One dashboard for all your local AI coding agents. Switch providers, manage sessions, and orchestrate tasks across Codex, Claude Code, OpenCode, and OpenClaw. Zero cloud, local-first control plane.

Production LLM call layer for AI agents and tools: keep OpenAI/Anthropic/AI SDK/LiteLLM, hot-swap models with MDA presets, and add cache, retries, circuit breakers, key rotation, singleflight, and Python/TypeScript/Rust parity.

A plugin for ASReview allowing for switching between models during runtime.

MCP server for hot-swapping llama.cpp models in Claude Code - launchctl (macOS) + systemd (Linux)

⚙️ Advanced fallback plugin for OpenCode agents — model switching, retry with backoff, and context overflow handling

Lightweight web UI for llama.cpp with dynamic model switching, chat history & markdown support. No GPU required. Perfect for local AI development.

[TCCN 24] GAIKube: Generative AI-based Proactive Kubernetes Container Orchestration Framework for Heterogeneous Edge Computing

A lightweight Claude Code model/provider switcher | 一个精简的 Claude Code 模型/服务商快速切换神器

Hermes Agent plugin: auto model switching based on token quota and content type detection. 根据额度和内容类型自动切换模型，对话不中断。

OpenCode plugin to switch agent models between performance and economy modes

Self-hosted model switcher for agents with profile-based provider accounts, encrypted credentials, OpenAI-compatible proxying, and per-agent manual model selection.

Per-prompt model switching for Claude Code - /opus, /sonnet, /haiku

Hermes Agent skill for dynamic AI model switching via AI API Proxy

A hybrid CNN-Transformer deep learning system for distinguishing COVID-19, Normal, and Pneumonia from chest X-ray images

Minimal, zero-dependency provider switching for Claude Code — switch between Anthropic, OpenRouter, DeepSeek, Z.AI, Kimi, Qwen, MiniMax and custom endpoints

🕹️ Downshift - Start premium. Finish cheap. Downshift cuts long Pi Coding Agent session costs by switching from your premium model to an economy model when context gets expensive.

Anthropic-compatible Claude Code proxy for OpenCode Zen and OpenAI-compatible chat completions models.

Define your LLM providers once, then let llmroute dynamically route every prompt to the right model — a smart CLI switchboard for multi-provider AI workflows.

Portable AI project workspace system with version-controlled context and command routing for team collaboration, model/agent switching, and in-repo project documentation.

Secure OpenClaw installations with encrypted, compressed backups uploaded to Cloudflare R2 using a simple command-line interface.