# freedmand/semantra-python

Multi-tool for semantic search

Repository: https://github.com/freedmand/semantra-python
Canonical: https://ross.abutalabs.com/products/semantra-python
Language: Python
License: MIT
License Family: permissive
Topics: cli, machine-learning, semantic-search
Last push: 2024-08-27T18:19:02+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 89
- inputs: {"age_days": 1251, "days_push": 736, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2711, forks 160 (observed 2026-08-28T04:07:11.817404+00:00)

## What it is
Semantra is a command-line tool that semantically indexes text and PDF documents and launches a local web application for querying them by meaning. It is designed to be easy, configurable, and private, running entirely on the user's machine.

## Use cases
- search pdf documents by meaning instead of keywords
- semantically search a collection of text files locally
- sift through leaked documents on deadline as a journalist
- query themes across research papers or books
- build a private semantic search engine without cloud services
- interactively explore document collections in a local web interface

## When to choose
- you need semantic search over local text or PDF files with a friendly UI
- privacy matters and you want everything running locally
- you want a one-command setup for a specialized search engine

## When to avoid
- you need a scalable production search service for many users
- you only need simple keyword/full-text search
- you need to index non-text formats like images or audio

## Facets
- artifact type: cli-tool
- maturity: active
- function: search-engine, cli, nlp, machine-learning, pdf
- domain: developer-tools, pdf
- platform: cli, python, cross-platform, self-hosted
- tags: semantic-search, local-web-app, document-search, embeddings, privacy-first, search, natural-language-processing, command-line, web-server

## Member repositories
- freedmand/semantra-python (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:11.817404+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:15:34.387276+00:00, confidence not recorded.
  - readme: https://github.com/freedmand/semantra-python (fetched 2026-08-28T04:07:11.817404+00:00, sha c1fe2db2f4e4)
- Data as of 2026-08-30T08:39:29.467469+00:00.