Skip to content

Projects

Things I've built

My own tools, plus open-source model APIs and demos built with LitServe and PyTorch.

Filter projects by category

10 projects

  • Developer ToolsFeatured

    An efficient open-source OCR engine for receipt image processing. Combines Tesseract OCR for raw text extraction with LLM-powered structured data parsing — available as a CLI tool and FastAPI service.

    • Python
    • OCR
    • LLM
    • FastAPI
    760 stars91 forksGitHubTry the app
  • Developer ToolsOct 1, 2026

    A Rust CLI that makes a fresh VPS ready and secure: audit, plan, apply and roll back, without locking yourself out.

    • Rust
    • CLI
    • SSH
    • Security
  • Model ServingMar 12, 2026

    Text-to-Speech API built on Resemble AI's Chatterbox model with LitServe. Supports zero-shot voice cloning, emotion intensity control, and base64 audio I/O.

    • LitServe
    • TTS
    • Voice Cloning
    • AI
  • Computer Vision & Medical AIMar 10, 2026

    Real-time object detection API using RF-DETR, a transformer-based model, deployed with LitServe. End-to-end inference with no region proposals or anchor boxes required.

    • LitServe
    • Object Detection
    • Transformers
    • Computer Vision
  • Model ServingOct 15, 2024

    A curated collection of AI serving examples built on LitServe, Lightning AI's inference engine. Covers speech, vision, LLMs, embeddings, and object detection.

    • LitServe
    • AI
    • APIs
    • Production
  • Multimodal LLMsAug 31, 2024

    Deploy and chat with Alibaba's Qwen2-VL multimodal large language model using LitServe. Supports image understanding, document parsing, and visual reasoning tasks.

    • LitServe
    • Multimodal
    • LLM
    • Qwen
  • Multimodal LLMsAug 16, 2024

    Deploy MiniCPM-V 2.6 — a multimodal LLM designed for edge devices — using LitServe. Handles single image, multi-image, and video inputs.

    • LitServe
    • Multimodal
    • LLM
    • MiniCPM
  • Multimodal LLMsMay 23, 2024

    Deploy and chat with Microsoft's Phi 3.5-vision multimodal LLM. LitServe serves the model while a Streamlit frontend gives you multi-image chat, comparison, and video summarization.

    • LitServe
    • Multimodal
    • LLM
    • Streamlit
  • Computer Vision & Medical AIApr 24, 2022

    3D semantic segmentation of lung tumours from CT scans using PyTorch Lightning and MONAI. Trained on the Medical Segmentation Decathlon lung dataset with a U-Net based architecture.

    • PyTorch
    • MONAI
    • Medical AI
    • Segmentation

Contact

Say hello.

Products, open-source tools, infrastructure, or a research idea: I'm open to talking about any of them. Message me on LinkedIn or leave a note in the chat; I read both.

Not ready to talk? Stay in the loop.

New posts, releases, and the occasional research note, sent only when there's something worth sharing.