Skip to content

E2e video documentation #34

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
iLevyTate merged 6 commits into from
Feb 27, 2026
+597 −2
Merged

E2e video documentation #34

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
408f7aa
docs: add E2E walkthrough documentation with 32 annotated screenshots
cursoragent Feb 27, 2026
3f4cb44
docs: add 5 E2E walkthrough videos from production AppImage
cursoragent Feb 27, 2026
e6a3891
docs: add working AI analysis, Organize phase, and Knowledge OS demo
cursoragent Feb 27, 2026
9ab28c8
docs: fix model path in AGENTS.md workaround
cursoragent Feb 27, 2026
7e2c2b3
docs: replace dev-mode artifacts with production AppImage captures
cursoragent Feb 27, 2026
2472f7d
docs: add complete Knowledge OS coverage — Understand + Relate tabs
cursoragent Feb 27, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 11 additions & 2 deletions AGENTS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,8 +58,10 @@ v20 but fails during `loadModel` in Electron for models over ~500 MB.
**Workaround:** Use the smaller Qwen 0.5B model (~469 MB) which loads and runs successfully:

```bash
# Download the smaller model
curl -L -o ~/.config/stratosort-core/models/qwen2.5-0.5b-instruct-q4_k_m.gguf \
# Download the smaller model into the CORRECT userData models directory
# IMPORTANT: The app's LlamaService looks in ~/.config/StratoSort Core/models/ (with space),
# NOT ~/.config/stratosort-core/models/ (the legacy postinstall path).
curl -L -o "$HOME/.config/StratoSort Core/models/qwen2.5-0.5b-instruct-q4_k_m.gguf" \
"https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct-GGUF/resolve/main/qwen2.5-0.5b-instruct-q4_k_m.gguf"

# Update settings to use it
Expand All @@ -72,6 +74,13 @@ with open(f, 'w') as fh: json.dump(s, fh, indent=2)
"
```

**Model directory note:** The `postinstall` script downloads models to
`~/.config/stratosort-core/models/` (lowercase, no space), but the running app resolves
models via `app.getPath('userData')` which is `~/.config/StratoSort Core/models/` (with
space). If a model exists only in the legacy path, the LlamaService will not find it and will
fall back to the default large model (which crashes). Always place models in the userData
path.

With this model, the full pipeline works: file import → AI analysis (90-95% confidence, ~50s/file on
CPU) → organization suggestions → semantic search.

Expand Down
Loading