Sentence Transformers Python Packages

mteb

MTEB: State-of-the-art evaluation of embeddings across languages and modalities

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.

pmb-ai

Local-first persistent memory for AI coding agents (Claude Code, Cursor, Codex) over MCP. Decisions, lessons and facts live in one SQLite file on your disk. Offline, multilingual.

vaultspec-rag

GPU-accelerated semantic search for your docs and source code - hybrid dense + sparse RAG on a local Qdrant backend, served to Claude Code and other MCP clients. The search companion to vaultspec-core.

fast-sentence-transformers

Simply, faster, sentence-transformers

brainlayer

Persistent memory MCP for AI agents — SQLite, knowledge graph, 12 tools with ToolAnnotations

spacy-sentence-bert

Sentence transformers models for SpaCy

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.

easy-transformers

Utility functions to work with transformers

open-text-embeddings

Open Source Text Embedding Models with OpenAI Compatible API

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.

defenx-nlp

Lightweight semantic NLP building blocks for Python.

hierarchy-transformers

Language Models as Hierarchy Encoders

embeddingcache

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

rk-transformers

Export and Run Hugging Face Transformers Models on Rockchip NPUs

corpus-core

Shared infrastructure for corpus indexing + MCP search. Used by arxiv-radar-mcp and lab-corpus-mcp.

modern-bert-score

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

llm-behave

Behavioral testing for LLM applications. pytest plugin with semantic assertions, multi-turn conversation testing, and drift detection. No LLM judge needed.

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.

chainmem

ChainMem（链忆）— 链式 + 向量混合记忆系统，让 AI 拥有像人一样的联想式回忆

smartmemo

Semantic memory for LLM agent calls with an equivalence-first cache architecture.