Han Xiao
hanxiao
VP, AI @elastic Prev: founder & ceo @jina-ai
Languages
Repos
133
Stars
740
Forks
86
Top Language
Python
Loading contributions...
Top Repositories
Telegram bridge for Claude Code
Pure MLX implementations of UMAP, t-SNE, PaCMAP, TriMap, DREAMS, CNE, MMAE, and NNDescent for Apple Silicon. Metal GPU for computation and video rendering.
UMAP in pure MLX for Apple Silicon. 30x faster than umap-learn.
PaCMAP in pure MLX for Apple Silicon. Pure GPU, no scipy/numba.
IO-aware batched K-Means for Apple Silicon, ported from Flash-KMeans (Triton/CUDA) to pure MLX. Up to 94x faster than sklearn.
MLX Local Serving (MLS) - Unified ASR, TTS, and Translation on Apple Silicon
Repositories
133Blog
IO-aware batched K-Means for Apple Silicon, ported from Flash-KMeans (Triton/CUDA) to pure MLX. Up to 94x faster than sklearn.
Telegram bridge for Claude Code
Pure MLX implementations of UMAP, t-SNE, PaCMAP, TriMap, DREAMS, CNE, MMAE, and NNDescent for Apple Silicon. Metal GPU for computation and video rendering.
Fast and memory-efficient exact kmeans
Real-ESRGAN on Apple Silicon via CoreML. 1.6x faster than MLX.
One-click deploy Qwen3.5-35B-A3B on GCP L4 (24GB VRAM) with llama.cpp + Open WebUI + nginx
Real-ESRGAN on Apple Silicon. Pure MLX, no PyTorch at runtime.
Autonomous LLM-driven optimization of mlx-vis NNDescent on Apple Silicon
UMAP in pure MLX for Apple Silicon. 30x faster than umap-learn.
PaCMAP in pure MLX for Apple Silicon. Pure GPU, no scipy/numba.
t-SNE in pure MLX for Apple Silicon. 12x faster than sklearn. FFT-accelerated (FIt-SNE) for O(n) scaling.
No description provided.
zvec-web is the official web frontend and documentation portal for Zvec
Minimal Nostr relay on Cloudflare Workers for OpenClaw agent-to-agent communication
A text-to-speech (TTS) and Speech-to-Speech (STS) library built on Apple's MLX framework, providing efficient speech synthesis on Apple Silicon.
Telegram Desktop messaging app
Telegram-iOS
Universal memory layer for AI Agents
Build Real-Time Knowledge Graphs for AI Agents
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
A lightweight, lightning-fast, in-process vector database
OpenViking is an open-source context database designed specifically for AI Agents. OpenViking unifies the management of context (memory, resources, and skills) that Agents need through a file system paradigm, enabling hierarchical context delivery and self-evolving.
MLX Local Serving (MLS) - Unified ASR, TTS, and Translation on Apple Silicon
:sunglasses: Curated list of awesome lists
:closed_book: A minimal Markdown editor desktop app
A cool 3D hover effect for your awesome web project.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
No description provided.
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.