If you can't own your tools, you don't own your future.
GoodQ builds local-first systems for memory, automation, and creative intelligence. The work is practical, inspectable, and meant to stay in the hands of the person running it.
GoodQ4All is the public local-first memory project: a Windows-first multimodal system that turns video, audio, and text into scene-level memory with visible proof paths.
Start with the two-minute onboarding film if you want to see the install and first ingestion loop before reading the deeper docs.
Watch the 2-minute guided demo · Open the repo · Read the demo guide
Each frame below is pulled from the final onboarding film and paired with the action it narrates. Click any frame to enlarge it.
| Step | Type or do this | Demo frame |
|---|---|---|
| 1 | Clone the official source:git clone https://github.com/GoodQ02/goodq4all.git |
 |
| 2 | Enter the project cabin:cd goodq4all |
 |
| 3 | Run the bootstrap installer:python scripts/bootstrap_install.pyCPU-safe first-run variant: python scripts/bootstrap_install.py --disable-gpu --disable-wsl-audio --skip-model-prefetch. |
 |
| 4 | Optional local config: copy .env.local.template to .env.local when using local model, cache, or provider settings. |
 |
| 5 | Validate the bootstrap:.\scripts\bootstrap_validate.bat |
 |
| 6 | Run the launcher/readiness check:.\LAUNCH_GOODQ.ps1 |
 |
| 7 | Start Watchdog, then drop one small media file into import_inbox:conda run --no-capture-output -n goodq_core python -m cli.watchdog |
 |
| 8 | Start the API and inspect proof:conda run --no-capture-output -n goodq_core python -m api.server |
 |
- Local-first memory: the supported runtime works without a required cloud dependency.
- Scene-centric ingestion: scenes are the atomic unit for video, audio, and text intelligence.
- Visible proof paths: runtime artifacts, manifests, logs, and API routes are part of the product surface.
- Operator-friendly flow: bootstrap, validate, launch readiness, start Watchdog, drop media, inspect proof.
Supported first-run host: Windows 11 with Git, Conda, Python 3.10+, and local disk space for the selected install path.
git clone https://github.com/GoodQ02/goodq4all.git
cd goodq4all
python scripts/bootstrap_install.py
.\scripts\bootstrap_validate.bat
.\LAUNCH_GOODQ.ps1Then leave Watchdog running in one terminal:
conda run --no-capture-output -n goodq_core python -m cli.watchdogDrop one small media file into the configured import_inbox, then start the API in another terminal:
conda run --no-capture-output -n goodq_core python -m api.serverOpen:
http://127.0.0.1:30000/api/health/summaryhttp://127.0.0.1:30000/docs
- Your data, your rules.
- Automate to liberate, not to surveil.
- Local truth beats cloud-shaped assumptions.
- Rigorous enough for production, friendly enough to invite curiosity.