Vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Plugins Filament, paquetes Laravel y starter kits open source mantenidos activamente. Todo MIT, con releases para v3, v4 y v5 cuando aplique.
A high-throughput and memory-efficient inference and serving engine for LLMs
Unified AI router with 356 providers, RTK+Caveman compression, auto fallback, MCP/A2A, desktop, PWA, and OpenAI-compatible APIs.
Extensible local model router for Codex and Cursor
See exactly what your coding agent sends to the model — a local logging reverse-proxy + web dashboard for Claude Code, Codex, DeepSeek-TUI, Reasonix, and Kimi. Just run `ccglass`.
Model-neutral agent desktop/runtime for private, enterprise, and OpenAI-compatible / Anthropic-compatible model API. Tested on DeepSeek, Qwen, Kimi, GLM models. Supports MCP, Skills,and local code search.
Todos los paquetes tienen CI, tests Pest e issues abiertas marcadas con good first issue.
Nueva versión disponible.