Louis Forster

Applied ML and systems work. Recent projects include graph-based retrieval for collaborative AI software and offline local-LLM tooling for Jetson devices.

Projects

  • OpenJet

    Link

    Claude Code for local LLMs. The fastest way to put a self-hosted coding agent on your own machine.

    • - Reads files, edits code, and runs commands fully offline. The Claude Code workflow without the cloud.
    • - Collapses a weekend of backend, runtime, and agent setup into a single install. Shipped on PyPI.
  • Treyspace

    Link

    AI-native canvas. Excalidraw boards become a queryable knowledge graph that beats semantic-only retrieval.

    • - Shipped to production on Azure and GCP, running real-time collaborative sessions for early users.
    • - Built solo end-to-end over ten weeks: ingestion pipeline, GraphRAG, auth, and billing.

Experience

  • Visual Computing Research Intern

    Bristol Vision Institute

    Jun-Jul 2025

    Fine-tuned RAFT and DPFlow optical-flow models on Sintel with synthetic noise, adding bidirectional warping, forward-backward consistency, and adaptive occlusion masking. Stabilised the self-supervised pipeline beyond prior state of the art. Second author on an IEEE IMCE 2026 paper.

  • Teaching Assistant

    University of Bristol

    Sep 2023-Apr 2025

    Taught around 200 undergraduates across Linear Algebra, C, Discrete Mathematics, and Data Science.

  • Software Engineer Intern

    Scribblepad Press

    Jul-Sep 2024

    Owned web deployment and site optimisation. Increased organic traffic by 119%.

Contact: louisforster64@gmail.com