Sandbox
951 repos for des · CursorClear
Railly/
agentfiles

Browse, create, and edit AI agent files across Claude Code, Cursor, Codex, and 12 coding tools — from Obsidian.

745
takashiishida/
arxiv-latex-mcp

MCP server that uses arxiv-to-prompt to fetch and process arXiv LaTeX sources for precise interpretation of mathematical expressions in scientific papers.

145
seuros/
action_mcp
seuros/action_mcpFrameworks & SDKs

Rails Engine with MCP compliant Spec.

120
Jane-xiaoer/
claude-skill-web-clone

Methodology for faithfully cloning any website (static / React / WebGL) — without copying AI-hallucinated code. Real source first.

996
boshu2/
agentops

The operations layer for agentic engineering — portable skills and contracts connecting intent, agents, software factories, and independent judgment.

434

One folder. Every session knows where you left off. — An open-source methodology for AI-assisted projects.

171
ilindaniel/
ponytail-lite

Stop agents from over-engineering. Inspired by Ponytail, but without the plugin madness. Just one AGENTS.md file.

171
Azure/
aks-mcp
Azure/aks-mcpConnectors

A Model Context Protocol (MCP) server that enables AI assistants to interact with AKS clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and AKS.

140
avivsinai/
agent-message-queue

File-based message queue for local agent-to-agent communication (Maildir-style)

85
Bria-AI/
bria-skill

Claude Code skills for Bria AI - generate, edit, and transform images with Fibo, RMBG-2.0, and VGL structured prompts

67
kapillamba4/
code-memory

MCP server with local vector search for your codebase. Smart indexing, semantic search, Git history — all offline.

49
vicarious11/
agenttop

htop for AI coding agents — monitor token usage, costs, and workflows across Claude Code, Cursor, Kiro, Codex, and Copilot

49

Tools for AI agents to test, fix and optimise your codebase

46
Klavis-AI/
klavis

Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale

5.8k

Build big projects with Claude. Chief breaks your work into tasks and runs Claude Code in a loop until they're done.

474
LuD1161/
agentjail

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.

92
Neeeophytee/
agent-stylebooks

11 installable editorial systems for AI agents, based on leading public style guides.

60
michaelshimeles/
ralphy

My Ralph Wiggum setup, an autonomous bash script that runs Claude Code, Codex, OpenCode, Cursor agent, Qwen & Droid in a loop until your PRD is complete.

3k
ctxrs/
ctx

Instant recall for coding agents. Search the history already on your machine. Git blame, but for agent sessions.

1.1k