A collection of sample apps and recipes built with the TinyFish web agent. Open-source examples for you to learn & build!
-
Updated
Nov 3, 2026 - TypeScript
#
web-agents
Here are 98 public repositories matching this topic...
Open-source benchmark for browser AI agents on daily tasks.
chrome-extension benchmark evaluation dataset browser-automation ai-agents web-agent web-agents everyday-tasks browser-agent llm llm-evaluation agentic-ai computer-use browser-use agent-evaluation ai-agent-benchmark online-tasks chrome-agent real-world-benchmark
-
Updated
Nov 5, 2026 - Python
Open, source-backed catalog of computer-use agents: reviewed papers, GUI models, datasets, benchmarks, tools, and reusable JSONL/SQLite data.
awesome research reinforcement-learning benchmarks awesome-list papers datasets ai-agents awesome-resources mobile-agents web-agents llm-agents vision-language-models agentic-ai gui-agents computer-use gui-grounding agent-evaluation browser-agents computer-use-agents
-
Updated
Nov 10, 2026 - Python
AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.
-
Updated
Oct 6, 2026 - Python
🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
python mcp wap browser-automation ai-agents playwright web-agents ai-tools record-replay llm mcp-server modelcontextprotocol browser-use web-agent-protocol
-
Updated
Jun 19, 2025 - Python
[ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents
-
Updated
Aug 24, 2026 - Python
Can AI agents rebuild websites through browser exploration?
benchmarking benchmark web-development ai reverse-engineering full-stack browser-automation harbor ai-agents web-agents llm llm-benchmarking browser-use agent-evaluation swe-bench llm-benchmark llm-benchmarks harbor-framework website-reconstruction visual-evaluation
-
Updated
Nov 10, 2026 - Python
Open benchmarks for browser agents: BU Bench V2.1, 200 real web tasks. Rerun them with your own API keys.
benchmark browser-automation ai-agents web-agents browser-agent evals llm-evaluation browser-use bu-bench
-
Updated
Nov 7, 2026 - Python
[NAACL2025] LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications
agent gpt autonomous-agents ai-agents agent-based-framework fastapi web-agent autonomous-agent web-agents ai-agent llm llm-agent llm-framework llm-agents agentic-agi agentic-framework agentic-workflow
-
Updated
Jul 11, 2025 - Python
DoomArena is a Framework for Testing AI Agents Against Evolving Security Threats
security machine-learning ai attack machine defense ai-safety red-teaming web-agents llm browsergym taubench
-
Updated
Sep 12, 2025 - Python
Benchmark for comparing agent harnesses on everyday online tasks — fixes the base model, varies the harness. Sister project of ClawBench, same scoring pipeline.
benchmark evaluation browser-automation ai-agents web-agents browser-agent llm llm-evaluation agentic-ai computer-use agent-evaluation agent-harness
-
Updated
Jul 17, 2026 - Python
TinyFish Web Agent integrations with workflow automation tools and AI agent frameworks
-
Updated
Nov 10, 2026 - Python
Benchmark of report fidelity for browser agents: does the agent's final report tell the truth about what it actually did?
-
Updated
Sep 4, 2026 - Python
[ACL'25 (Findings)] Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents
-
Updated
Feb 17, 2026 - Python
A coding agent for the browser
-
Updated
Jun 25, 2026 - TypeScript
TinyFish MCP server — web search, page fetching & extraction, browser automation and page monitoring for Claude, Cursor, VS Code and any MCP client. Search and Fetch are free.
fetch search agent ai mcp browser-automation ai-agents web-search web-automation web-agents llm agentic model-context-protocol mcp-server tinyfish
-
Updated
Nov 3, 2026 - TypeScript
An automated prompt injection vulnerability discovery framework for AI web agents.
-
Updated
Aug 2, 2026 - Python
This repository contains the code and data of the WebMall benchmark for evaluating the capability of Web agents to find and compare product offers from multiple e-shops.
-
Updated
Aug 3, 2026 - HTML
Source code for "Terminal Agents Suffice for Enterprise Automation"
gitlab mcp erpnext agents servicenow web-agents enterprise-automation llm-agents cli-agents terminal-agents
-
Updated
Aug 5, 2026 - Python
Turn any URL into agent-callable MCP tools. One spec-compliant MCP server endpoint, no per-site build.
oauth typescript mcp openapi json-rpc shopify json-ld cursor ai-agents claude cloudflare-workers tool-use web-agents anthropic llm-tools model-context-protocol mcp-server streamable-http mcp-security
-
Updated
Oct 27, 2026 - TypeScript
Add this topic to your repo
To associate your repository with the web-agents topic, visit your repo's landing page and select "manage topics."