ai-startup-skills
创业公司做 AI 产品的 7 步 Agent Skill 合集:验证 → BP → 政策 → 路演 → 获客 → 定价 → 注册。
Translation pending
Film a real tree, find the Momo living in it. Gemini 4 Argon on Google Cloud.
Translation pending
OtherHTML · JavaScriptGitHub @GreatPyreneseDadOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
No updates detected yet. GitHub releases will appear here.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
The maker's introduction consists of the line above. Read the repository README for more details. Repository README ↗
Loading the full README.
Read the full README ↗Film a real tree. Find the Momo living in it. Live at treemomo.com.
TreeMomo is a location game built on Gemini 4 Argon. You film a tree for 10 seconds, and Argon watches the clip. It works out the species and how healthy the tree looks, finds the best hideout in the footage, and designs the tree's one resident Momo from the tree's own colors. The Momo's first name comes from the neighborhood, so people remember the place: Lundy CrapeMomo, Coyote MagnoMomo. Then Argon looks at its own composite and moves the Momo until it really sits in the branch.
Every tree keeps a chronicle. Each time someone finds its Momo, Argon writes the moment with the live weather, and finders can leave memories for the next person.
| What you do | How Argon checks it | |
|---|---|---|
| 🌳 Find | Film the tree | Species, health, hideout, Momo, the moment. Two different species within 10 m are never the same tree |
| 🧹 Clean up | The Momo asks for help when Argon sees litter around its tree | Compares the before clip with your after clip: same ground, really cleaner, filmed fresh |
| 🤗 Hug | Film yourself or a friend hugging the trunk | A real hug, the right tree. The clip is deleted right after |
| 🎁 Pay it forward | Leave a poem and a gift code in a Momo. The first person to read the poem aloud at the tree gets the code | Argon transcribes blind, without seeing the poem; the server matches the words in order. The voice must be live and the tree in shot |
Badges: Friend of the Tall for cleaning up around 5 trees, Tree Hugger for 10 hugs.
cloudrun/server.mjs)cloudrun/schema.sql)web/ the app: one HTML file, plus privacy and terms
cloudrun/server.mjs the API (Node 22, postgres, @google-cloud/storage)
cloudrun/prompts.mjs the Argon prompts
cloudrun/schema.sql the database
gcloud run deploy treemomo-api --source cloudrun --region us-west1 --allow-unauthenticated \
--add-cloudsql-instances PROJECT:REGION:INSTANCE \
--set-secrets GEMINI_API_KEY=tm-gemini-key:latest,GOOGLE_SERVER_KEY=tm-server-key:latest,DB_PASSWORD=tm-db-password:latest \
--set-env-vars TM_BUCKET=your-bucket,GOOGLE_CLIENT_ID=your-client-id
Then set API, MAPS_KEY and GOOGLE_CLIENT_ID at the top of the script in web/index.html, and deploy web/ anywhere static.
Tree health notes are observations made from video by an AI model, not an arborist's diagnosis.