Thin, file-based CLI that routes a multi-step article workflow (brief → outline → draft → review → final) across OpenAI and Anthropic with fallback, schema validation, judge-model evaluation, and platform profiles (Qiita/Zenn/blog/note).
Give every opencode model multimodal capabilities by routing attachments to a fallback multimodal model. Configure everything via the /multimodal command.
Cloud fallback adapter for the Expo AI Runtime. POSTs to a configurable backend (OpenAI / Anthropic / Gemini / Bedrock / custom) with streaming via expo/fetch.
Priority-based LLM routing across multiple providers to reduce cost with free-first and fallback chains.
Safety Type Conversion Utility Library, providing type judgment and conversion methods with fallback values
Provider-agnostic, modality-aware language model router with fallback for the Vercel AI SDK.
Native sharing using the Web Share API if supported, a beautiful fallback if not.
Generate fallback values for content with alt text
Unified multi-provider LLM caller with automatic fallback
Fallback ads for React Native & Expo (JS only)
MCP server that completes prompts with automatic provider fallback across OpenAI, Anthropic Claude, and Google Gemini. Handles rate limits, transient errors, and missing keys by trying the next provider in chain. Returns first success with full attempt lo
Resilient loader for Module Federation remotes: retry with exponential backoff, cache-busted dynamic-import recovery, deterministic fallback, idle prefetch, and telemetry hooks. Never let a single failed remote take down your shell. How to handle a failed
Multi-provider web search with automatic fallback, circuit breaking, and zero-config defaults — for AI agents and resilient apps.
API key rotation for pi-coding-agent. Multiple keys per provider, automatic 429/401 fallback, max-retries guard.
Composable resilience patterns: retry (with exponential backoff/jitter), circuit breaker, timeout, fallback. Inspired by Polly (.NET) and Tenacity (Python). Zero dependencies, TypeScript.
Generate a solid-color image from any color
Least Cost Routing for LLMs — route every model call to the cheapest available provider, fall back automatically, and track real cost. Built for the Vercel AI SDK.
Browser SDK for SpekoAI — real-time voice conversations
Official Speko TypeScript SDK — one API, every voice provider
Styled ASCII fallbacks for broken images using their alt text.
Local stdio bridge for the hosted SpekoAI MCP server
LiveKit adapter for Speko — run STT/LLM/TTS routing inside a LiveKit agent worker