โ— Shell
clean mode source โ†—

Pringled - Overview

Skip to content

Navigation Menu

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Sign up

Appearance settings

Hi there ๐Ÿ‘‹

I'm Thomas van Dongen. I'm head of AI engineering at Springer Nature and co-founder of Minish, an open-source NLP lab working on efficient models and packages.

LinkedIn Google Scholar Website


Open Source Projects

Project Description
semble A code-search MCP/CLI tool for AI agents that drastically reduces token consumption
model2vec Distill sentence transformers into static embeddings that are orders of magnitude faster
semhash Multimodal semantic deduplication, outlier detection, and representative filtering
pyversity Diversify search & retrieval results to reduce redundancy and improve coverage
vicinity Fast, lightweight nearest neighbor search with pluggable backends
model2vec-rs A Rust port of Model2Vec
tokenlearn Pre-train static embedding models
agentcheck A Go CLI that audits what an AI agent can access before you run it

Pinned Loading

  1. Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read

    Python 5.2k 225

  2. Fast State-of-the-Art Static Embeddings

    Python 2.1k 122

  3. Fast Multimodal Semantic Deduplication & Filtering

    Python 936 57

  4. Fast Diversification for Search & Retrieval

    Python 493 27