- Austin, TX
- www.asianefficiency.com
- @runsonai
- humanrouter
-
granola-live Public
Query your in-progress Granola meeting transcript from any MCP-capable coding agent (Claude Code, Codex, etc.). Summarize, query, or research a live conversation while you're still recording.
Python MIT License UpdatedJun 11, 2026 -
mlx-ddtree-failed Public
DDTree speculative decoding for Qwen 3.5/3.6 on Apple Silicon — what we tried and why raw inference still wins
Python UpdatedApr 25, 2026 -
spark-vllm-docker Public
Forked from eugr/spark-vllm-dockerDocker configuration for running VLLM on dual DGX Sparks
Shell MIT License UpdatedApr 20, 2026 -
ddtree-mlx Public
Tree-based speculative decoding for Apple Silicon (MLX). ~10-15% faster than DFlash on code, ~1.5x over autoregressive. First MLX port with custom Metal kernels for hybrid model support.
-
exo Public
Forked from exo-explore/exoRun frontier AI locally.
Python Apache License 2.0 UpdatedApr 8, 2026 -
TextExpander snippet that pastes your Google Calendar availability with one keystroke
-
xbm-cli Public
CLI for managing X/Twitter bookmarks. Works great with Claude Code and OpenClaw.