The 5 pieces of AI plumbing every SaaS needs in 2026 (with code)

A developer has open-sourced five essential AI plumbing components for SaaS applications in 2026, providing working TypeScript code for Next.js 15. The components include streaming tokens via server-sent events, typed tool execution with Zod, usage metering to control API costs, prompt caching optimization, and robust SSE buffer parsing. The code is available in the MIT-licensed agentship-lite repository, with a full SaaS version called AgentShip offered as early access for £49.

Every SaaS is adding AI features in 2026. Most teams burn the first two weeks on the same five pieces of plumbing — none of which are the actual product. Here's each one, with working TypeScript for Next.js 15. Users won't stare at a spinner for 20 seconds. Stream tokens as they generate with server-sent events: js // app/api/chat/route.ts const runner = anthropic.beta.messages.toolRunner { model: "claude-opus-4-8", max tokens: 64000, thinking: { type: "adaptive" }, system: SYSTEM PROMPT, tools, messages, stream: true, } ; const stream = new ReadableStream { async start controller { for await const messageStream of runner { for await const event of messageStream { if event.type === "content block delta" && event.delta.type === "text delta" { controller.enqueue encode data: ${JSON.stringify { text: event.delta.text } }\n\n ; } } } controller.close ; }, } ; return new Response stream, { headers: { "Content-Type": "text/event-stream" } } ; The difference between a chatbot and a product is tools — the model acting on your data. Define them once with Zod; the SDK's tool runner handles the execution loop: js export const searchOrders = betaZodTool { name: "search orders", description: "Look up a customer's orders. Call when the user asks about order status.", inputSchema: z.object { email: z.string .email } , run: async { email } = db.orders.findByEmail email , } ; No manual agentic loop, no JSON schema by hand, inputs typed end to end. One enthusiastic user on your £10/month plan can generate £200 of API costs. Meter every request and weight output tokens they cost ~5x input : export function billableUnits u: Usage : number { return u.input tokens + u.cache read input tokens ?? 0 / 10 + u.output tokens 5; } // After each response: await recordUsage userId, billableUnits message.usage ; // Before each request: if await getUsage userId planLimit return quotaExceeded ; Prompt caching can cut input costs ~90% — but it's a prefix match . One interpolated timestamp in your system prompt and you pay full price on every request. Rules: js export const SYSTEM PROMPT = { type: "text" as const, text: STABLE INSTRUCTIONS, // never interpolate into this cache control: { type: "ephemeral" as const }, } ; Verify it works: usage.cache read input tokens should be non-zero from the second request on. Parse the SSE buffer across chunk boundaries — the naive split on every chunk drops tokens: js let buffer = ""; while true { const { done, value } = await reader.read ; if done break; buffer += decoder.decode value, { stream: true } ; const lines = buffer.split "\n\n" ; buffer = lines.pop ?? ""; // keep the partial event for the next chunk for const line of lines handleEvent line ; } All five pieces above are open source MIT in agentship-lite https://github.com/mt211211/agentship-lite — copy them into any Next.js app. If you want the full SaaS around it — Stripe subscriptions, auth, Postgres schema, plan gating wired to the metering — that's AgentShip https://mt211211.github.io/agentship-site/ , currently £49 early access.