Sandbox
11 repos for web · Cursor · Code reviewClear
patchorbit/
domscribe

Domscribe is a pixel-to-code development tool that bridges the gap between running web applications and their source code.

189
utkusen/
sast-skills

Collection of agent skills to find vulnerabilities inside your web/mobile apps.

1.3k

Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agent harnesses, pure Rust.

98
ohmiler/
gridgeist

Gridgeist turns product intent into a rigorous visual system—without the generic AI SaaS aftertaste.

115
Untrivial-ai/
agent-orchestrator

Run and supervise teams of coding agents from planning to merge. Any harness (Claude code, codex, +25 more). Desktop, web, mobile, and cloud agents.

11k

AI agents can generate code, but they still struggle to understand what they build. Reticle gives them runtime perception of web & desktop applications.

458
callstack/
agent-device

Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.

4.5k
Shelpuk-AI-Technology-Consulting/
agent-skill-tdd

TDD + requirements workflow skill for AI coding agents (Claude Code, Codex, Antigravity, Cursor, Windsurf, etc.). Part of the Shelpuk agentic suite alongside Serena, Kindly Web Search, and Lad.

30

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.

362
Community-Access/
accessibility-agents

Accessibility review agents for Claude Code, GitHub Copilot, and Claude Desktop. Eleven specialists that enforce WCAG 2.2 AA compliance so AI coding tools stop generating inaccessible code.

405

Vestige enhances agents by deterministic root-cause retrieval that reaches backward through time to find the quiet change, decision, or service that caused today’s failure, not the lookalike.

617