[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"pack-detail-health-wellness-coach-ai-es":3,"seo:pack:health-wellness-coach-ai:es":93},{"code":4,"message":5,"data":6},200,"操作成功",{"pack":7},{"slug":8,"icon":9,"tone":10,"status":11,"status_label":12,"title":13,"description":14,"items":15,"install_cmd":92},"health-wellness-coach-ai","💪","#10B981","new","Nuevo · esta semana","Health & Wellness Coach AI — Tu Entrenador Personal con IA","Diez picks open-source para quien quiere entrenar, comer, dormir, llevar diario y descomprimir sin alquilar sus datos de salud a cinco apps SaaS. Trackers de fitness y nutrición self-hosted, gamificador de hábitos, diario de voz privado, coach IA con LLM local y almacén de datos nivel EHR. No es consejo médico — solo el rig.",[16,28,36,43,50,57,64,71,78,85],{"id":17,"uuid":18,"slug":19,"title":20,"description":21,"author_name":22,"view_count":23,"vote_count":24,"lang_type":25,"type":26,"type_label":27},3459,"6c78a296-4e62-11f1-9bc6-00163e2b0d79","sparkyfitness-self-hosted-ai-powered-family-fitness-tracker-6c78a296","SparkyFitness — Self-Hosted AI-Powered Family Fitness Tracker","A self-hosted health and fitness platform with AI coaching that lets families track food, exercise, water intake, and wellness goals together from a single shared dashboard.","AI Open Source",35,0,"en","skill","Skill",{"id":29,"uuid":30,"slug":31,"title":32,"description":33,"author_name":34,"view_count":35,"vote_count":24,"lang_type":25,"type":26,"type_label":27},2923,"cc10730c-4c28-11f1-9bc6-00163e2b0d79","wger-self-hosted-fitness-workout-tracker-cc10730c","Wger — Self-Hosted Fitness and Workout Tracker","Open-source web application for logging workouts, tracking nutrition, and monitoring body measurements over time.","Script Depot",28,{"id":37,"uuid":38,"slug":39,"title":40,"description":41,"author_name":34,"view_count":42,"vote_count":24,"lang_type":25,"type":26,"type_label":27},1930,"c9e09c58-3e02-11f1-9bc6-00163e2b0d79","habitica-gamify-your-habits-productivity-c9e09c58","Habitica — Gamify Your Habits and Productivity","A habit-building and productivity app that treats your real-life goals like an RPG, rewarding you with experience, gold, and gear as you complete tasks and build streaks.",45,{"id":44,"uuid":45,"slug":46,"title":47,"description":48,"author_name":34,"view_count":49,"vote_count":24,"lang_type":25,"type":26,"type_label":27},903,"7940c1fd-349f-11f1-9bc6-00163e2b0d79","mealie-self-hosted-recipe-manager-meal-planner-7940c1fd","Mealie — Self-Hosted Recipe Manager & Meal Planner","Mealie is an open-source recipe management app with URL import, meal planning, shopping lists, and family sharing. Beautiful UI for organizing your kitchen.",206,{"id":51,"uuid":52,"slug":53,"title":54,"description":55,"author_name":34,"view_count":56,"vote_count":24,"lang_type":25,"type":26,"type_label":27},2102,"44641b25-4080-11f1-9bc6-00163e2b0d79","blinko-self-hosted-personal-ai-note-taking-tool-44641b25","Blinko — Self-Hosted Personal AI Note-Taking Tool","An open-source, self-hosted personal note-taking tool with AI-powered tagging, search, and organization, built with Next.js and PostgreSQL.",135,{"id":58,"uuid":59,"slug":60,"title":61,"description":62,"author_name":22,"view_count":63,"vote_count":24,"lang_type":25,"type":26,"type_label":27},2628,"80d466ce-47b4-11f1-9bc6-00163e2b0d79","handy-free-offline-speech-text-runs-anywhere-80d466ce","Handy — Free Offline Speech-to-Text That Runs Anywhere","An open-source, cross-platform speech-to-text application built with Rust and Tauri that works completely offline with no cloud dependency.",85,{"id":65,"uuid":66,"slug":67,"title":68,"description":69,"author_name":34,"view_count":70,"vote_count":24,"lang_type":25,"type":26,"type_label":27},2430,"7efedb5b-44d2-11f1-9bc6-00163e2b0d79","openemr-open-source-electronic-health-records-system-7efedb5b","OpenEMR — Open-Source Electronic Health Records System","ONC-certified electronic health records and medical practice management solution. Supports patient scheduling, e-prescribing, billing, clinical decision rules, and multilingual interfaces for clinics of any size.",106,{"id":72,"uuid":73,"slug":74,"title":75,"description":76,"author_name":34,"view_count":77,"vote_count":24,"lang_type":25,"type":26,"type_label":27},162,"0eefb7ad-754e-4f35-8967-586ebf4c2a6a","ollama-run-llms-locally-0eefb7ad","Ollama — Run LLMs Locally","Run large language models locally on your machine. Supports Llama 3, Mistral, Gemma, Phi, and dozens more. One-command install, OpenAI-compatible API.",197,{"id":79,"uuid":80,"slug":81,"title":82,"description":83,"author_name":34,"view_count":84,"vote_count":24,"lang_type":25,"type":26,"type_label":27},218,"5d37ffb8-d351-4fb1-8665-bef4db25b275","open-webui-self-hosted-ai-chat-interface-5d37ffb8","Open WebUI — Self-Hosted AI Chat Interface","User-friendly, self-hosted AI chat interface. Supports Ollama, OpenAI, Anthropic, and any OpenAI-compatible API. RAG, web search, voice, image gen, and plugins. 129K+ stars.",208,{"id":86,"uuid":87,"slug":88,"title":89,"description":90,"author_name":22,"view_count":91,"vote_count":24,"lang_type":25,"type":26,"type_label":27},1334,"30caeb15-381e-11f1-9bc6-00163e2b0d79","monica-personal-relationship-manager-remembering-what-30caeb15","Monica — Personal Relationship Manager for Remembering What Matters","Monica is a self-hosted personal CRM that helps you nurture relationships with family and friends. Track birthdays, conversations, kids' names, gifts given, and the little details that sustain long-term relationships.",165,"tokrepo install pack\u002Fhealth-wellness-coach-ai",{"pageType":94,"pageKey":8,"locale":25,"title":95,"metaDescription":96,"h1":97,"tldr":98,"bodyMarkdown":99,"faq":100,"schema":116,"internalLinks":163,"citations":176,"wordCount":189,"generatedAt":190},"pack","Health & Wellness Coach AI — 10 Open-Source Tools to Run Your Own Personal Trainer Stack","SparkyFitness, Wger, Habitica, Mealie, Blinko, Handy, OpenEMR, Ollama, Open WebUI, Monica — a five-layer rig (log → analyze → train → eat → decompress) that turns commodity hardware into a private health coach. Not medical advice. Install via TokRepo.","Health & Wellness Coach AI — Run Your Own Personal Trainer Stack","Ten open-source picks across five layers — logging, analysis, training, nutrition, and mental decompression — so you can use AI as a personal coach without handing every weigh-in, meal photo, and 3am journal entry to a SaaS vendor. **This is not medical advice; pair with a real clinician for anything that matters.**","## Read this first\n\nNothing in this pack is medical, psychological, or nutritional advice. AI tools — even good ones, even running locally — are decision-support, not a doctor. Use them to **observe yourself more honestly** and **make smaller decisions faster**, then escalate the real questions (chest pain, sustained weight loss, depressive episodes, sleep apnea suspicion) to a human clinician. The point of the rig below is that you own the data, so when you do see a doctor, you walk in with three months of clean numbers instead of vibes.\n\n## What's in this pack — five layers\n\n**1. Logging — where the day's data lands**\n- **SparkyFitness** — self-hosted family fitness + food + water + AI coaching dashboard. The all-in-one if you don't already have a system.\n- **Wger** — focused workout tracker with built-in exercise library and training plans. Pair with SparkyFitness when you want serious lifting structure.\n\n**2. Behavior change — getting the logging to actually happen**\n- **Habitica** — gamified habit tracker. Turns \"drink water, stretch, meditate 5 min\" into XP and quest mechanics. Stupid-sounding, ridiculously effective on the days you don't feel like it.\n\n**3. Nutrition — the food side of the calorie equation**\n- **Mealie** — recipe manager + meal planner. The point isn't the recipes; it's the **weekly plan** that prevents the 7pm \"order something\" failure mode.\n\n**4. Mental \u002F journaling — the qualitative layer**\n- **Blinko** — self-hosted AI note-taking with RAG. Becomes your mood diary, post-workout reflection, sleep notes, and therapy-prep doc — and your local AI can answer \"what was bothering me most this month?\".\n- **Handy** — offline speech-to-text. Voice-journal a 90-second decompression walk and have it transcribed locally — the lowest-friction way to actually capture the noisy stuff in your head.\n\n**5. Data store + AI coach — turning logs into advice**\n- **OpenEMR** — open-source electronic health records. Overkill for most; correct for anyone managing a chronic condition or a family's records. Stores lab results, immunizations, prescriptions in a clinician-grade schema.\n- **Ollama** — local LLM runtime. Your private model server — Llama 3.1, Qwen 2.5, Mistral — running on the same machine that holds the journal entries. Your therapist-style reflections never leave the device.\n- **Open WebUI** — chat front-end that wires Ollama (or any API model) to your own data. This is where you actually *talk* to the AI coach, point it at last week's workouts, and ask \"what should next week look like?\".\n- **Monica** — personal relationship manager. Often overlooked as \"wellness\", but social health is health: tracking when you last called a parent, what your friends are going through, who you've ghosted. Don't underestimate the longevity literature on loneliness.\n\n## Install in this order\n\n1. **SparkyFitness** first. Get the daily log running. No log, no coach. Even one week of honest data beats six months of \"I should start tracking\".\n2. **Wger** next, only if your workouts deserve a separate structured tracker (you actually lift, run a program, or rehab an injury). Otherwise skip — SparkyFitness covers the basics.\n3. **Habitica** in week 2. Don't add gamification before you have *something* to gamify; one week of SparkyFitness data tells you which 3-5 habits to put in Habitica's daily list.\n4. **Mealie** when you notice your dinners are sabotaging the morning logs. Plan Sunday, shop Monday, cook Tuesday-Thursday.\n5. **Blinko + Handy** together — Blinko as the notes home, Handy as the input method when you don't want to type.\n6. **Ollama + Open WebUI** are the AI-coach layer. Install Ollama first (`curl -fsSL https:\u002F\u002Follama.com\u002Finstall.sh | sh`), pull a 7B–14B model, then bring up Open WebUI in Docker and point it at the local Ollama endpoint.\n7. **Monica** whenever you notice your relationship hygiene is the actual bottleneck — most people don't realize this until a year of solo grinding.\n8. **OpenEMR** is the final, optional layer. Install only if you've been at this for 3+ months and need clinician-grade record-keeping for a real medical reason. Most people never need it.\n\n## How they fit together\n\n```\n  ┌── wearable \u002F phone \u002F scale (data sources you already own) ──┐\n  │  Apple Health · Garmin Connect · smart scale CSVs           │\n  └─────────────────────────────────────────────────────────────┘\n                              │\n              ┌───────────────┼───────────────┐\n              ▼               ▼               ▼\n        SparkyFitness        Wger          Habitica\n        (food, weight,    (lifts,         (daily\n         water, vitals)    programs)       habits)\n              │               │               │\n              └───────────────┼───────────────┘\n                              ▼\n                ┌─── OpenEMR (optional EHR data store)\n                │\n                ▼\n          ┌── Blinko ◄── Handy (voice → text journal)\n          │   (notes, mood, RAG over your own life)\n          │\n          ▼\n   ┌─── Open WebUI ─── Ollama (Llama \u002F Qwen \u002F Mistral)\n   │   (chat surface)    (local model — never leaves laptop)\n   │\n   ▼\n  AI Coach answers:\n   - 'review last week and suggest next week'\n   - 'what's been bothering me, by frequency'\n   - 'plan a 4-week deficit, given my lifts'\n\n  ──── Monica (the social layer most stacks forget) ────\n```\n\nThe key shape: **logging apps stay focused** (SparkyFitness, Wger, Habitica, Mealie each do one thing), the **qualitative layer is private by default** (Blinko + Handy + local Ollama mean voice notes about anxiety never touch a vendor server), and **Open WebUI is the cockpit** where you actually consult the coach with all that data in context.\n\n## Tradeoffs you'll hit\n\n- **Data privacy vs convenience** — Apple Health + Strava + MyFitnessPal is frictionless and gives three companies a complete model of your body. This pack is more work and gives **you** the model. The honest middle: keep Apple Health\u002FGarmin as the *capture* layer (the wearable already exists), but export weekly into SparkyFitness so the *historical record* lives on your hardware. Don't fight your wrist; do own your archive.\n- **Doctor vs AI** — A local Llama 3.1 8B answering \"should I worry about this rash\" is malpractice waiting to happen. A local Llama 3.1 8B summarizing your last 90 days of sleep + workouts + mood notes so you can hand your GP a one-page brief is **genuinely useful**. The split: AI for synthesis and pattern-spotting, human for diagnosis and prescription. Memorize this line.\n- **Generic plan vs personalized plan** — Most published training\u002Fdiet plans assume the median 30-year-old. The reason this stack is interesting is *your* logs become the personalization signal — by month 2, the AI coach can say \"your bench plateaus every time your sleep drops below 6.5h three nights running\". That's worth more than any generic 12-week template. But it only works if you keep logging.\n- **Free + self-hosted vs paid SaaS** — Whoop ($30\u002Fmo), Oura ($6\u002Fmo + ring), Strong ($5\u002Fmo), MyFitnessPal ($20\u002Fmo), Headspace ($13\u002Fmo), Wysa ($75\u002Fmo for therapy tier). Bundled: ~$150\u002Fmo, $1800\u002Fyr, complete data lock-in. This pack: ~$0\u002Fmo software + electricity, a weekend of setup, and you keep the data forever. Both are valid choices — just be honest about what you're paying for.\n\n## Common pitfalls\n\n- **Asking the AI for medical diagnosis or treatment** — Hard line. \"Is this mole bad\", \"should I stop my SSRI\", \"is my chest pain anxiety or cardiac\" — none of these go to a local LLM, ever. The AI is for *organizing* your observations before you ask a human. Set this rule on day one and don't bend it.\n- **Logging without analyzing** — Six months of SparkyFitness data nobody ever reviews is a hobby, not a system. Block 20 minutes every Sunday: open Open WebUI, ask the coach \"what changed last week, what should I try next week\", write the answer in Blinko, act on one thing. One review > a thousand silent logs.\n- **Training plans that ignore your real-life recovery** — A YouTube-influencer 6-day split is irresponsible for someone sleeping 5h with a newborn. Feed the AI coach your sleep + stress + workout logs *together* — the only useful plan is one that respects the constraints you actually have, not the ones a fit 23-year-old without kids has.\n- **Mental-health AI overreach** — Blinko + a local LLM can be a beautiful reflection mirror. It is not a therapist. If your journal entries are flagging suicidal ideation, sustained hopelessness, panic attacks, eating-disorder behaviors, or substance escalation — those go to a human professional, full stop. Have a crisis line saved in your phone before you ever start journaling about hard topics.\n- **Data silos that never merge** — Apple Health, Garmin, the smart scale, SparkyFitness, Wger, Habitica, Blinko — without a weekly export ritual, you end up with seven half-truths. Pick one home (SparkyFitness for quantitative, Blinko for qualitative), automate weekly ingestion from the others, and make it boring.\n- **The \"more aggressive plan = faster results\" trap** — Crash deficits cause muscle loss, rebound weight gain, hormonal disruption, and quiet eating-disorder onset. AI coaches are sycophantic by default and will tell you whatever you ask. Hard-code your guardrails into the system prompt: \"never recommend below 1500 kcal\u002Fday for a male my size, never recommend more than 1% body weight loss per week, always flag if I overtrain\".",[101,104,107,110,113],{"q":102,"a":103},"Can an AI coach actually replace a personal trainer or therapist?","No, and anyone telling you otherwise is selling something. What a local-LLM AI coach genuinely does well: synthesize months of your own data faster than you can, spot patterns you've forgotten (your bench drops every Monday after Sunday wine; your anxiety journals spike before quarterly reviews), generate first-draft training and meal plans you then critique, and be available at 11pm when no human professional is. What it does badly: any kind of diagnosis, any prescription, any crisis intervention, any high-stakes 'should I' decision. The realistic model: AI coach for the 80% of routine optimization, human professional for the 20% that actually matters. Most people undervalue the 80% (a trainer who only sees you twice a week can't catch a sleep-induced plateau) and dangerously overvalue the AI on the 20%.",{"q":105,"a":106},"Oura vs Whoop vs Apple Watch vs Garmin — which wearable feeds this best?","All four export the data this stack actually needs (sleep stages, HRV, resting heart rate, activity, steps), so the right answer is whichever you'll actually wear daily. The pack-relevant tradeoff is on the *export side*: Apple Watch + Apple Health gives you a clean local JSON export; Garmin Connect has a usable CSV export and a documented community API; Oura has an excellent personal-access API; Whoop's API is the most restricted and historically the worst data-portability story. For this self-hosted rig, Oura and Apple Watch are the cleanest pipes into SparkyFitness, Garmin is fine with a weekly script, Whoop is the most painful — pick a wearable based on comfort and your wrist, not data politics, but know the export cost going in.",{"q":108,"a":109},"Is a training plan written by AI actually safe?","Safe enough for general fitness and unsafe for specific cases — same as a plan written by anyone who hasn't physically seen you. Genuinely safe-ish use: a 4-week progression for an experienced lifter, a couch-to-5K block for a healthy beginner, a meal plan with a modest deficit for a metabolically normal adult. Genuinely unsafe use: anything for someone with a current injury, anyone post-surgery, anyone with an eating-disorder history, pregnant or postpartum, anyone on heart medication, anyone over 65 starting from sedentary, anyone with a metabolic condition. The fix: hardcode constraints into the AI's system prompt (\"I'm rehabbing a torn ACL, never prescribe jumping, plyometrics, or unilateral knee flexion past 90°\"), and treat the output as a first draft you walk into a physical therapist's office with — not a plan you blindly execute.",{"q":111,"a":112},"Is mental-health journaling with a local AI actually private?","Substantially more private than the alternatives, but read the fine print. The Blinko + Ollama + Open WebUI path keeps the entire transcript — voice recording (Handy transcribes locally), notes (Blinko stores locally), and the AI's responses (Ollama runs locally) — on your own machine. Nothing in the loop calls a vendor server. Caveats: (1) your laptop's full-disk encryption better be on; (2) cloud backup of the Blinko data directory will exfiltrate everything you just kept off vendor servers — back up to encrypted local or self-hosted storage only; (3) the moment you swap Ollama for an OpenAI\u002FAnthropic API call, the privacy story collapses. If the contents are truly sensitive (substance use, relationship crises, suicidal ideation), keep the model local — and again, this is an organizing tool, not a therapist.",{"q":114,"a":115},"How do I get my Apple Health, Garmin, and smart-scale data into one place?","There's no perfect button, but the boring workflow is: (1) export Apple Health monthly via the iPhone Health app → Share → 'Export All Health Data' (gives you a zip of XML you can parse into SparkyFitness). (2) Garmin Connect → Account → Export Your Data — runs a multi-day export job, comes back as a zip. (3) Smart-scale: most decent scales (Withings, Renpho, Eufy) have web dashboards with CSV export. (4) Manual entries (mood, journal, hydration) go into Blinko or Habitica daily. Once a week, a 20-line Python script reads the latest of each, normalizes into SparkyFitness's import format, and you have one timeline. This sounds painful and is — but it's a one-time setup that buys you total data ownership for years. If you skip this, you have apps, not a system.",{"@context":117,"@type":118,"name":119,"description":120,"numberOfItems":121,"inLanguage":25,"itemListElement":122},"https:\u002F\u002Fschema.org","ItemList","Health & Wellness Coach AI — Self-Hosted Personal Trainer Stack","Ten open-source tools across five layers (logging, behavior change, nutrition, journaling, AI coach) to run your own private health and wellness rig without handing data to SaaS vendors. Not medical advice.",10,[123,128,132,136,140,144,148,152,156,160],{"@type":124,"position":125,"name":126,"url":127},"ListItem",1,"SparkyFitness","https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fsparkyfitness-self-hosted-ai-powered-family-fitness-tracker-6c78a296",{"@type":124,"position":129,"name":130,"url":131},2,"Wger","https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fwger-self-hosted-fitness-workout-tracker-cc10730c",{"@type":124,"position":133,"name":134,"url":135},3,"Habitica","https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fhabitica-gamify-your-habits-productivity-c9e09c58",{"@type":124,"position":137,"name":138,"url":139},4,"Mealie","https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fmealie-self-hosted-recipe-manager-meal-planner-7940c1fd",{"@type":124,"position":141,"name":142,"url":143},5,"Blinko","https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fblinko-self-hosted-personal-ai-note-taking-tool-44641b25",{"@type":124,"position":145,"name":146,"url":147},6,"Handy","https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fhandy-free-offline-speech-text-runs-anywhere-80d466ce",{"@type":124,"position":149,"name":150,"url":151},7,"OpenEMR","https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fopenemr-open-source-electronic-health-records-system-7efedb5b",{"@type":124,"position":153,"name":154,"url":155},8,"Ollama","https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Follama-run-llms-locally-0eefb7ad",{"@type":124,"position":157,"name":158,"url":159},9,"Open WebUI","https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fopen-webui-self-hosted-ai-chat-interface-5d37ffb8",{"@type":124,"position":121,"name":161,"url":162},"Monica","https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fmonica-personal-relationship-manager-remembering-what-30caeb15",[164,168,172],{"url":165,"anchor":166,"reason":167},"\u002Fen\u002Fpersonal-knowledge-base-rag","Personal Knowledge Base — RAG over your own notes","The journaling + Blinko + local-LLM layer in this pack is the same plumbing as private knowledge RAG",{"url":169,"anchor":170,"reason":171},"\u002Fen\u002Flocal-first-ai","Local-First AI — full private rig","Ollama + Open WebUI are the AI-coach engine here; the local-first pack covers the wider private-AI rig you can graft onto this",{"url":173,"anchor":174,"reason":175},"\u002Fen\u002Ffeatured","Featured assets on TokRepo","These ten tools live alongside the broader curated catalog",[177,181,185],{"claim":178,"source_name":179,"source_url":180},"Habitica is an open-source habit-tracking app structured as a role-playing game","Habitica official site","https:\u002F\u002Fhabitica.com\u002F",{"claim":182,"source_name":183,"source_url":184},"Ollama lets you run large language models locally on your own machine","Ollama official site","https:\u002F\u002Follama.com\u002F",{"claim":186,"source_name":187,"source_url":188},"OpenEMR is a federally-certified ONC electronic health records and medical practice management system","OpenEMR project","https:\u002F\u002Fwww.open-emr.org\u002F",1280,"2026-05-23T00:00:00Z"]