VisionCAM-2
Loading tracks…D-FINE-S
See
Detect, track and re-identify what cameras see, live and on edge devices.
Edge · int8
Multi-camera re-ID, exported to ONNX int8
Bring us a real problem. We build the AI, ship it to production and keep it running.
Today, 08:25
RunningSolutions
Document intelligence
HÓA ĐƠN GIÁ TRỊ GIA TĂNG
請求書 · VAT invoice
Đơn vị bán: Công ty TNHH Minh An
Mã số thuế: 0312 457 889
Ngày 18 tháng 11 năm 2026
| Hàng hóa | SL | Thành tiền |
|---|---|---|
| Thùng carton 5 lớp | 1,200 | 21,600,000 |
| Băng keo OPP 100y | 400 | 6,400,000 |
| Pallet nhựa 1200 | 60 | 13,200,000 |
| Phí vận chuyển | 1 | 3,818,519 |
Thuế GTGT 8%: 3,601,481
Tổng cộng: 48,620,000 ₫
(Ký, ghi rõ họ tên) — 署名
Extracted
schema: vat_invoice.v3
Under the hood
data → product
Vision analytics
Offline D-FINE-S tracks on this clip, no hand-placed boxes. Tap a box to inspect it.
Under the hood
data → product
Voice agents
Transcript
Slots
Decision
Waiting for the full request…
{ "title": "Meeting with Lan", "start": "2026-11-20T15:00+07:00" }{ "at": "2026-11-20T14:30+07:00" }auto-playing · tap to pauseauto-playing · click a decision to pause
Under the hood
data → product
Analyst agent
Under the hood
data → product
More solved problems
Under the hood
data → product
Evolution
Level 1 of 5
Research
The same four-step pipeline, killed with SIGKILL in step three under three frameworks. We counted how many steps each one repeats on resume.
LangGraph 1 · LlamaIndex 2 · Agno 3
In LifeMate, a spoken request becomes the right tool calls, one clarifying question, or nothing. Hotword-biased speech recognition keeps names and places right, in English and Vietnamese.
act / ask / quiet
DPO and KTO pipelines for smaller models on curated clinical documents, traced end to end with Langfuse.
Work with us
Not sure AI can do it?
A short sprint on your real data. You get a working prototype, the numbers, and an honest go or no-go.
You know what you need.
Agreed scope, from first dataset to production, handed over with code, docs and decision records.
AI is part of your roadmap.
Our engineers join your team month to month, in your tools, your repos and your timezone hours.
How we work
A week with your documents, cameras or logs. We agree on one number that means “working” and freeze a test set before we train anything.
Baselines first, then models and agents. Every change runs against the frozen set, so progress is a chart, not an opinion.
Quantize, serve, trace and cost it. Retraining, rollback and monitoring are built in, not bolted on.
Your team gets the code, the decision records and a walkthrough. We stay on call while it settles.
Founders

Lê Văn Duy
Co-founder · CEO
Owns the product layer: agents, document AI, and the APIs and interfaces around them.

Võ Hoàng Minh Trí
Co-founder · CTO
Turns new research into models that hold up: vision, tracking and generative AI.

Nguyễn Chí Nguyện
Co-founder · COO
Takes systems onto real sites: production lines, robots and LLM platforms that stay up.

Nguyễn Trung Hậu
Software Engineer
Builds the backend behind each product: APIs, data models, access control and releases.
Before Untern, our team built and was recognised at
Tell us what the data looks like and what “working” would mean for you. One of the founders will reply.
Prompt
Agent