# alexpinel/Dot

Text-To-Speech, RAG, and LLMs. All local!

Repository: https://github.com/alexpinel/Dot
Canonical: https://ross.abutalabs.com/products/alexpinel-dot
Homepage: https://dotapp.uk/
Language: JavaScript
License: GPL-3.0
License Family: copyleft
Topics: embeddings, llm, local, rag, standalone, standalone-app, document-chat, faiss, langchain, privategpt, llamacpp, self-hosted, phi-3, tts, whisper-cpp
Last push: 2024-12-09T15:46:44+00:00

## Health v2 (maintenance only)
Score: 16/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 64
- inputs: {"age_days": 901, "days_push": 632, "days_rel": 632, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1911, forks 110 (observed 2026-08-28T04:05:53.201989+00:00)

## What it is
Dot is a standalone Electron desktop application for chatting with your documents using fully local LLMs and Retrieval Augmented Generation. It bundles llama.cpp, FAISS vector stores, LangChain, Whisper speech recognition, and text-to-speech so everything runs offline with no data leaving the device.

## Use cases
- chat with pdf documents locally
- ask questions about my files without uploading them
- offline private chatgpt alternative
- run a local llm rag app on windows or mac
- query spreadsheets and docs with ai privately
- talk to documents with voice using whisper and tts

## When to choose
- you need document Q&A with strict privacy or offline operation
- you want a no-code, install-and-run local RAG app
- you're on Apple Silicon or Windows and want bundled TTS/STT

## When to avoid
- you need Linux support (not yet available)
- you want a server-side or multi-user hosted deployment
- you need cutting-edge model performance beyond small local LLMs

## Facets
- artifact type: application
- maturity: active
- function: rag, llm-inference, chatbot, speech-recognition, tts, pdf
- domain: large-language-models, privacy, self-hosted, files
- platform: windows, cross-platform
- tags: local-llm, document-chat, faiss, langchain, llamacpp, offline, privategpt-alternative, phi-3, retrieval-augmented-generation, macos, electron, desktop

## Member repositories
- alexpinel/Dot (main) score 16

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:53.201989+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 2026-08-30T03:10:47.074859+00:00, confidence not recorded.
  - readme: https://github.com/alexpinel/Dot (fetched 2026-08-28T04:05:53.201989+00:00, sha 06645a48e3cd)
  - homepage: https://dotapp.uk/ (fetched 2026-08-29T10:50:15.694539+00:00, sha e5979f4f345c)
- Data as of 2026-08-30T08:39:29.467469+00:00.