PyPI Stats
  • Insights
  • PyPI
  • GitHub
  • Search
  • Compare
  • Advisories
  • Ecosystem
  • About
Home

Search Packages

Find Python packages by name, description, GitHub topic, or filter by metrics
cereja-project
cereja

Cereja is a bundle of useful functions we don't want to rewrite and .. just pure fun!

9K 29 12
PaulMcInnis
jobfunnel

Scrape job websites into a single spreadsheet with no duplicates.

3K 2K 261
AreteDriver
memboot

Zero-infrastructure persistent memory for any LLM

1K 1 1
castnettech
mnemosyne-engine

LLM Context Compression and Retrieval Engine -- zero dependencies, sub-100ms queries, document + code ingestion

1K 53 9
castnettech
mnemosyne-ollama

State aware knowledge compression, ingestion, and hybrid retrieval engine. Zero dependencies. Sub-100ms queries.

721 53 9
andrewtavis
wikirec

Recommendation engine framework based on Wikipedia data

625 20 10
brunoarine
findlike

findlike is a package to retrieve similar documents

543 16 2
castnettech
mnemosyne-mcp

State aware knowledge compression, ingestion, and hybrid retrieval engine. Zero dependencies. Sub-100ms queries.

534 53 9
SauravPattnaikCS60
weighted-class-tfidf

Custom implementation of tfidf for imbalanced datasets

526 14 1
Jash271
youglance

Package for analyzing Youtube Videos from searching by relevant entities to analyzing sentiments and clustering different parts of the video according to your liking

468 1 0
andrewtavis
kwx

BERT, LDA, and TFIDF based keyword extraction in Python

460 76 12
parthjain18
sassyshell

A sassy, AI-powered CLI sidekick that remembers the commands you forget and mocks you into getting better.

234 8 3
Jash271
summarizeit

Package for analyzing Youtube Videos from searching by relevant entities to analyzing sentiments and clustering different parts of the video according to your liking

190 1 0
daedalus
llm-distiller

Model distiller automator

121 1 0
nikhiljsk
preprocess-nlp

A fast framework for pre-processing (Cleaning text, Reduction of vocabulary, Feature extraction and Vectorization). Implemented with parallel processing using custom number of processes.

67 10 4
    • Data from PyPI, GitHub, ClickHouse, and BigQuery