Route AI model requests across providers via a local endpoint.
npx skills add https://github.com/traylinx/switchAILocal --skill switchailocal
Please help me install this Agent Skill. Skill: switchailocal Source: https://github.com/traylinx/switchAILocal/tree/main Command: npx skills add https://github.com/traylinx/switchAILocal --skill switchailocal
switchAILocal provides a unified local endpoint to route and manage requests across multiple AI providers, eliminating the need to individually configure and call each service.
Point your client at http://localhost:18080/v1 and issue a chat request using a provider-formatted model, such as geminicli:gemini-2.5-pro or ollama:llama3.2, or use auto-routing with switchai:auto.
High-intent search queries and answers about installing and using this skill.
Routing AI requests across providers uses a unified local endpoint at http://localhost:18080/v1. Point your client there and specify the provider using a formatted model name like geminicli:gemini-2.5-pro, ollama:llama3.2, or use switchai:auto for automatic routing across CLI tools, local models, and cloud APIs.
Yes. The unified endpoint integrates CLI tools, local models, and cloud APIs with provider prefixes and auto-routing. You can attach files to CLI providers, enable health checks, and set fallback strategies for reliable provider selection across your mixed stack.
A single local endpoint eliminates individual provider configuration. The pluggable architecture with provider executors and routing matrices lets you switch providers via model prefix or auto-routing, reducing operational complexity and centralized management overhead.
File attachment and context enrichment is built into the unified endpoint. Pass files or folders directly to CLI providers, and the system enriches prompts automatically, enabling richer interactions across your provider mix without manual payload construction.
Yes. Dynamic model selection with health checks and fallback strategies ensures reliability. If a provider is unavailable, the routing logic automatically selects an alternative, maintaining uptime across your integration.
Optional security hardening is available to meet deployment security needs. The pluggable architecture supports enforcement policies within the routing and provider execution layer, protecting your local endpoint configuration.
Rust-sohamConfigure Golem Cloud CLI authentication and deploy apps via golem.yaml.
Proxy2021Aggregate endpoint metrics, latency, and alert status to monitor API health.
liaoxinjie666Convert OpenAI, Anthropic, and Gemini protocols through a local proxy layer.
salvo-rsForward client requests to configurable backend services via a reverse proxy.
