Description: "A 100% offline, privacy-first personal AI vault preserving family oral histories, memories, and personal anecdotes. Built for Hacktoberfest 2026: Ghost in the Machine."
tags: "devchallenge, hacktoberfest, opensource, ai"
canonical_url: false
cover_image:
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine
"Some voices deserve to live forever."
What I Built
Every family has stories that live only in the voices of aging grandparents, faded handwritten index cards, or casual Sunday afternoon conversations:
- The exact way Nani brewed cardamom chai when the monsoon started.
- The afternoon Uncle Leo held his trenchcoat over a drenched saxophone player during the 1989 Jazz Festival in the rain.
- Grandpa Joe's 1968 blue Chevy pickup and the summer road trips before interstates existed.
When these voices fade, those stories are often lost forever.
Echoes is an offline, privacy-first personal AI application engineered to preserve family oral histories, memories, and personal anecdotes using 100% open-source AI running directly on your own computer.
Interpreting the Theme: Ghost in the Machine
In folklore and fiction, a "ghost" is an echo of a life once lived. While technology often tries to simulate deceased people with conversational bots, we believe that crossing into supernatural imitation is ethically fraught and emotionally dissonant.
We interpreted the theme through a grounded, human lens:
- The Machine: A 100% offline local computer running open-weight language models and speech recognition engines in complete isolation from the cloud.
- The Ghost: The indelible human spirit captured in authentic voice recordings, spoken memories, and family narratives.
- The Creative Track ("Ghost Story Mode"): A playful, vintage CRT terminal where users can select keepsake props from real memories (an old watch, a recipe, a jazz cassette) and have the local AI weave them into atmospheric gothic campfire tales—always prominently certified as 100% artistic fiction.
Key Capabilities
-
🏛️ The Memory Vault: Record voice stories in your browser or upload audio files (
.wav,.mp3,.m4a), paired with rich text narratives, dates, relatives, and tags. Search everything instantly with offline hybrid search. - 🎙️ Local Voice Transcription: Converts spoken recordings to text locally via Whisper—no audio ever leaves your computer.
- 📻 AI Memory Assistant (RAG): Chat with your family memories. The assistant answers questions strictly using your saved stories, citing exact memories as sources and refusing to invent or hallucinate facts.
- 🕯️ Remembrance Studio: Create a digital tribute honoring a loved one—weaving their favorite songs, comfort foods, life motto, and memories into a respectful memorial message with a standalone printable HTML keepsake.
- 👻 Ghost Story Mode: Retro green CRT scanline terminal with a 1-to-5 Horror Intensity Slider (Cozy Twilight to Gothic Nightmare) that spins creative campfire fiction inspired by keepsake motifs.
- 🛡️ 100% Zero-Cloud Privacy Guarantee: No cloud API keys. No OpenAI, Gemini, or Claude. No telemetry. Your memories belong to your family alone.
Demo
Video Walkthrough
An interactive animated walkthrough demonstrating the Memory Vault, Local Transcription, RAG Memory Assistant, Remembrance Studio, and Ghost Story Terminal:
(A high-resolution demo recording is included in the repository at docs/media/echoes_app_tour_1793469836415.webp)
Live Interface Screenshots
| Memory Vault & Detail Modal | Remembrance Studio Tribute |
|---|---|
 |
 |
| Ghost Story Mode CRT Terminal | Voice Keepsake Recorder |
|---|---|
 |
 |
Local Quickstart (Ready in Under 2 Minutes)
Because Echoes is built for total privacy, it runs entirely on your local machine:
bash
# 1. Clone repository
git clone https://github.com/ashutosh-ranjan/ghost-in-the-machine.git
cd ghost-in-the-machine
# 2. Start local AI model (using Ollama)
ollama pull llama3.2:3b
# 3. Launch both backend & frontend
# On Windows PowerShell:
.\scripts\run_all.ps1
# Or with Docker Compose:
docker compose up --build
Top comments (0)