ONE AI Labs — Research · Build · Ship
Research AI.Build What's Next.
ONE AI Labs researches the convergence of blockchain and AI — at the intersection of intelligence and trust, we prove our research as working technical references.
If AI is intelligence,blockchain is trust.
Blockchain brought trust to the digital world; AI adds intelligence on top. ONE AI Labs researches where the two meet — and proves every finding as a working technical reference.
01
1
Core framework
ONE AI Labs
02
9
Tech references
+3 this year
03
4 / 3
Desktop / Web
Wails · Next.js
04
39
Tech stacks
polyglot
Researched as technology.Proven as references.
Davinci
Davinci
Declare a goal, and the loop ships the product
ONE AI Labs Framework IDE — autonomous development powered by Loop Engineering
- 017-stage loop pipeline — Idea → Plan → Design → Work → Verify → Improve → Report
- 023-tier verification gates + automatic convergence detection, 5-tier complexity classification
- 03Wave orchestration parallel execution — 3.5× faster than sequential
Nexus Talk
Nexus Talk
Built to talk, not to answer
A 27B open-weight LLM adapted for Korean character conversation
- 01Turn-level conversational adaptation — says one thing, stops, asks only when it matters
- 02Mean response length −68% (301 → 96 chars), length error vs. human turns −80%
- 0310 character-breaking probes — 0 persona breaks · 0 English drift · 0 system prompt leaks
LiloImage
LiloImage
One character, the same face from every angle
An in-house anime image model that draws character scenes
- 01Identity transfer from two references — face, hair color and outfit hold across cuts
- 02Hair color and outfit come from the appearance line in the character bible — the model never guesses them from an image
- 03Camera sentences come from a fixed table — high angle, low angle, top-down or POV, exactly per scene
ImageToApp
ImageToApp
One sentence of an idea becomes a working app
An AI app factory that turns a one-line idea into a spec, UI mockups, and a working app
- 01IDEA EXPANSION — auto-expands a one-liner into a spec and market-research report
- 02MOCKUP GROUNDING — decomposes image-AI mockups into layout trees that ground the code
- 03WORKING CODE — generates finished apps where buttons, inputs, and saving actually work
Kiroro
Kiroro
While the marketer sleeps, growth keeps going
24/7 autonomous performance marketing run by 27 AI agents
- 0127 agents including Product analysis · Positioning · SEO · Community · X Outreach
- 02Autopilot Engine — unmanned operations loop on a virtual day (default 60s/tick)
- 03Pipeline graph (@xyflow) · performance chart (recharts) visualization
PerfectPixel
PerfectPixel
One sentence becomes a living, moving pixel character
One line of text → 100+ motion sprites — the AI pixel-art studio
- 01Base character + 100+ motions auto-generated from one line of text
- 028-direction sprite sets with engine-friendly export
- 03Self-correcting quality loop and real pixelization
wasd
wasd
One line of description, a playable game 60 seconds later
Text-to-game engine — write it and it's built, say it and it's fixed
- 01Platformer · top-down · tower defense · puzzle · strategy — 2D Phaser templates
- 02FPS · racing — 3D Three.js templates
- 03Chat-based iteration (iterate via chat)
StoryMaker
StoryMaker
Write a novel, get a webtoon
Writing · characters · worldbuilding · webtoon rendering — the all-in-one AI creation studio
- 01Multi-LLM web novel writing (Claude and more via OpenRouter)
- 02Automatic per-episode storyboard analysis — 18–50 panels
- 03Speech bubble · narration · sound-effect overlay rendering
ONEchain Skills
ONEchain Skills
One sentence, and your agent acts on-chain
A suite of 9 natural-language AI agent skills that drive ONEchain
- 01ONEforge · ONEgametoken — token launches, bonding-curve trades, and GameToken AMM swaps/LP by sentence
- 02ONEnft · ONEshop — MarketplaceV1 NFT trading and in-game package checkouts in natural language
- 03ONEexplorer — read blocks, transactions, addresses, and contracts with no credentials
The brain of the Labs,ONE AI Labs framework
An in-house framework that orchestrates multiple AI backends in one workbench and runs autonomous loops until each goal is verifiably met.
Loop Engineering autonomous loops
The agent loop — perceive → reason → plan → act → observe — keeps running on its own until it reaches a verifiable goal (Done when).
Loop guardrails & file-based memory
Six guardrails — max iterations, token/cost budgets, stall detection, circuit breakers, completion criteria, and human checkpoints — block runaway loops, goal drift, and silent failures.
Multi-AI backend research environment
Drives Claude Code · Codex · Gemini CLI as native structured streams and experiments with 70+ LLMs via a direct OpenRouter connection.
Wave DAG parallel execution
Decomposes work into a DAG, runs it in parallel across isolated git worktree sessions, and converges through wave-level merges and Gate approvals.
da:* research-to-reference pipeline
Runs idea exploration (idea) → design (plan) → implementation (work) → verification (verify) as an automated skill chain.
24/7 autonomous operations infrastructure
Three remote-control channels — E2EE mobile bridge · Telegram · SSH — plus rotation and quota management from a Go account-pool server.
Key features, screen by screen
The ONE AI Labs framework isn't a slide deck — it's a workbench that actually runs. From the Loop Engineering dashboard to the 24/7 remote operations panel, see the key features exactly as they appear on screen.
01Loop Engineering
A loop that runs itself until the goal is reached
The perceive → reason → plan → act → observe pipeline runs with a live log while the Goal Evaluator rules PASS or RETRY on every iteration. A Done-when checklist, a Loop 7/50 iteration badge, the stop-hook status, and token-budget gauges — every state of the loop is controlled from one screen.
02Multi-AI Backend
Claude · Codex · Gemini in one workbench
Switch between three AI backends by tab, give them the same task, and swap among 70+ LLMs instantly with the OpenRouter model picker. Per-backend quota gauges and the account-pool indicator in the status bar show remaining capacity in real time.
03Wave DAG
Parallel like a team, safe behind the Gate
The work DAG unfolds across Wave 1 → 2 → 3 columns while agent sessions isolated in git worktrees execute simultaneously. When each wave finishes, the Gate Approval panel shows build, test, and lint checks before you approve the merge.
0424/7 Remote Ops
At 3 AM, the lab is still running
Direct agents from anywhere over the E2EE (X25519 · ChaCha20) mobile bridge and a Telegram command feed, while the overnight session monitor tracks per-account cost and quota rotation — 'All systems running, 03:42 AM'.
ONE AI Labs technical references
Browse by platform or search by name.
Desktop
Step 00 — The Engine Behind Everything
Davinci
ONE AI Labs Framework IDE — autonomous development powered by Loop Engineering
AI Model
Talk — characters that hold a conversation
Nexus Talk
A 27B open-weight LLM adapted for Korean character conversation
Image — characters become scenes
LiloImage
An in-house anime image model that draws character scenes
Desktop
Step 00.5 — The App Factory
ImageToApp
An AI app factory that turns a one-line idea into a spec, UI mockups, and a working app
WebStep 02 — Market Research · Growth
Kiroro
24/7 autonomous performance marketing run by 27 AI agents
DesktopStep 03 — Asset Production
PerfectPixel
One line of text → 100+ motion sprites — the AI pixel-art studio
Web
Step 04 — Game Development
wasd
Text-to-game engine — write it and it's built, say it and it's fixed
Desktop
Step 06 — ONE Story Creation Pipeline
StoryMaker
Writing · characters · worldbuilding · webtoon rendering — the all-in-one AI creation studio
Web
Chain — ONEchain by sentence
ONEchain Skills
A suite of 9 natural-language AI agent skills that drive ONEchain
While You Sleep,AI Keeps Creating.
ONE AI Labs never stops. AI doesn't just automate your work — it keeps producing breakthrough, creative results even while you rest.
It Automates While You Sleep.
Agents handle the repetitive work.
It Creates What You Didn't Imagine.
Ideas that begin with AI's own judgment go beyond automation into creation.
It Compounds Overnight.
Wave parallel execution validates and merges hypotheses simultaneously.
THE LAB NEVER SLEEPS. NEITHER DOES THE FUTURE.
One Engine.Every Reference.
39 skills and 33 specialized agents run the full cycle from idea to deployment as autonomous loops toward verifiable goals.
39
da:* skills
Full-cycle automation from idea to deployment
33
Specialized agents
CTO · PM · Security · QA · Creative
4+
AI backends
Claude · Codex · Gemini · OpenRouter 30+ models
3
Remote channels
E2EE mobile · Telegram · SSH
Wave DAG parallel orchestration
Decomposes work into a DAG and executes it concurrently in git worktree-isolated sessions.
PM Agent quality gates
A triple runtime of ConfidenceChecker (90%+ confidence) · SelfCheckProtocol · ReflexionPattern verifies every deliverable.
E2EE secure remote control
An X25519 + ChaCha20-Poly1305 end-to-end encrypted mobile bridge.
Automatic complexity routing
Automatically classifies five complexity tiers from LIGHT to EPIC and selects the optimal pipeline.
AI judges. Labs implements. References prove it. ONE AI Labs framework.