TraceApps @ TraceApps @lemmy.world

Posts

14

Comments

48

Joined

2 mo. ago

Here is what i see as some differences today between CookTrace and Tandoor:

CookTrace:

• Pantry is a real first-class catalog, not a tag list. Barcode scanner, Open Food Facts + USDA lookup, per-item stock / serving size / nutrition, plus an "8 / 10 in pantry" match pill on every recipe card. Tandoor has the food list; CookTrace treats it as a primary surface.
• AI assistant with tool use — not just a chat bubble. Trace can log a cook, plan a cook, add things to the shopping list, mark a pantry item out of stock, import a recipe URL, etc. by reading and writing your real data
• FDA-style Nutrition Facts box auto-computed per recipe from pantry-linked ingredients
• Android app with full offline mode (on-device SQLite, differential sync when you reconnect)
• NutriTrace federation can import foods from NutriTrace directly into CookTrace's pantry.

Where Tandoor still wins today: PDF / image OCR bulk import, longer track record, larger ecosystem, iCal meal-plan feeds.

Importer's there in CookTrace, so you can move a copy over to compare with zero risk to your existing library whenever the time shows up.

Honestly, not automagically. CookTrace's bulk importers today handle JSON, HTML, schema.org Recipe markup, and full-backup zips from Mealie / Tandoor / Paprika. Plain text, RTF, and PDF aren't on that list yet, and there's no "point at a folder and import everything" mode.

What works today for the same end goal:

• Photo Import — point Trace AI at an image of any recipe (including a PDF you've screenshotted) and it extracts it. Fine for a handful, probably painful for hundreds.
• Trace AI chat — paste the recipe text into the assistant and ask it to create a recipe. Same idea, no image step.

A proper OCR import is a worthwhile feature. I created a feature enhancement request in the GitHub repo, so that in the near future I can set aside some time to explore how feasible it would be to implement.

That URL should import cleanly; it's a standard food blog with the markup the importer expects.

TikTok though, honestly, no. TikTok pages don't expose the recipe text to scrapers and the AI fallback has almost nothing to work with. A real TikTok URL importer would need to call TikTok's caption API and transcribe the video audio, which isn't built yet.

Workaround that may possibly work today: screenshot the recipe overlay (or the comment where the creator wrote it out) and use Photo Import the AI extracts the recipe from the image. Two taps, same result.

Not right now. I want to get all my apps past the RC stage and into stable GA but will certainly consider it in the future.

The app is primarily aimed at lifting weights but does also account for body weight exercises such as pullups, pushups, etc. with respect to walking/running/cycling etc, i have that incorporated into my other app which is primarily focused on nutrition/wellness called NutriTrace.

just added. Was a request for my other NutriTrace App so made sure to add it here as well.

Thanks for taking the time to write this out and thank you for the feedback that helped improve the onboarding process.

I completely respect your preference (as well as the community's). LLMs definitely have their flaws, and they aren't for everyone. For me, AI acts as a thoroughly tested extension of my workflow rather than a shortcut, but I know that doesn't fit every project's philosophy.

I really appreciate your mature approach to the "No thank you" mindset. I hope you find a solution that works perfectly for your needs and aligns with your principles!

Thanks for asking. Reception of this app has actually been positive overall since my first post here, with upvotes well ahead of downvotes.

Last week I posted about my newer app LiftTrace, which I also build with AI assistance. Once folks realized AI was part of how I work, "AI slop" became the read on that post and the downvotes came fast. I assume some of this week's downvotes here are coming from the same crowd reacting to a familiar name, which is fair. Everyone is entitled to their opinon and I respect that.

I've never hidden the AI involvement, and from what I can tell on the NutriTrace GitHub page real users are getting value out of it: stars are steadily climbing and issues and enhancement requests are coming in. I'll keep posting these updates because I think the apps are genuinely useful, I use them every day myself, and I wouldn't share them if I didn't believe they could help someone with their own health or fitness journey.

Happy to answer any other questions folks have.

Unfortunately there are no demo sites for either of the projects yet, that is planned for the future.

Understood. The public repo isn't where day-to-day work happens. Active development lives in a private dev repo and the public mirror gets squashed syncs at release time, which is why all you see are "chore: sync from lifttrace-dev (v1.0.0-rc.X)" entries.

Same pattern applies to my sister app NutriTrace. That public repo at TraceApps/nutritrace is at rc.42 right now, similar squashed-sync history, plus a couple of merged external PRs in the open, so the workflow isn't unique to one repo or trying to hide anything.

Reason for the split: the dev repo has a few files (internal planning docs, keystore config, that kind of thing) that aren't part of the shipped product, so I've been keeping it separate.

Appreciate the tip. Thanks!

Sorry to hear that. It's completely optional and you can go minimalistic with no banner if you so choose. Try it out and hopefully it works for you.

Cookidoo has no public API and their ToS prohibits scraping, so a direct integration would be both legally fragile and maintenance-heavy (the scraper breaks on every UI change Vorwerk pushes). The indirect path that works today: Mealie is a self-hosted recipe manager that imports Cookidoo URLs as one of its many recipe sources, and NutriTrace has Mealie integration built in (Settings → Mealie). Your wife adds recipes from Cookidoo into Mealie once, and they show up as searchable foods in NutriTrace with full nutrition.

Also worth mentioning: I've got a sister app called CookTrace (may not be final name) in development as a purpose-built self-hosted recipe manager that pairs natively with NutriTrace (same UI patterns, same AI assistant, federation already wired between them). It has a schema.org Recipe scraper for URL imports, though Cookidoo itself is gated content so it'd still need either a Mealie middle layer or manual entry. Currently private; aiming for a public release in the next month or so.

That is correct, and it is called out in the README under Apps → iOS and in the Support section at the bottom. iOS needs a Mac, an iPhone, and a paid Apple Developer account, none of which I currently have. The Support section is where I mention that donations go toward exactly that. Apple Health sync specifically needs a native iOS wrapper since the data isn't exposed to PWAs, so it has to wait on the same blocker. I hope to someday get this out to the community.

Nice work, exactly the kind of bridge that makes leaving MFP a lot less painful for self-hosters. Would you be OK with me linking the gist from the NutriTrace README (under Foods & Meals) and from inside the Bulk Food Import modal? Happy to credit it as your script with a link back to the gist.

Either way, thanks for putting it together.

thank you, appreciate it!

Let me know your issues and post server/browser console/app logs, and ill do my best to assist. You can also create an issue if you feel that this is a bug in the repo. Outside of this i do want to mention, im working on a suite of "Trace" apps. One of which is a Recipe app. I love Mealie, but wanted a bit more for myself, and have created something that i think will be special. It also allows for direct api integration to and from NutriTrace. Will hopefully have a beta that will be publicly available in the next month or so if interested.

latest update has been released!

Thank you and great question. There's already an open issue for this in the repo (#31) and the fix is in dev. Next RC will have it. The Android scanner will use the bundled ML Kit model directly, with no Google Play Services calls at runtime. Same scanning engine.

Thank you so much! I appreciate it!