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

Python SDK for building AI applications, agents, and integrations with 150+ inference.sh models. \n \n Supports sync and async execution with streaming progress updates, fire-and-forget task submission, and stateful sessions for warm worker continuity \n Agent SDK includes template agents, ad-hoc agent creation with custom tools, and built-in capabilities like web search, code execution, and image generation \n Tool builder API enables four tool types: client tools (run in your code), app tools

Secure, isolated code execution environments on Cloudflare Workers with multi-language support. \n \n Provides exec() for shell commands, runCode() for LLM-generated code with state persistence, and file operations (read, write, mkdir, list) \n Supports Python, JavaScript, and TypeScript with a base image including Python 3.11, Node.js 20, and common tools; extend via Dockerfile for additional dependencies \n Includes code interpreter contexts for data analysis workflows, port exposure for HTTP

Use this skill when:

Use the Kernel Python SDK when you need to:

sentry-ruby-sdk

Programmatic agent runtime for embedding Copilot's agentic workflows in applications across Python, TypeScript, Go, and .NET. \n \n Exposes the same production-tested engine behind Copilot CLI with support for streaming responses, custom tool definitions, and multi-turn conversations \n Supports four language runtimes (Node.js 18+, Python 3.8+, Go 1.21+, .NET 8.0+) with consistent APIs across all platforms \n Enables integration with MCP servers for pre-built tools, custom agent personas with sp

AI SDK documentation and guidance for building AI-powered features with Vercel's framework. \n \n Covers core APIs including generateText , streamText , ToolLoopAgent , embed , and tool calling across multiple AI providers (OpenAI, Anthropic, Google, etc.) \n Supports building agents, chatbots, RAG systems, and text generation with structured output and streaming capabilities \n Includes React hooks ( useChat , useCompletion ) and framework-specific patterns for Next.js, SvelteKit, and other pla

When implementing SDK features or debugging provider-specific issues, check reference implementations.