 | +0.91 | ||
| #2135 | @six5536/smllm-wasm @six5536/smllm-wasm: smllm's engine as WebAssembly: run smllm state machines that drive an LLM agent, in a browser or Node. | 14 | 11.3 | +0.15 | ||
| #2138 | @dudko.dev/agent-web mcp-server@dudko.dev/agent-web: Headless, configurable in-browser LLM agent on the Vercel AI SDK: multi-provider bring-your-own-key (OpenAI, Anthropic, Google, xAI, DeepSeek, gateway, openai-compatible) AND local WebGPU/WebLLM, native + prompted tool-calling, structured output, an encry. | 87 | 11.2 | +1.93 | ||
| #2148 | taw-computer mitmcp-servertaw-computer: Give any AI a real computer. Open source MCP server with Ubuntu sandbox, browser automation, desktop control, and 30+ tools. Works with Claude Code, Cursor, Claude Desktop. | 16 | 10.8 | 0.00 | ||
| #2188 | Genspark-AI mitide-pluginGenspark-AI: Genspark AI open-source, self-hosted Super Agent. Free alternative to Genspark.ai with multi-agent orchestration, deep research, Sparkpages, AI slides & sheets, image generation and 80+ tools. One-command Windows install. Run locally with any LLM (OpenAI, Anthropic, Gemini, Ol... | 13 | 10.0 | 0.00 | ||
| #2220 | agentic-recorder agentic-recorder: The DemoBites agentic recorder — you prompt, it films a real browser, and DemoBites turns the take into an editable demo bite. | 13 | 9.7 | 0.00 | ||
| #2342 | @anybrowser/cli mcp-server@anybrowser/cli: Let any LLM agent drive a real, logged-in browser over MCP. No browser extension required. | 17 | 4.9 | -0.08 | ||
| #2357 | agentic-surfaces agentic-surfaces: Visualize and follow your agentic-surfaces workflows in the browser — run `npx agentic-surfaces` from your repo to open the live dashboard. | 52 | 3.3 | -2.97 | ||
| #2399 | ecomolt mcp-serverecomolt: A civilization game for LLM agents — ecology, economy, self-government, and a shared existential deadline. MCP-first, browser-spectated, research-driven. | 18 | 0.0 | 0.00 |
Browse all sectors at /sectors.