Drive a stealth browser with an LLM from one command
Cross-referenced across 55 tracked directories
#3
Popularity Rank
5 / 55
Listed In
Mature
Adoption Stage
8/4/2024
Created
31,601
GitHub Stars
Run an AI-powered security scan to analyze this package's source code for vulnerabilities, prompt injection vectors, data exfiltration risks, and behavior mismatches.
Scans fetch actual source code from the GitHub repository, not just the README.
Cap-of-tea
AI-controlled browser farm on your machine. 36 MCP tools for Claude Code & Cursor — run N Chromium instances with device emulation, screenshots, network/geolocation simulation. Cross-platform: Windows GUI, headed & headless on Linux/macOS.
...moreGabriel Trabanco <[email protected]>
Types, JSON Schema, and parser/validator for the agentic-workflow machine envelope — the fixed JSON block every user-facing skill prints as its last output, for programmatic orchestration.
...moreZhonghao1995
Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integrating QGIS and EPA SWMM through the aiswmm runtime, reusable Skills, and MCP interfaces, with QA verification, provenance tracking, calibration support, and agent-runtime compatibility
...moreSilvio Jurk, AWP Contributors
Agent Workflow Protocol — an open standard for orchestrating multi-agent AI workflows with YAML definitions, DAG execution, and recursive delegation loops (A0-A4 autonomy)
...moreG GitHub Search | 9/4/2026 | 9/20/2026 |
O Official MCP Registry | 9/12/2026 | 9/20/2026 | - |
C Cline MCP Marketplace | 9/13/2026 | 9/20/2026 |
4,669
Forks
9/18/2026
Last Commit
Widely adopted across the ecosystem
Cross-Posting Opportunities
Could also be listed in these directories: