Unclaimed profileBuilt from public GitHub and Hugging Face activity. Raullen has not joined Lounge yet.Claim it
Not on Lounge yet
Raullen Chai
developer🛰️ Building AI that reads the physical world — Cogitating....
Public projects
Rapid-MLX
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.
Pythonanthropic-apiapple-siliconclaude-code
twinspark
Production-grade recipe for DeepSeek-V4-Flash-0731 (284B MoE) on 2x NVIDIA DGX Spark: self-healing 2-node vLLM cluster, reboot-verified, tuned DSpark speculative decoding (~75 tok/s), full benchmarks, OpenAI Codex CLI integration
Shelldeepseekdgx-sparkllm-inference
vnsh
One workspace all your AI agents can read and write. Encrypted client-side, model-agnostic, gone 24h after the last edit.
TypeScriptai-agentsclaudeclaude-code
homebrew-rapid-mlx
Homebrew tap for Rapid-MLX — AI inference for Apple Silicon
rapid-mlx-dsh-provider
Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.
JavaScriptapple-siliconcoding-agentdeepseek-harness
ai-math-kills-crypto
Does AI math kill crypto? Attack paths, resource comparisons and gaps for selected OpenAI Math results.
HTML
Likely stack
ClaudeOpenAILlamavLLMOllamaCursorMCP
