Show HN: An n8n alternative where coding agents build the workflows, not humans

Velane launches an open-source n8n alternative that lets AI agents build, test, and deploy workflows autonomously via MCP, eliminating manual coding of integrations. The platform supports 800+ tools, sandboxed execution, and environment promotion, targeting solo developers and teams using AI coding assistants.

Don't write workflows. Let your agent do it. Connect Velane to Cursor or Claude via MCP. Your agent creates workflows, pulls integration docs, tests against dev, and promotes to production — without leaving the chat. Integrations 800+ tools. Zero tokens in your code. Your agent discovers connected accounts and calls any API through Velane — no OAuth flows, no credentials, no glue code. Who it's for Built for developers who ship with AI Whether you're a solo developer or part of a larger team, Velane fits the way you already work. Solo developers You're building an AI agent and don't want to maintain a backend just to call Stripe or Slack. Velane handles the runtime, OAuth, and deployment pipeline so you can stay in your editor. - Ship integrations in one agent conversation - No OAuth plumbing or credential management - Open source — self-host or use the hosted version - Sandboxed execution, no infra to manage Teams Your agents need shared credentials, audit trails, and controlled rollouts. Velane gives every team member's agent the same integrations without anyone touching a secret. - Shared credential store — one OAuth connection per provider - Environment promotion: dev → staging → prod - Invocation logs and audit trail per tenant - Role-based access: invoke, manage, admin scopes How it works Your IDE is now your deployment pipeline. One MCP connection. Your agent handles the rest — writing, testing, and shipping production workflows autonomously. Create & Connect Your agent calls list connections to discover your OAuth accounts, fetches live API docs for any provider, then writes Bun or Python code and saves it as a versioned workflow. Run & Debug The agent invokes the workflow on dev, reads execution logs with get logs , and autonomously fixes errors — all without leaving the chat window. Each run is isolated in an ephemeral sandbox. Promote Once tests pass, the agent calls publish snippet with env: "prod" . Your workflow goes live at a stable HTTP endpoint — versioned, audited, and rollback-ready. Setup Two lines to connect. One handler to ship. Add Velane to your MCP config, then your agent writes real Bun or Python code. No credentials in code — the proxy injects auth automatically. { "mcpServers": { "velane": { "url": "https://mcp.velane.sh/mcp", "headers": { "Authorization": "Bearer vl xxxx" } } } } js // No credentials — proxy injects auth const PROXY = process.env.VELANE PROXY URL; const TENANT = process.env.VELANE TENANT ID; export default async function handler { customerId } { const customer = await fetch ${PROXY}/v1/proxy/stripe/v1/customers/${customerId} , { headers: { 'X-Velane-Tenant': TENANT } } .then r => r.json ; await fetch ${PROXY}/v1/proxy/hubspot/crm/v3/objects/contacts , { method: 'POST', body: JSON.stringify { properties: { email: customer.email }, } } ; return { synced: true }; } Comparison Why not just use... Lambda handles execution. Pipedream handles workflows. Neither was designed for AI agents that write, test, and ship code autonomously. | Feature | DIY / Lambda | Pipedream | Velane | |---|---|---|---| | Agent-native via MCP | ||| | Zero OAuth setup | Partial | || | Isolated sandbox per invocation | ||| | Execution logs in your agent | ||| | Environment promotion dev → prod | ||| | Write code in your editor | ||| | Self-hostable | Pricing Simple, predictable pricing Start free on cloud or self-host under AGPL. Upgrade when you need more. Cloud Free For personal projects and exploration. Get started free https://app.velane.sh - 500 invocations / month - Up to 5 workflows - Shared runtime - All 800+ integrations - Community support Hobby For active builders and indie developers. Start building https://app.velane.sh - 10,000 invocations / month - Unlimited workflows - Shared runtime - All 800+ integrations - Email support - 30-day execution log history Dedicated For production workloads that need isolation and guarantees. Get started https://app.velane.sh - Unlimited invocations - Unlimited workflows - Dedicated cluster - All 800+ integrations - Priority support - Uptime SLA - Custom domain Self-host Personal / Small Startup Self-host the full stack under AGPL-3.0. Free forever for personal projects and startups building open-source products. View on GitHub https://github.com/abskrj/velane - Full source code access - Deploy on your own infra - OpenTofu configs for EKS included - Community support via GitHub Issues - AGPL-3.0 — changes must stay open source Commercial Self-host Velane in a proprietary product without the AGPL-3.0 copyleft requirement. Includes a commercial license for your entire organisation. Contact for a license mailto:abhi@velane.sh?subject=Velane%20Commercial%20License - Commercial license — no copyleft obligations - Self-host on your own infra - Full source code access - Priority email support - License covers your entire organisation FAQ Common questions Your agent is waiting for a runtime. Add two lines to your MCP config and let your agent ship its first workflow in minutes.