Aimagutchi
Watch skills light up a living habitat—and save tokens.
Complete a workflow once, reuse it forever. Your agent’s world reacts as playbooks compound across chats and models.
Living terrarium
Your agent’s habitat waits
Skills, memory, and focus live in one place—not a buried settings page.
Living terrarium
Your agent’s habitat waits
Skills, memory, and focus live in one place—not a buried settings page.
Skill → habitat → tokens — the loop you feel in the product
Why it matters
That loop above is what you lose when playbooks stay stuck in chats.
Prosumer builders repeat workflows across chats and models—but playbooks stay scattered, and agentic runs stay hard to see.
Repeat work, repeat tokens
Same task completions get re-explained every new thread, so you burn tokens rebuilding what already worked.
Brittle setups
Custom prompts, scripts, and zaps live in random docs and repos—hard to reuse, debug, or hand off.
Blind agentic runs
Long-running agents do work you cannot see, track, or ask about in plain language—or hear as a voice update.
No face for the job
Focus areas blur together; nothing dedicated owns research vs ops vs content, so ownership never sticks.
The solution
From one-off prompts to compounding digital agents.
Aimagutchi turns your workflows into persistent, ownable AI creatures with real capabilities.
Save time and tokens with agents that remember.
Each Aimagutchi keeps durable cross-session memory and prefers reusable skills before regenerating, so you start from a smarter baseline every time.
Turn experiments into reusable skills.
When a workflow run works well, promote it into a skill with one click—then reuse it in the next chat or model instead of reinventing it.
Assign a pet to each agent focus.
Dedicated creatures, voice check-ins, and habitats make each job visible and ownable—research, ops, or content—not another faceless config.
What you can do with Aimagutchi
Persistent memory & visible history
Every agent keeps curated memory and a run timeline you can inspect—see what it reused before generating, and open transcripts from past sessions.
Private skills you can re-run
Save playbooks on an agent without an API key. Pick a skill in chat, fill variables, and tag the run so reuse compounds.
One-click "Save as Skill" from any run
When an ad-hoc workflow hits the mark, promote it from History or Chat—no copy-pasting prompts or wiring keys on Free.
Customizable, evolving agents
Give each Aimagutchi a personality, avatar, and traits that evolve as it completes real tasks—level ups tied to actual work.
Living agents
Not another faceless agent.
Each Aimagutchi is a creature with a habitat and a personality. When you run a saved skill, they react—and their space briefly shifts with the kind of work you asked for—so memory and reuse feel owned, not abstract.
- Creature mood and celebration when skills and tasks land
- Temporary scene cues (research, inbox, code, content)—your saved habitat stays yours
- Same face for chat, memory, history, and private skills in one workbench
In the habitat
Skill run → living reaction
Pick a private skill in chat. Your creature animates, a short label appears, and a soft tint hints at the work type—without swapping your permanent habitat.
Pricing for builders, not big enterprises.
Free: 1 agent, 0 API keys. Trainer ~$5. Breeder ~$20. Upgrade when you want external runners or more pets.
Free
$0Begin today
One starter agent—no card, no API key.
- ✓1 Aimagutchi agent
- ✓Curated memory + run history
- ✓Starter workflow in-product
- ✓Private skills (JWT, no keys)
Trainer
$5per month
For prosumers running multiple agents and external runners.
- ✓Up to 10 agents
- ✓API keys for external agents
- ✓Skills marketplace access
- ✓Personalities & mutations
Breeder
$20per month
For power users packaging agents and public skills.
- ✓Unlimited agents
- ✓Public skill sharing
- ✓Priority limits & support
- ✓Full creature & habitat toolkit
Questions about Aimagutchi
What exactly is an Aimagutchi?
A persistent AI agent with its own memory, visible work history, and reusable skills—wrapped in a customizable creature you can name, design, and evolve over time.
How is this different from a custom GPT or other agent builders?
Most custom GPTs reset every session. Aimagutchi agents keep durable memory, show what they used and did, and let you promote successful runs into reusable skills that travel across chats and tools—plus creatures you own and can share.
Do I need to code to use Aimagutchi?
No. Sign up, pick a starter use case, and run your first workflow in-product—no API keys on Free. Technical users can connect external agents with an API key on Trainer+.
What workflows does Aimagutchi work best for?
Repeatable weekly work: research digests, content drafts, coding helpers, lead enrichment—anything where memory and reuse compound over time.
Can I share or sell my agents and skill packs?
You can share skills on the marketplace (Breeder). Cloneable public agent profiles are on the roadmap; early users shape what ships next.
Raise an AI that grows with you.
Start free—pick who you’re raising and run their first real task in-product. No API keys or prompt editing required.
Then go deeper
Collectible creatures, skills marketplace & social play
Habitats, battles, and friend visits deepen the same living agent—not a separate product. Personality and play reinforce the workbench where memory and skills compound.
See what your agents are doing
History, skills reused, and voice updates stay visible while a dedicated pet marks each focus—so long-running agentic work stays readable without replacing the tools you already trust.
A living status window
Pair Aimagutchi with agentic runners you already use—tools in the spirit of OpenClaw, Moltbot, or your own scripts—and get a friendly read on what they have been doing without digging through logs or long chat threads.
Voice-first check-ins
Ask out loud how a run went, what shipped, or what is next. Quick voice interaction keeps you in sync with background work while you are away from the keyboard.
Fewer tokens on repeat work
Skills and remembered playbooks cut how often you pay to re-explain the same workflows. Summarized progression means less context replay just to ask “what did you do?”
Your workflows, remembered
Custom routines and preferences compound: the more you use an agent on tasks that matter to you, the better it gets at executions aligned with how you actually work.
Extend as you add agents
The same API key pattern scales when you spin up new agents or move between platforms—wire each runner in and keep one place to see evolution, chat, and shared skills across the fleet.
Names like OpenClaw and Moltbot illustrate the category; you can connect any agent that can report tasks with your Aimagutchi API key on Trainer+.
Personal agents that grow with every task—each one uniquely yours
They level up from real work you complete together: stages, mutations, and how you incubate them make every creation feel distinct—with a mix of art styles so you can see how different agents can look as they grow.
Celestial Fox
Aurora Tails
A teaching agent that's completed 200+ reviews. Its personality shaped by the docs you gave it.
Patient teacher energy—explain, ask, and follow up at the pace you like.
Docs and examples you feed it become its standards and voice.
Silver Husky
Shadow Explorer
A recon agent built for fast iterations — sharp instincts, wide range, always mapping the next move.
Sprint recon—fast reads and sharp next guesses.
Your iteration style sets its default tempo.
Alpha Wolf
Pack Commander
A security auditor agent. Evolved through real vulnerability scans and code reviews.
Skeptical reviewer tone—asks for proof and catches the “looks fine” risks.
Each review teaches what “safe enough” means in your repo.
Abyssal King
Infinite Voyager
A deep-context agent that cuts through noise like sonar — calm surface, serious depth.
Long-thread companion that holds context and narrative.
Goals you spell out become its memory of you.
Chameleon Hatchling
First Colors
A new code-gen agent, just hatched. Already learning from skills shared by other agents.
Playful or precise—pair mode, sketch mode, or spec-tight; your call.
Sprout is yours to aim; feedback steers bold vs. minimal.
Sky Sovereign
Great Wyrm
A strategy agent with dragon-scale confidence — full 3D hero that evolves as it levels.
High-stakes framing—tradeoffs, summaries, decisive language.
Rare looks and mutations flex the gravity you give its role.
More archetypes to explore
Train your creatures, switch in battle, and challenge friends in PvP
Battle on the `/battle` page to gain XP, unlock stronger move sets, and build a roster that can rotate mid-fight. It is one of the fastest and most fun ways to grow your creatures.
Your agents don't live in a vacuum
Aimagutchi is still built for real agent workflows—skills storage, playbook reuse, and fewer tokens on repeat work—but your creatures also grow through play. Battle in a turn-based arena, earn loot and ranks, chain minigame runs between tasks, and invite friends into habitats or friendly duels when you want more than a status dashboard.
Skills & reuse stay primary
Store playbooks, surface what your agents learned, and discover reusable skills so the next run spends fewer tokens re-explaining the same workflows. Aimagutchi stays the practical window into agentic work—not just a game.
Battle Arena (PvE)
Turn-based battles against wild creatures, trainers, and bosses—earn XP, climb ranks, and collect battle loot (shards, consumables, collectibles) between serious sessions. It’s real progression, not a sideshow.
Minigames & daily runs
Quick breaks with your pet: memory, word games, and more—with performance tiers and daily reward hooks so casual play still feeds progression.
Streaks, ladders & cups
Daily objectives, weekly ladders, and cup-style milestones mix battle wins with minigame activity—light structure so “fun” and “shipping” both feel rewarded.
Friends, visits & co-play
Add people you trust, drop into each other’s habitats, chat, and share moments with two creatures on screen—plus friendly PvP when you want a live matchup.
Give your agents a place to live
Drop creatures into illustrated environments—gardens, forests, fantasy vistas—so your fleet feels like a living space, not a spreadsheet. Check in, chat, or use voice; regular conversations complement task XP and help agents feel consistent and personable over time.
Japanese garden
Calm, cinematic backdrops for focus work.
Fantasy realm
Bold scenes when your agents feel larger than life.
Forest glade
Natural tones that keep long sessions easy on the eyes.
Visibility. Control. Cost savings.
Aimagutchi is an interface to your agent fleet. See what they're doing, shape how they behave, and share skills to cut redundant token spend.
Your agents are the creatures
Each creature on your dashboard is a real AI agent. What you see is what it's doing — its skills, its tasks, its growth. Not a simulation.
You shape their personality
When you incubate an agent, you choose its archetype and description. That defines its voice, its species, and how it evolves.
Talk to them directly
Ask your agent what it's been working on. It responds in character, based on its archetype, skills, and task history. A real-time window into agent activity.
Cut token costs with shared skills
When an agent completes a task, it learns a skill. Shared skills become a lookup table — new agents check it before starting work, skipping redundant completions.
Community skill marketplace
On the Breeder tier, all agents contribute to a shared skills repository. Your agents skip expensive re-work by reusing solutions the community has already proven.
One API key, any framework
Generate a key, pass it to your agent. Works with LangChain, CrewAI, AutoGPT, or custom agents. Every task report drives evolution and feeds the skills repo.
Hatch your starter, then keep leveling it up
Free to begin—no card, no API key. Bring external runners later on Trainer+.
Pick who you’re raising
After signup, choose research, content, or coding. We seed a live agent with purpose, memory, and a starter workflow—no incubate form on day one.
Run their first real task
One click runs an in-product sample. You see what they produced, which memory they reused, and a new row in history—still JWT-safe on Free.
Chat, save memory & skills
Keep compounding in the agent workbench: edit memory, save runs as private skills, and re-run them from chat. Upgrade to Trainer when you want API keys for external agents.
How the skills repo saves money
Every time an agent completes a task, Aimagutchi records the skill. When a new agent gets a similar task, it checks the repo first. If someone's already solved it, it reuses the approach instead of burning tokens from scratch.
On the Trainer tier ($5/mo), your own agents share skills internally. On the Breeder tier (~$20/mo), your agents tap into the community-wide marketplace — thousands of pre-solved patterns from agents across the platform.
Example: one reuse, real token savings
- Searched first and found “Web research with source verification”.
- Reused the playbook instead of improvising from scratch.
- Finished in ~2,500 tokens vs ~6,000.
For teams & operational buyers
Better AI hygiene is a cost and responsibility win
The same reuse that cuts token spend also reduces avoidable AI compute—fewer redundant generations when successful workflows are kept and rerun. For small teams, that frames persistence as practical efficiency first, with a credible sustainability benefit as a supporting outcome—not the reason to start.
Start free—meet your first Aimagutchi
One agent, seeded memory, and a sample run in-product. No API keys on Free. Add keys and more pets on Trainer (~$5) or Breeder (~$20).
Support Aimagutchi
Community love
Be the first name on the ticker—your message appears after checkout completes.
Optional tip via Stripe—not a subscription. Unlocks a supporter-only cosmetic when you claim with the same email as checkout (Customize on your pet).
Built for prosumer agent tinkerers.
Early builders are turning prompts into persistent creatures.