Skip to content
View T0mSIlver's full-sized avatar
8 followers · 5 following

Achievements

Achievement: YOLOAchievement: Pull Sharkx3Achievement: StarstruckAchievement: QuickdrawAchievement: Pair Extraordinaire

Achievements

Achievement: YOLOAchievement: Pull Sharkx3Achievement: StarstruckAchievement: QuickdrawAchievement: Pair Extraordinaire

Block or report T0mSIlver

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
T0mSIlver/README.md

Tom Vaucourt

AI engineer — LLMs, local inference, and developer tooling. I build end-to-end systems and contribute upstream to the tools I depend on.

Now: on-device speech for Apple Silicon — shipping localvoxtral and contributing the Voxtral realtime inference path to mlx-audio-swift.

Selected work

  • localvoxtral — native macOS menu-bar app for realtime, fully local dictation: words appear while you're still speaking, with optional on-device LLM polishing. Runs Mistral's Voxtral Mini 4B Realtime on Apple Silicon, or against any OpenAI Realtime-compatible backend. Swift
  • mlx-audio-swift — contributor to the Voxtral realtime streaming path: incremental mel/conv front end (O(N²) → O(N) per utterance), fp16 dtype fixes, Metal buffer-pool policy, and quantized tied-embedding loading — teaching the engine to load a 4-bit tied-head checkpoint I publish, which cuts the per-token LM-head projection ~10× (~30 ms → ~3 ms on an M1 Pro). Streaming went from ~1.9× slower than realtime to a flat 0.76 RTF. Swift
  • llama.cpp #20120 — merged: preserve Anthropic thinking blocks through the server's message conversion. C++
  • fastcontext — read-only repository-exploration agent that coding agents delegate to over bash: cited file:line answers, not context noise. Python
  • voxmlx — realtime Voxtral transcription in MLX; my fork adds an OpenAI-Realtime-compatible WebSocket server and Metal memory caps. 4-bit conversions on Hugging Face. Python
  • pi-intl-segmenter-fallback — diagnosed a V8 segfault (null icu::BreakIterator on small-ICU Node builds, nodejs/node#51752), filed it upstream with a proposed patch, and shipped this pure-JS Intl.Segmenter fallback to npm the same day. TypeScript
  • pi-llamacpp-provider — pi extension that registers a llama.cpp server as a provider and auto-discovers every model it exposes. JavaScript
  • skills — skills that let a coding agent delegate work to another coding CLI and keep itself in sync from git. Shell

Elsewhere

LinkedIn · Hugging Face · npm

Pinned Loading

  1. localvoxtral localvoxtral Public

    Talk to your coding agents by voice. Realtime, fully local macOS dictation that streams words as you speak and grounds LLM polishing in the exact Claude Code session under your cursor — Ghostty, iT…

    Swift 47 6

  2. skills skills Public

    Skills that let a coding agent delegate work to another coding CLI, and keep itself in sync from git.

    Shell 1

  3. ggml-org/llama.cpp ggml-org/llama.cpp Public

    LLM inference in C/C++

    C++ 121k 20.9k

  4. pi-llamacpp-provider pi-llamacpp-provider Public

    pi extension that registers your llama.cpp server as a provider and auto-discovers every model it exposes at /v1/models

    JavaScript

  5. voxmlx voxmlx Public

    Forked from awni/voxmlx

    Realtime Transcription with Voxtral in MLX

    Python 4 1

  6. pokemon-agent pokemon-agent Public

    Forked from NousResearch/pokemon-agent

    AI-powered Pokemon gameplay agent with headless emulation, REST API, and live dashboard. Works with any LLM.

    Python