Sandbox
3,789 repos
voska/hass-mcpConnectors

Control and query Home Assistant from Claude and other LLMs β€” a Model Context Protocol (MCP) server.

340
shrijayan/
itwillsync

Sync any terminal-based AI coding agent to your phone. Claude Code, Aider, Codex. Local network, zero cloud.

98
steve228uk/
metro-mcp

πŸš‡ A plugin-based MCP server for React Native runtime debugging, inspection, and automation. Connects to Metro bundler via Chrome DevTools Protocol β€” no app code changes needed for most features.

80
mgorabbani/
askdb

Give AI agents safe access to your database.

73
CloudChef/
atlasclaw
CloudChef/atlasclawFrameworks & SDKs

AtlasClaw is an enterprise agent framework supporting mutliple users and multi system integration.

90

A command-line tool that injects credentials to curl requests to known public APIs.

124
hnaymyh123-henry/
skills-compat-manager

Cross-platform compatibility layer for AI agent skills β€” pre-flight dependency checks, MCP-native, works with Claude Code, Cursor, Codex CLI, OpenCode and more

83
jgravelle/
jdatamunch-mcp

Token-efficient MCP server for tabular data retrieval. Index CSV/Excel files, query rows, aggregate β€” 99%+ token savings vs raw file reads.

81
gnurio/
porter-strategy-skills

12 executable AI agent skills for competitive strategy analysis, extracted from Michael Porter's Competitive Strategy. Five forces, competitor profiling, strategic groups, market signals, generic strategies, competitive moves, and industry-type playbooks β€” grounded in Porter's original frameworks.

48
sorafujitani/
ccsession

pick any past Claude Code session via fzf, then resume it from the right cwd

46
OdradekAI/
bundles-forge

An agentic skills framework & bundle-plugin engineering toolkit that works.

230
ilang-ai/
autocode

You say it. AutoCode ships it. 48 skills. Code to deployment in one session. I-Lang v5.0 judgment + secret-safe deploys. Free forever.

86
alicicek/
tale-mode

A discipline plugin for Claude Code + OpenAI Codex β€” plan first, verify against the real code, receipts on every decision, independent adversarial review, and a self-armed loop that keeps going until a real check passes. Built by Fable to make any Claude work like a careful senior engineer.

36
matlab/
agent-skills-playground

A sandbox for prototyping and demonstrating Agent Skills for MATLAB and Simulink work.

176
browser-use/
vibetest-use

Vibetest MCP - automated QA testing using Browser-Use agents

830
ypollak2/
llm-router

Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.

78

Travel MCP server + CLI for AI assistants β€” flights, hotels, trains, cars, ferries, price alerts. No API keys, single Go binary. 1 smart MCP tool + 66 aliases (98.9% smaller tools/list). Works with Claude, Cursor, Windsurf, Codex.

75
Hainrixz/
agente-pagokit

Claude Code plugin that picks and implements the right payment method for your app β€” from your terminal. 42 providers, 136 payment rails, and deterministic validators that block insecure payment code as it is written.

48
sneg55/
agent-starter

A toolkit of skills, templates, and guides for bootstrapping AI-agent-friendly projects. Started from Anthropic's Claude Code engineering patterns, extended with a per-project self-improvement loop and more.

76
Happenmass/
omux

Orchestrate AI coding agents (Claude Code, Codex) as parallel subagents over tmux β€” a loop-engineering runtime with auto-continue, execute-then-review, and cross-session memory.

95
pumblus/
okf-harness

Agent-first local harness for OKF-compatible LLM Wikis.

34

Instant, accurate Unreal Engine API lookups instead of expensive source file reads, saving your agent tokens, context, and hallucinations.

95