5 packages found
Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 30 MCP tools (preview)
Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.
SGPT is a command-line tool that provides a convenient way to interact with OpenAI models, enabling users to run queries
An MCP server that gives a language model a structured, persistent scratchpad for hard thinking — staged reasoning + sel
🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️