Lean AI in LangBear

LangBear, a fully bootstrapped application, has developed a lightweight, provider-agnostic AI interface to avoid the maintenance burden and dependency issues of heavier frameworks like LangChain.js. The custom interface, defined by a simple TypeScript type, allows the app to switch between AI providers such as OpenAI, Gemini, Anthropic, and OpenRouter in a single commit. This lean approach enables flexible migration to cheaper AI options without sacrificing functionality.

LangBear https://langbear.com is fully bootstrapped. This means no investors' money to burn, no big budgets. All funding has been coming from my main job's income. This is why I made a decision early on to stay AI provider-agnostic as much as possible to have the flexibility to migrate to cheaper options. At first, I tried LangChain.js. It was too heavy and was burdensome to maintain. Too many dependencies. The API wasn't stable and oftentimes broke when I had to bump the version for security fixes. I decided to write a very lightweight interface that would satisfy all use cases of the app. I present it to you with all its glory as it is today: python import type z from "zod/v3"; export type AIProvider = { generateText<T extends z.ZodTypeAny prompt: string, schema: T, options?: AIProviderGenerateTextOptions, : Promise<z.infer<T ; transcribeAudio filePath: string : Promise<string ; }; export type AIProviderThinkingConfig = | { // 0 disables thinking, -1 lets the provider choose automatically thinkingBudget: 0 | -1; thinkingLevel?: never; } | { thinkingBudget?: never; thinkingLevel: "MINIMAL" | "LOW" | "MEDIUM" | "HIGH"; }; export type AIProviderGenerateTextOptions = { model?: string; thinkingConfig?: AIProviderThinkingConfig; }; So far, I've already tried OpenAI, Gemini, Anthropic, OpenRouter and switching between providers only takes 1 commit. In the code, you would use it like this: function translateText aiProvider: AIProvider, model: string, text: string, targetLang: string, : Promise<string { const { translatedText } = await aiProvider.generateText getTranslateTextPrompt text, targetLang , z.object { translatedText: z.string } , { model, }, ; return translatedText; } await translateText geminiProvider, "gemini-3.5-flash", "hej", "en" // hello Implementation of this interface is trivial. Here's a partial implementation for the Gemini provider for generateText function: async function generateText<T extends z.ZodTypeAny prompt: string, schema: T, { geminiApiKey, model, thinkingConfig }: GenerateTextOptions, : Promise<z.infer<T { const gemini = new GoogleGenAI { apiKey: geminiApiKey, } ; const config: GenerateContentConfig = { responseMimeType: "application/json", responseJsonSchema: zodToJsonSchema schema , }; const geminiThinkingConfig = toGeminiThinkingConfig thinkingConfig ; if geminiThinkingConfig { config.thinkingConfig = geminiThinkingConfig; } const response = await gemini.models.generateContent { model, contents: prompt, config, } ; if response.text { throw new Error "no content" ; } return schema.parse JSON.parse response.text ; }