sdk▌

$22

sentry-nextjs-sdk

The Flags SDK (flags npm package) is a feature flags toolkit for Next.js and SvelteKit. It turns each feature flag into a callable function, works with any flag provider via adapters, and keeps pages static using the precompute pattern. Vercel Flags is the first-party provider, letting you manage flags from the Vercel dashboard or the vercel flags CLI.

Build backend AI with Vercel AI SDK v6, covering structured outputs, multi-modal capabilities, tools, and 15 error solutions. \n \n Supports text generation, structured outputs (objects, arrays, choices), speech synthesis, transcription, embeddings, and image generation across 69+ providers (OpenAI, Anthropic, Google, Cloudflare) \n Output API replaces deprecated generateObject/streamObject; use Output.object() , Output.array() , Output.choice() for type-safe structured data with Zod schemas \n

React chat interfaces with Vercel AI SDK v6, covering hooks, message parts, tool approval workflows, and 18 documented UI error solutions. \n \n Three core hooks: useChat for conversational AI, useCompletion for text generation, and useObject for structured output streaming \n Message content now accessed via .parts array (breaking change from v5) with support for text, tool invocations, files, reasoning, and source citations \n Tool approval workflows enable human-in-the-loop confirmation befor

CloudBase document database Web SDK for querying, creating, updating, and deleting data in web applications. \n \n Supports CRUD operations, complex queries with operators (gt, gte, lt, lte, eq, neq, in, nin), and method chaining for filtering, sorting, and field selection \n Includes pagination via skip/limit, aggregation pipelines, geolocation queries, and real-time data synchronization with watch() listeners \n Requires SDK initialization with environment ID and authentication before database

Reference documentation and hands-on guidance for building AI-powered applications with the Vercel AI SDK. \n \n Covers core APIs for text generation, streaming, tool calling, structured output, embeddings, and agent building with ToolLoopAgent \n Includes React hooks (useChat, useCompletion) and framework-specific patterns for Next.js, SvelteKit, and other platforms \n Provides provider integration guides for OpenAI, Anthropic, Google, and others, plus AI Gateway setup for unified model access

sentry-browser-sdk

JavaScript SDK for building features in existing Base44 projects with CRUD operations, authentication, AI agents, and backend functions. \n \n Provides modules for entities (data models), auth, agents, functions, integrations (AI, email, file uploads), analytics, and user management \n Requires an initialized Base44 project with base44/config.jsonc ; use base44-cli skill for new project setup \n Includes critical API reference tables to prevent hallucination of method names (e.g., loginViaEmailP

Build stateful AI agents on Cloudflare Workers with persistent state, RPC methods, scheduling, and workflow orchestration. \n \n Core features include SQLite-backed state management, callable RPC methods via @callable() , one-time and recurring task scheduling, and durable multi-step workflows \n Supports MCP server integration (both client and server modes), email routing with secure replies, and streaming chat with resumable streams on disconnect \n Includes React hooks ( useAgent , useAgentCh