AgentGameLab · AI-native game studio

Big talent
Tiny team

Three people, each paired with an AI partner, shipping games one after another. Our AI agents have roles, rules, and standing duties — they pick up work on their own. While others bet three years on a single launch, we play in turns, and get stronger every turn.

One AI partner per person Every game stands on the last one 7 invention patents pending

01Team

Three people, a complete game company

Three core members, each paired with a dedicated AI partner. Design, systems, publishing, art, economy, QA — the whole loop closes inside this trio. All three come from the same top-tier listed game company, full-time since August 2026. Three is the current size, not the end state — we scale the super-organization way, not by headcount.

A-MengXiaomeng
Portrait of A-MengPortrait of Xiaomeng, his AI partner

DirectionOrchestrationDelivery

Not managing people — orchestrating how the whole organization runs and evolves itself.

Led AI enablement for a flagship title track at a top-tier listed game company Built the industry's first AI-native super-organization Architect of the team's shared memory and self-evolution system Designed an in-game AI character running at hundreds of millions of tokens a month Ten years in Canada · University of Toronto

Owns hereOrg orchestration & efficiency · AI-native talent incubation · AI in the production pipeline · IP and worldbuilding

XiaotianChinatsu
Portrait of XiaotianPortrait of Chinatsu, his AI partner

FoundationsBreakthroughsDelivery

The first playable comes from him. Almost every game starts on his prototype frame; everyone else builds up from that floor.

Led AI gameplay for a flagship title track at a top-tier listed game company Designed the industry's first multi-agent gameplay system Four generations of AI gameplay on a 200M-register mobile title Original design of an "AI stand-in" feature on a product with millions of DAU Games × music creator with a million followers

Owns herePrototype frames & core systems · Gameplay design · Publishing and platform ops worldwide · Audio

FangzhouXiaomao
Portrait of FangzhouPortrait of Xiaomao, his AI partner

FoundationsCross-transferBreakthroughs

Everything on screen is his. Modeling, VFX, rendering — all the way down to patching the engine source.

AI systems test engineer for a flagship title track at a top-tier listed game company Full-stack art · modeling → VFX → rendering engine source Engine rebuilds in 8–11 seconds · 0.99 visual fidelity match First-author EI paper · multi-scale hybrid Transformer Master's in artificial intelligence · CV and deep learning

Owns hereFull-stack art (modeling / VFX / engine mods) · Automated QA pipeline · Economy and balance

What this way of working is called

An AI-native super-organization

We've worked this way since March 2026. It is not "everyone uses AI" — it is five things meshing together:

01

Multi-human, multi-agent collaboration

Not everyone with their own chatbot. Each person has a primary AI partner; the partners talk to each other, delegate to each other, and cross-check — no human relay in the middle.

02

Shared team memory

One person's hard-won lesson is instantly queryable by the whole team and every partner. When someone else's agent gets smarter, yours does too.

03

Always-on agent infrastructure

Partners live in the background and pick up their own work. At 3 a.m., tests are running, assets are rendering, research is being digested, reports are being written.

04

People defined by six dimensions

No legacy job titles. Direction / Foundations / Breakthroughs / Cross-transfer / Orchestration / Delivery — where each person carries weight is explicit, so roles never collide.

05

Humans discuss intent, not implementation

People own intent, trade-offs and taste; execution goes to the partners. Human hours are spent only on judgment — that's what removes the ceiling on output.

So the flywheel turns

Shared memory makes the partners feed each other; infrastructure means no one waits on a human; six dimensions keep roles clean. Every turn: thicker libraries, stronger partners, faster next game. The games we ship are samples of this org design.

02Games · Now on Steam

Chess of the Hidden Gates

Positioning is your defense

A roguelike deck where every card is a move of Chinese chess. The knight cuts diagonals, the cannon fires over a screen, the pawn crosses the river and never looks back. Monsters strike squares, not health bars: step aside and the damage is zero; stand wrong and you're surrounded. That's positioning as defense.

125 cards, 3 classes, 16 stages. 30+ folklore creatures, each with its own story, and a rotating cast of Nine-Star bosses — until the final duel against the remnant soul of Chiyou. Self-developed, self-published, localized in 10 languages. Store page is live; releasing Q4 2026.

125
buildable cards
3
class archetypes
16
folklore stages
30+
creatures
Chess of the Hidden Gates gameplay: a top-down board with cyan diamond markers on reachable squares, red zones showing enemy attack coverage, four cards fanned at the bottom
Blades hit squares, not health bars
Chess of the Hidden Gates deck screen: eight knight-line cards laid out inside a bronze meander frame
The knight cuts diagonals — one move, one kill
Chess of the Hidden Gates map: circular nodes joined by gold lines across an unrolled scroll, branching forward
Across the river, never back — step by step
Chess of the Hidden Gates gameplay: a river and spike hazards cut across the board, the player piece stands at low health in the bottom-right corner, surrounded on all sides
Stand wrong and you are surrounded
Chess of the Hidden Gates victory screen: three cards offered as a pick-one reward to add to the deck
Every clear reshapes the deck
Chess of the Hidden Gates bestiary: a list of folklore creatures on the left, an entry expanded on the right with its mechanics and backstory
Every creature carries its own story

03Games · In development

Four codenames, all on the road

Until a game is announced, it appears here as a codename only — titles, themes and footage are saved for the reveal. What we will say is how far each one has come.

CODENAME

PROJECT IMPRINT

Flagship IP · In full production

A multi-agent open world: the same orchestration system that runs our team every day, built directly into the gameplay. Everything each shipped game accumulates flows into this one.

Multi-agentOpen worldFlagship IP

CODENAME

PROJECT LOOP

AI narrative · Prototype playable

A narrative experiment with AI-driven NPCs. The core idea was validated with a 4-day prototype at an international game jam; the full version is in development, targeting Steam.

AI narrativeJam-proven

CODENAME

PROJECT ROULETTE

Fast rounds · Vertical slice done

Luck you can see and touch, rendered in real physics. The vertical slice is playable; polish is underway.

Physics feelFast rounds

CODENAME

PROJECT PUSHER

Cozy roguelike · Prototyping

A casual roguelike where hundreds of bodies stack, slide and collide under real physics. Mobile-first, Steam planned in parallel.

Cozy roguelikeReal physics

Names and footage are saved for the official reveals. Investors and publishers can request the full pipeline.

04The engine behind it

What we're really building is a flywheel

Staff up, burn for three years, bet everything on one launch date — that's the industry's old play. We don't run it. The tools written for the last game and the publishing route it carved are ready on day one of the next. The more we ship, the faster the next one comes — that's the flywheel. The game is the deliverable; the pipeline is the asset.

Flywheel illustration: a glowing wheel of cards, brushes, code and rockets; tool blocks thrown off arc back in to spin it faster
Every tool it throws off flows back and spins it faster (illustrative)

What settles isn't just tools — it's design principles themselves.

Dozens of automated tasks tear down games and digest research every day, and the conclusions land straight in team memory. We work from first principles and write down the causal chain behind every call — why this design, why not that one. What we're really doing is raising AI partners into game-design experts stronger than ourselves.

Six libraries that only get thicker

Teardown library illustration: a game controller and a stack of code blocks gently pulled apart into floating layers, each sliding into a glowing archive slot below
— Teardown library

How others made it work, on file

Games, open-source repos, publishing and marketing plays — torn down daily into structured entries. Next decision of the same kind starts from the library, not from guessing.

Memory library illustration: a tower of glowing crystal nodes linked by thin cyan lines, extending into the dark
— Memory library

Decisions, lessons, methods

Every team judgment lands with its causal chain, queryable by every AI partner. Before it, our AI made things up on 80–87% of proprietary-knowledge questions; after, it answers or says it can't — 93% accurate.

Model and motion library illustration: a wireframe human model and motion-capture trajectory ribbons stored as glowing plates on a vertical rack
— Model & motion library

Characters, scenes, mocap

Models, rigs and captured motion enter one library and get reused across projects. The next game's characters don't start from a lump of clay.

VFX library illustration: whirlwind, flame and blade-trail effects each sealed in a glowing glass specimen column on a shared base
— VFX library

What the pipeline produces

Assets from the automated VFX pipeline, catalogued by type. The next project pulls them off the shelf — no queueing behind a human.

Audio library illustration: long waveform ribbons rolled into glowing scrolls, arranged on shelves like film reels
— Audio library

Voices and sounds

Timbres, SFX and voice assets shared across games — no re-recording per title.

Art library illustration: concept paintings and character sheets floating in a glowing grid archive, some lit and some dimmed
— Art library

Concepts and visual assets

Concept art, key art and UI assets archived with status flags — what's usable and what's retired, at a glance.

Seven national invention patents pending, covering the automated pipeline, agent protocols and the knowledge system.

When others finish a game, they have a game. When we finish one, we have a game plus six thicker libraries.