# modem-works/dream-recorder

Dream Recorder is an open-source venture by Modem. Developed in close collaboration with Mark Hinch (software & hardware), Ben Levinas and Joe Tsao (industrial design), and Alexis Jamet (illustrations).

Repository: https://github.com/modem-works/dream-recorder
Canonical: https://ross.abutalabs.com/products/dream-recorder
Homepage: https://modemworks.com/projects/dreamrecorder/
Language: G-code
License: MIT
License Family: permissive
Last push: 2025-10-14T13:13:54+00:00

## Health v2 (maintenance only)
Score: 41/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 47, release rhythm 35, longevity 38
- inputs: {"age_days": 534, "days_push": 323, "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 1607, forks 129 (observed 2026-08-28T04:05:10.615348+00:00)

## What it is
Dream Recorder is an open-source DIY bedside device built on a Raspberry Pi 5 that records users speaking their dreams aloud and turns them into ultra-low-definition cinematic dream reels. It combines speech recognition, LLM-based prompt generation, and LumaLabs video generation, with a 3D-printable glow-in-the-dark shell and full hardware documentation.

## Use cases
- record and visualize my dreams as short videos
- build a DIY AI bedside device with a Raspberry Pi
- turn spoken dream descriptions into cinematic reels
- phone-free dream journaling device
- experiment with speech-to-video generative AI pipelines

## When to choose
- you want a hands-on DIY hardware project with full assembly guides and BOM
- you want an offline, app-free bedside dream journaling experience
- you want to tinker with a complete speech-to-video AI pipeline on a Raspberry Pi

## When to avoid
- you need a polished consumer product rather than a self-built device
- you don't want to pay per-dream API costs for OpenAI and LumaLabs
- you need high-definition video output rather than deliberately low-fi reels

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, llm-inference, video-processing, tts, machine-learning
- domain: artificial-intelligence, large-language-models, hardware, media, developer-tools
- platform: python, iot, self-hosted
- tags: raspberry-pi, diy-hardware, dream-journal, generative-ai, 3d-printable, bedside-device, openai-api, luma-labs, linux

## Member repositories
- modem-works/dream-recorder (main) score 41

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:10.615348+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 2026-08-30T03:51:48.359122+00:00, confidence not recorded.
  - readme: https://github.com/modem-works/dream-recorder (fetched 2026-08-28T04:05:10.615348+00:00, sha 42f0af738619)
  - homepage: https://modemworks.com/projects/dreamrecorder/ (fetched 2026-08-29T11:23:42.267656+00:00, sha 5dd981bb1ab8)
- Data as of 2026-08-30T08:39:29.467469+00:00.