Code Execution
Top open-source Code Execution AI systems, agents, and MCP tools.
Discover and install verified Code Execution AI systems, autonomous agent skills, and Model Context Protocol servers on AIStoreHub. Reusable, security-scanned, and ready for 1-click execution in Cursor, Claude Code, and terminal workflows.
Available AI Systems & Skills (28)
Open in Advanced FilterYour own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, GitHub Copilot, OpenRouter), custom skills, and MCP servers.
Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
Self-hosted MCP gateway and company brain for AI agents: connect Claude, ChatGPT and Copilot to your ERP, APIs, databases and file servers, with company memory, skills, knowledge graph, SSO/RBAC and audit. 691 connectors (SAP, Odoo, SQL…). Open source, EU cloud.
An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Implementation of Anthropic's and Cloudflare's ideas for reducing MCP tool definitions context bloat.
Secure, isolated Linux microVM cloud sandboxes for AI agents to run untrusted code, execute terminal commands, and analyze data safely in cloud environments.
Next-generation visual node canvas for chaining multimodal AI prompts, image generation pipelines, and code execution blocks.
AI-Powered Roblox Luau Code Execution Server for Live Game Testing 2026
In-process Revit AI agent with dynamic C# code execution, multi-provider LLM support, and a guardrail system for safe BIM automation.
claude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Your 24/7 autonomous AI sales representative powered by Claude Code or Codex. Finds qualified prospects, crafts hyper-personalized cold email sequences, executes sending campaigns, classifies inbound replies, and books meetings. Runs locally on your existing Claude Pro/Max subscription with zero per-token API bills.
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
AI agent skill for generating interactive, animated HTML slide decks, executive presentations, and visual walkthroughs directly in code.
The open source autonomous coding agent built for full codebase refactoring, multi-file editing, test generation, and automated terminal execution.
Hugging Face's lightweight Python library for autonomous CodeAgents that write and execute actions in plain Python syntax instead of cumbersome JSON.
Open GUI agent framework for operating computer desktop environments across macOS, Windows, and Linux using visual grounded navigation.
Teams-first Multi-agent orchestration for Claude Code
Autonomous coding agent MCP server that navigates codebases, performs intelligent semantic refactoring, and executes build verification.
Autonomous developer agent CLI for codebase memory, cross-session architecture understanding, and intelligent task execution.
Autonomous coding workflow that generates implementations, runs unit test executions, and self-corrects runtime stack traces.
Observability and guardrails for your ai agents. AgentTrail Guard traces your agent's execution and automatically compiles repeat failures into permanent guardrails.
JSON-driven multi-agent cadence-team development framework with intelligent CLI orchestration (Gemini/Qwen/Codex), context-first architecture, and automated workflow execution
External executive function system for founders with AUDHD - a Claude Code skill
Faster than your agent alone. And better. A workflow plugin that takes a bug, idea or ticket to a verified pull request: specs, cross-model review by risk, live QA, receipts in your repo. Claude Code · Codex · Cursor · Droid · Grok Build · OpenCode · Muse Code.
Build & Monetize for Code Execution
Have you created an autonomous agent, MCP server, or Claude Code skill for Code Execution? Publish it to AIStoreHub with dual-currency checkout (USD $ + INR ₹) and earn 85–90% net revenue.