Orchestrate deployment and configuration of local LLM inference servers for OpenCode.
npx skills add https://github.com/Aveer/OpenZeus --skill zeus-llm
Please help me install this Agent Skill. Skill: zeus-llm Source: https://github.com/Aveer/OpenZeus/tree/main/skills/zeus-llm Command: npx skills add https://github.com/Aveer/OpenZeus --skill zeus-llm
This Skill simplifies the complex setup and configuration of local LLM environments, including llama.cpp, llama-swap, and Ollama, ensuring seamless integration with OpenCode.
Use the zeus-llm skill to configure the llama.cpp server for local model inference.
High-intent search queries and answers about installing and using this skill.
This Skill orchestrates local LLM inference servers like llama.cpp and Ollama to integrate with OpenCode. It provides ready-to-use configuration templates and proxy routing to connect local model backends into your workspace through standardized, OpenAI-compatible API endpoints.
To manage load balancing across local LLM models, this Skill configures llama-swap proxy routing. It sets up fallback strategies and balances requests across multiple backend models, ensuring high-performance local model execution without manual routing intervention.
Yes, you can use Ollama and llama.cpp together. This Skill provides unified LLM management that standardizes the installation and operation of various local inference engines, allowing you to operate them side-by-side within the same local infrastructure.
You can expose local models through an OpenAI-compatible API by configuring proxy routing via this Skill. It sets up standardized API endpoints for your local model backends, ensuring OpenAI-compatible API compatibility for downstream applications.
Yes, OpenCode works with local LLM backends. This Skill facilitates seamless integration by providing ready-to-use configuration templates that connect local inference engines like Ollama and llama.cpp directly to the OpenCode workspace.
kwcantrellServe local GGUF LLMs with an OpenAI-compatible HTTP API.
tadod12Serve LLM inference via OpenAI-compatible endpoints using vLLM.
GarrettRoiOptimize LLM inference with TensorRT-LLM on NVIDIA GPUs.
afel6Run GGUF-quantized LLM inference on CPUs and non-NVIDIA GPUs.
