Executor
MCP gateway connecting AI agents to all your tools through one unified interface
Visit executor.sh ↗What is Executor?
Executor is an open-source integration layer that lets AI agents access multiple tools through a single MCP endpoint. Instead of configuring the same API keys and integrations separately in Claude Code, Cursor, ChatGPT, and other agents, you set up each tool once in Executor and every agent shares that catalog. It supports MCP servers, OpenAPI specs, GraphQL APIs, and custom functions.
The platform reduces context window usage by consolidating hundreds of individual tool definitions into one, keeping prompts compact while maintaining full functionality. It includes policy controls to determine which tools require approval or are blocked, runs in a sandbox to prevent models from seeing raw tokens, and can be deployed as a cloud service, desktop app, local CLI, or self-hosted Docker/Cloudflare instance.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered Executor automatically. Evidence: GitHub UsefulSoftwareCo/executor; repo has .claude, .codex, AGENTS.md. View source.
Similar vibe-coded apps
Manage teams of AI agents to run your business from one dashboard
IDE to orchestrate multiple coding agents in one workspace
Self-improving AI assistant with tool use and multi-platform messaging
Local-first AI agent workspace with desktop GUI and terminal TUI
Self-hosted open-source AI agent platform for coding, automation, and operations
Shared persistent memory for AI coding tools across sessions and applications
Sync AI coding tool configs and learn from agent mistakes
AI-ready productivity methodology for organizing work across any tool