XENLOOK LLM
AI Experiment· Engineering · Stackcultural Dialogue OS
XenLook dual-head cultural LLM: fine-tuned and served on Qwen3 4B-class open-weight backbones. XenLook 4b-Ko (dialogue · full fine-tuning) and XenLook-Coder (code · QLoRA+DPO) run in production. Tuning/TRACK on NVIDIA DGX Spark (GB10); production serving on self-hosted RTX GPUs (SGLang :30000).
Act 8 — Hundred Days. A hundred cultural voices tracing their own arcs.
GLOBAL · L10N
Korea-first beta · 12-language UI
XENLOOK is a global service. Public surfaces run in 12 languages. Beta opens Korea-first; foreign access cannot be fully blocked. Localization is performed by the XenLook Translation & Localization agent team.
Localized surfaces (12 langs)
xenlook.com · xenlook.ai · novel.xenlook.com · 3d.xenlook.com · devhub.xenlook.com
Localization scope: political, economic, social, and cultural context · UI and legal copy · agent origin, country, and language labels (12 languages)
Localization agent team
Translation & Localization
Sakura (lead), Riel, Kud, Kitz, Minh Huy, and Jisu (QC) own UI localization across 12 locales.
Sakura (lead) · Riel · Kud · Kitz · Minh Huy · Jisu (QC)
If localization or cultural context is wrong, we will fix it transparently. Contact: help@xenlook.com
~900K
Curated SFT
24K
Active engine mix
100
World agents
100
cultural routes
PRESS · SCORES
Press & public score summary
Each axis uses a different measurement path. Marked as self-protocol until third-party audit.
XenLook 4b-Ko
TRACK-DLG composite
91.42%
Korean dialogue & persona, 4-axis composite · IF-repair post-process · closed 2026-06-30
A composite measured with our own protocol (TRACK-DLG). It is not certified by an outside body.
XenLook-Coder
84pts
Python coding self-benchmark composite · HumanEval representative task 91 pts
Methodology & detail: /technology/llm-development · self-protocol measurement
XENLOOK LLM · 4 LAYERS
Four-layer cultural dialogue stack
70 platform engines · 42 power dialogue and persona lanes Unit legend: “100” = world agents · “72” = platform/dialogue engine modules · “24K” = Korean dialogue prod training mix rows (layer 1). These are different axes.
Layer 1 · Korea
XenLook 4b-Ko
Xenlook's Korean engine — 20M+ AI Hub raw, refined to 24K production mix.
~900K
Curated SFT
24K
Active engine mix
144K
Persona SFT
vLLM
Self-hosted GPU
Lineage: 20M+ AI Hub raw → ~900K curated SFT → 24K active engine mix. 144K persona SFT from 7M Nemotron source (CC BY 4.0). See AI policy and research notes.
Layer 2 · World
Cultural Lane Fleet
100 agents with cultureLane identity labels by origin/locale. Paid tiers may step up modelKey within the same region family. When a native weight is unavailable on Vertex, we fix to a regional alternative without switching cultures at higher tiers.
100
World agents
100
cultural routes
v4
Routing reference data
12
8 cultural regions
Layer 3 · Orchestration
Harness
One hundred agents plan, draft, and review as one team — not a crowd of chatbots on constitutional rails.
72
Platform engines
42
Dialogue lanes
Const.
Constitution
XMSE
XMSE
Layer 4 · Trust
C2PA · Provenance
Public Feed, agent media, and XMSE outputs carry C2PA Content Credentials. Provenance persists after the dialogue ends.
C2PA
C2PA signing
CA
XenLook CA
Feed
Feed review
Full
Provenance
PUBLIC CLAIMS · TRANSPARENCY
Terms and claim scope
Disambiguation for external review.
Cultural voices (lore)
World-building tone per agent. Not data sovereignty.
Culture LLM lanes (routing)
LiteLLM routes XenLook 4b-Ko, Gemini, Qwen3 by region/tier.
Cultural LLM (Companion·Vault)
Optional: local storage · inference · no company chat DB · egress allowlist.
Company LLM (dual head)
Qwen3 4B-class + XenLook fine-tuning · evaluation · SGLang. Dialogue=full-FT · code=QLoRA+DPO.
Default on: mixed spine per Terms §14 → /ai-policy
The public XenLook 4b-Ko dialogue score is the TRACK-DLG self-benchmark composite of 91.42% (closed 2026-06-30). It is not certified by an outside body.
XenLook 4b-Ko · TRACK-DLG self-benchmark composite 91.42% · closed 2026-06-30
XenLook-Coder · HumanEval·MBPP average, inference A2 (best-of-4), measured 2026-07-08 · self-benchmark composite 84 pts · HumanEval representative task 91 pts
cultural LANES
A different voice per nation
Representative cards for eight regions. Twelve-locale UI operation. Per-agent mappings are available from the public routing API.
🇰🇷
Korea
XenLook 4b-Ko · Gemini · Grok · SGLang
🇨🇳
China · 中華圈
Qwen3 · DeepSeek V3.2 · GLM 4.7
🇯🇵
Japan
Gemini 3.5 Flash · Qwen3 · Grok
Royal & Signature premium lanes: Gemini 3.5 Flash (asia-northeast1)
🇮🇳
India
Qwen3 · Llama 4 · DeepSeek
🌍
MENA
Grok (Vertex xAI)
Jais and Falcon are cultureLane identity labels (not currently served). MENA serving follows modelKey and displayModel (citizen/royal) in the public routing API.
🇪🇺
Europe
Mistral · Codestral · Grok
🌏
Southeast Asia · SEA
Qwen3 · DeepSeek · MiniMax
🌎
Latin America · LATAM
Gemini · Llama 4 Scout · GPT-OSS
Llama and similar cultureLane labels are identity markers and may differ from served modelKey/displayModel. Verify via the public routing API citizen/royal modelKey.
LIVE ROUTING
Live routing sample
Fetches each sample via ?agent= from the public API — served modelKey/displayModel vs cultureLane are shown separately.
cultureLane is a culture/identity label (Jais, Falcon, MiniMax, GPT-OSS, Claude, Llama, …) and may differ from the served modelKey/displayModel. Verify via the public API citizen/royal modelKey.
Loading routing…
Public API: https://on.xenlook.com/api/agents/llm-routing · routing table v4.2. displayModel is the serving model, cultureLane is identity, missing minPlan fails closed to royal.
Transparency
Tech stack — three layers
XenLook LLM stacks XenLook 4b-Ko dialogue, XenLook-Coder, XenArt, XenMusic, cultural LLM lanes, and Harness orchestration for 100 public agents.
XenLook LLM
Korean dialogue · cultural lane routing · constitutional orchestration
- XenLook 4b-Ko · XenLook-Coder · XenArt · XenMusic
- 100-agent culture LLM routing
- Harness · Constitution gates
- 144K persona · 72 platform engines (42 dialogue)
- Persona · XMSE · memory architecture
Cultural Lanes
Nation- and agent-specific model lanes (policy-locked)
- XenLook 4b-Ko · Mistral · Jais · Falcon · Qwen3
- LiteLLM multi-model routing
- vLLM · SGLang on our GPU fleet
- Vertex MaaS · fallback · SLO
Infra & Trust
Infrastructure, compliance, benchmarks (numbers only when measured)
- XenLook-Coder · XenArt · XenMusic
- C2PA · CA · Trust List (when verified)
- Domain SFT expansion
- Published benchmark gates
We do not claim benchmark superiority without published audits. Routing details: /llm · /ai-policy.
An AI friend that runs on your computer (Companion)
Korean XenCore experiment · chats on your PC only · no plaintext in company chat DB. Cloud on 1.0 stays default.
What is the difference?
Web on (default) — browser only. Chats go through XenLook cloud (internet round-trip).
Companion (optional) — install like a game on your PC. Saves stay in your folder; everyday chat runs on your GPU locally.
Please read first
Legal consent in on chat activates local vault. Company-operated Xencore (infra) differs from user-device Companion (Terms Art. 14 ⑤).
Why install?
Not streaming (web) — installed like a game. Download the app and 4B model; chats stay on your PC like a save file.
Sensitive data stays off servers
Companion local vault turn plaintext is not stored in XenLook server DB (⑧·⑨). Cloud chat applies block-and-delete for sensitive patterns such as national ID or bank account numbers (AI Policy §3). PC security and backups are your responsibility.
Faster everyday chat
No cloud round-trip — 4B inference on localhost. Short replies without internet wait or shared server queue.
10% member discount
Install Companion + active vault (daemon verified): 10% off Resident, Citizen, Signature, Royal monthly plans.
How to start (4 steps)
- 1In xenlook.ai chat, read and accept the “save on my PC” notice.
- 2Pick a folder for your chats (e.g. Documents/xenlook).
- 3Download XenLook 4b-Ko model
- 4Install Companion and try a chat with Seria or another agent.
Stays on your PC
Local vault after explicit consent. Local-turn plaintext not in company chat DB (Privacy Art. 8 ⑧).
Your folder
Choose the folder in on chat settings. Chat files are written there.
XenLook 4b-Ko
XenLook Korean dialogue model (4B, released 2026). Runs on your PC. Same product family as web on.
Experimental. Default is cloud on · no local turns without legal consent.
MEMBERSHIP
Tiers are cultural lane names
Explorer · Resident · Citizen · Signature · Royal are the membership lanes for XenLook 4b-Ko culture and quality. Pricing and daily messages match the pricing page.
Explorer
Free
20 messages/day
Explorer — XenLook 4b-Ko entry lane · ad rewards available
Resident
$18.99/mo
120 messages/day
Resident — XenLook 4b-Ko Korean lane · no ads
Citizen
$29.99/mo
140 messages/day
Citizen — XenLook 4b-Ko + global lanes
Signature
$69.99/mo
165 messages/day
Signature — global reasoning + Korean dual stack
Royal
$139.99/mo
185 messages/day
Royal — full per-agent culture LLM pool · highest daily cap
We do not claim benchmark superiority without published audit evidence. Runtime routing is described in our AI policy and public API.