Spawn
Spawn is an experimental OpenRouter tool for deploying AI coding agents on your own infrastructure with a single command. Pick an agent, choose a cloud, and Spawn provisions a virtual machine, installs the agent and its dependencies, authenticates to OpenRouter and the cloud using a CLI OAuth flow, configures endpoints and model routing, and then opens an SSH session so you can start working. Each agent-and-cloud combination is implemented as a self-contained script, avoiding Terraform and YAML while keeping deployment portable. Supported agents include Claude Code, OpenClaw, Codex CLI, OpenCode, Kilo Code, Hermes Agent, Junie, Pi, Cursor CLI, and T3 Code, making it easy to explore coding-agent workflows or switch between them with one command. Spawn supports cloud environments such as DigitalOcean, Sprite, Hetzner Cloud, AWS Lightsail, GCP Compute Engine, and Daytona, as well as a local machine or a throwaway local Docker sandbox.
Learn more about Spawn
Showly
Showly is a website hosting platform for sites created with AI agents, giving agent-generated work a polished place to preview, publish, share, and manage. Users describe what they want to build in the coding agent they already use, such as a report, research page, presentation, documentation site, portfolio, landing page, prototype, or product specification, and the agent creates the page while Showly handles hosting and publishing. It connects through MCP and works with Claude Code, Codex, Cursor, OpenClaw, Hermes Agent, and other compatible agents, allowing users to publish without leaving their existing workflow. Every change appears first as a private preview, so users can review the exact page, request revisions, and decide when it goes live. Published work receives a stable, shareable web link, and version history makes it possible to restore an earlier published version when needed. Showly can also turn existing output into live pages by accepting content.
Learn more about Showly
Harden
Harden AIF is an agent endpoint security platform for AI coding agents. It evaluates supported agent tool calls before execution using the developer’s intent, session context, organisational policy, and the effect of the proposed action.
Harden helps protect against destructive commands, unauthorized access, unintended data transfers, secret exposure, privilege misuse, and other unsafe agent actions. Legitimate actions can proceed normally, sensitive data in supported flows can be safely redacted, and actions that fall outside the developer’s intent or authority are blocked before execution.
Harden works across popular coding agents and agentic development tools including Claude Code, Codex, Cursor, Antigravity CLI, Kiro, Hermes, and OpenClaw, providing a consistent security layer across the agent ecosystem.
Learn more about Harden
Agent Teams
Agent Teams is a hosted AI-agent workspace for solo founders and early-stage startups. Users can create a lead agent and specialist agents for product, growth, and operations, then coordinate work through shared tasks, files, and messages. Hosted agents can use persistent files and memory, browser access, tools, and schedules to handle ongoing work beyond a single browser session. The shared workspace lets users review agent conversations and activity and collaborate with invited colleagues. Agent Teams supports Hermes and OpenClaw workers, model and tool choices, and connectors for WhatsApp, Telegram, and Slack. Compatible AI clients, including Codex, Cursor, and Claude Code, can connect through supported reporting or MCP tools. The service is designed for startup teams coordinating AI-assisted product, growth, and operational work.
Learn more about Agent Teams