# PromtEngineer/localGPT

Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.

Repository: https://github.com/PromtEngineer/localGPT
Canonical: https://ross.abutalabs.com/products/localgpt
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-26T04:52:30+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 85
- inputs: {"age_days": 1197, "days_push": 7, "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 22205, forks 2462 (observed 2026-08-28T04:11:32.438646+00:00)

## What it is
LocalGPT is a fully private, on-premise document intelligence platform that lets users chat with, summarize, and query their own documents using local GPT models, with no data leaving the device. It implements an advanced RAG pipeline with hybrid vector and full-text search, cross-encoder reranking, and a smart router between RAG and direct LLM answering.

## Use cases
- chat with my pdf documents locally
- ask questions about my files without uploading to the cloud
- build a private document Q&A system
- run RAG on my own machine with local LLMs
- summarize documents privately on-device
- search my document collection with AI

## When to choose
- privacy is critical and documents must never leave your device
- you want a self-hosted RAG pipeline with hybrid search and reranking
- you have a GPU or local hardware to run open-source LLMs
- you need a modular, configurable document intelligence stack

## When to avoid
- you want a fully managed cloud service with no local setup
- you lack the hardware to run local LLM inference
- you need multi-user enterprise document management out of the box
- you only need simple keyword search without LLM answering

## Facets
- artifact type: application
- maturity: active
- function: rag, llm-inference, search-engine, chatbot, nlp
- domain: large-language-models, artificial-intelligence, privacy, self-hosted
- platform: python, self-hosted, cross-platform
- tags: local-llm, document-qa, hybrid-search, vector-database, lancedb, reranker, private-ai, on-premise, retrieval-augmented-generation, docker, gpu

## Member repositories
- PromtEngineer/localGPT (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:32.438646+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 2026-08-29T16:57:41.836057+00:00, confidence not recorded.
  - readme: https://github.com/PromtEngineer/localGPT (fetched 2026-08-28T04:11:32.438646+00:00, sha affb94f8c96e)
- Data as of 2026-08-30T08:39:29.467469+00:00.