도구

High-throughput LLM inference and serving engine: vllm serve starts an OpenAI- and Anthropic-compatible server in one command. Supports 200+ model architectures from Hugging Face, quantization and distributed inference. Aimed mainly at NVIDIA, AMD and other GPUs.

AI pair programming in your terminal: builds a repo map of the whole codebase, auto-commits changes to git, works with Claude, DeepSeek, OpenAI and almost any other model including local ones, and can run lint and tests after edits.

Mistral's official open-source terminal coding assistant: uses Mistral models to read and write code, run commands and search the codebase, with multiple agent profiles and subagents, plus Skills, MCP and a --prompt scripting mode. Needs a Mistral API key.