Code Execution

E-signatures for agents: mint a sandbox key, send PDFs, track status, download the sealed result.

Driverless delivery.

Pay-per-call API gateway for AI agents. 108 tools including image and video generation, LLM inference (72 models), code execution, audio transcription, voice cloning, crypto data, wallet analytics, travel, ENS, IPFS, web search, web scraping, and transaction simulation. All via HTTP 402 micropaymen…

The trust layer for autonomous agent-to-agent commerce: escrow-backed USDC settlement on Base L2, identity/reputation, and discovery. Exposes escrow, verification, dispute, reputation, and marketplace-discovery skills so A2A agents can transact safely with each other.

Create a free sandbox object storage bucket; upload, download, list, inspect, and delete objects.

Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.

MCP server for SandboxAPIs — read-only, API-compatible replicas of GitHub, GitLab, Bitbucket, Azure DevOps, Jira, Linear, Slack, Microsoft Teams, Sentry, PagerDuty, Anthropic, OpenAI, ChatGPT, Cursor and Devin, preloaded with one realistic simulated data

An Open, Structured, and Standard Registry for MCP Servers and Packages.

AMEVA OS: Universal Polyglot WASM & AI Vector MCP Hub. Zero-Install Multi-Language Tool Runtime & Real-Time Dynamic Multi-Repo Subscription Engine.

MCP server giving AI agents real interactive terminal sessions — PTY, TUIs, REPLs, SSH, even another agent's CLI — with a live web view a human can watch and type into

A thin MCP client for humans and agents — run any Model Context Protocol server, call its tools, read its stderr, and reconnect after each edit. REPL, headless CLI, or an MCP server your agent drives. No client config edits, no restarts.

Business Execution OS for solo founders and bootstrappers — 42 structured tools guiding raw idea to validated revenue. Market research, buyer personas, offer design, landing pages, email sequences, ad copy, traffic strategy, SEO content engine, revenue ph

An ability-resolution and governed execution layer for AI agents: use prepared providers first, then resolve abilities from the broader software world.

MCP server that gives AI agents (Claude Code, Cursor, Windsurf) real interactive terminal sessions — run REPLs, SSH, databases, Docker, and any interactive CLI with clean output and smart completion detection

Salesforce sandbox seeding CLI + MCP server: SOQL-scoped org-to-org copy with dependency-graph walking, cross-org FK remapping, deterministic PII masking, and a hard AI-never-sees-your-data boundary.

Local Memory MCP Server - AI-powered persistent memory system for Claude Code, Claude Desktop, Gemini, Codex, OpenCode and other MCP-compatible tools

MCP server for real-time JupyterLab notebook collaboration

sdk.run simulator sandbox: run JS snippets against the live iOS SDK on a booted simulator (and macOS via Node-API), verified against sdk.run first, over MCP or HTTP

REPL-sharing MCP server — AI and humans co-drive the same visible terminal. 19 embedded adapters: shells (bash, pwsh, zsh, cmd), language REPLs (Python, Node, Deno, Lua, Racket, CCL/ABCL/SBCL Common Lisp, F# Interactive, jshell, Groovy, SQLite3), and debu

A real interactive terminal for AI agents (MCP). Run and test vim, htop, gdb, REPLs, and any TUI — things the built-in fire-and-forget terminal can't touch.