Sandbox
908 repos for agentic-coding · Claude CodeClear
PxyUp/
fitter

New way for collect information from the API's/Websites

133
AsyncFuncAI/
github-chat-mcp

A Model Context Protocol (MCP) for analyzing and querying GitHub repositories using the GitHub Chat API.

89
mgorabbani/
askdb

Give AI agents safe access to your database.

73
jhonsfran/
unprice
jhonsfran/unpriceFrameworks & SDKs

Open-source customer money path for usage-based SaaS — authorize customer spend before paid work runs.

36

A symbiotic AI agent that remembers everything, challenges you, and extends your cognition.

737
ZhangHanDong/
claude-code-api-rs

A high-performance Rust implementation of an OpenAI-compatible API gateway for Claude Code CLI.

177
yogthos/
Matryoshka

MCP server for token-efficient large document analysis via the use of REPL state

148

MCPify is an AI enablement compiler that transforms existing applications into AI-native, agent-operable systems.

96
aakashadesara/
ctop

CTOP - Interactive Process Viewer for AI Coding Agents

95
JasonBoy/
msw-mcp

Cli & MCP server for msw (Mock Service Worker) for AI Agents with dynamic mocking

81
cypress-io/
ai-toolkit

Fast, flexible, and open tooling for building intelligent workflows with Cypress.

40
Coding-Solo/
godot-mcp

MCP server for interfacing with Godot game engine. Provides tools for launching the editor, running projects, and capturing debug output.

5.6k

Minimal Coding Agent Harness on MCP for ChatGPT, Claude, Hermes, Grok Bot, OpenClaw

4.6k
hyper-mcp-rs/
hyper-mcp

📦️ A fast, secure MCP server that extends its capabilities through WebAssembly plugins.

880
dtormoen/
tsk-tsk

Keeping your agents out of trouble with sandboxed coding agent automation

170
molefrog/moiHarnesses

💾 MOI: agent-agnostic generative UI workspace. Give your agent a skill and let it build software around itself.

158
st3v3nmw/
sourcerer-mcp

MCP for semantic code search & navigation that reduces token waste

119
aronprins/
claude-loop

Hand Claude a PRD. Get a working feature back. One story per subagent, fresh context every time.

49