Search Packages

mteb

MTEB: Massive Text Embedding Benchmark

model2vec

Fast State-of-the-Art Static Embeddings

setfit

Efficient few-shot learning with Sentence Transformers

beir

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

top2vec

Top2Vec learns jointly embedded topic, document and word vectors.

loremem-ai

Persistent AI memory for LLMs and AI agents. Local-first. Learns from every interaction.

fast-sentence-transformers

This repository contains code to run faster sentence-transformers. Simply, faster, sentence-transformers.

semantic-keywords

TF-IDF counts words. semantic-keywords understands meaning. It uses sentence embeddings (all-MiniLM-L6-v2 by default) and Maximal Marginal Relevance (MMR) to return keywords that are both relevant and diverse — not just the most frequent phrases. Works fully offline after a one-time model download. No API key. No rate limits.

classy-classification

This repository contains an easy and intuitive approach to few-shot classification using sentence-transformers or spaCy models, or zero-shot classification with Huggingface.

factlens

Geometric LLM hallucination detection. No second LLM. Deterministic. Auditable.

easy-transformers

Utility functions to work with transformers

obsidian-umbra

Turn any Obsidian vault into a Zettelkasten graph — locally, with a dozen years of notes in minutes. 4-phase pipeline: daily splitter (Qwen3-4B) → semantic backlinks (Potion-32M) → keyword linker → synonym clustering (GTE-large + HDBSCAN). Zero cloud.

schema-matching

A python tool using XGboost and sentence-transformers to perform schema matching task on tables.

spacy-sentence-bert

Sentence transformers models for SpaCy

hierarchy-transformers

Language Models as Hierarchy Encoders

splade-index

Fast search index for SPLADE sparse retrieval models implemented in Python using Numpy and Numba

context-lens

Semantic search knowledge base for MCP-enabled AI assistants. Index local files or GitHub repos, query with natural language. Built on LanceDB vector storage. Works with Claude Desktop, Cursor, and other MCP clients.

incite-app

Local-first citation recommendation system

rk-transformers

Export and Run Hugging Face Transformers Models on Rockchip NPUs

open-text-embeddings

Open Source Text Embedding Models with OpenAI Compatible API

modern-bert-score

Re-implementation of BERTScore for evaluation of generated text, leveraging vLLM and SentenceTransformers.

pyragix

Local-first Python RAG pipeline with sentence-transformer embeddings, FAISS/BM25 hybrid retrieval, query expansion, reranking, and Ollama-driven generation.

sentrev

Simple customizable evaluation for text retrieval performance of Sentence Transformers embedders on PDFs

embeddingcache

Retrieve text embeddings, but cache them locally if we have already computed them.