Production resilience for the Anthropic SDK — circuit breaker, smart retry, and model fallback in three lines.

내 일을 대신해주는 막둥이들. Self-contained opencode plugin for 사내 workflow: per-stage specialist agents, deterministic shell gates, primary-only enforcement, and a model fallback advisor.

Resilient multi-model fallback chain for the Groq API. When one model fails, the next one tries. Users always get a response.

Pi extension that switches to a fallback model after provider failures such as 429 rate limits.

Plan model fallback chains from capability, cost, and health data.

Auto-switch the model on rate-limit / quota exhaustion by advancing a user-configured fallback chain

Smart model fallback for the Vercel AI SDK: reactive fallback on rate-limit/transient errors and proactive switching before limits are hit.

Keep OpenCode Zen apps running with ordered free and paid model fallback.

In-process Runtime implementation for @orchestral/core. Submits jobs, dispatches Patterns through a CapabilityRouter, walks the model fallback chain when a call fails, and dedupes by idempotency key. Same-model transient retry and cross-Pattern Alternativ

Model fallback chain extension for pi — automatic retry and failover across AI providers

Minimal LLM router with multi-model fallback chain. Zero dependencies. Works in CF Workers, Lambda, Node.js.

Dashboard settings surface for the pi-blackhole extension — reads and writes its on-disk pi-blackhole-config.json through validated server routes, including an ordered per-worker model fallback-chain editor.

Self-hosted AI Assistant plugin for NodeBB forums with automated unprivileged bot provisioning, multi-model fallback resiliency, thread history context, Unicode/Hebrew mention parsing, RAG, and support for Gemini, Grok, Claude, OpenAI, Groq, DeepSeek, Oll

Stable Pi model aliases with ordered fallback, cooldowns, and latency controls

OpenCode plugin that retries failed sessions with fallback models.

Smart model fallback for the Vercel AI SDK: reactive fallback on rate-limit/transient errors and proactive switching before limits are hit.

dsh plugin + agent preset that replicates opencode + oh-my-openagent (omo): opencode's toolchain and system prompt, omo's multi-role subagent orchestration, and browser-side omo role selection + per-role model/fallback settings.

Styrr multi-model fallback as a Strands Agents SDK Model provider.

Curated agents, skills, and commands for the OpenCode AI coding CLI — autonomous orchestrator, multi-agent code review, model fallback, and in-session asset creation tools.

Native-OS-chooser backend of the directory-picker seam for the DeepSeek Harness web GUI host