NIOPTINET
The coherent optical transceiver with the lowest latency per bit.
Our own coherent design, with Natural Intelligence built in. It adds less delay, reaches further and tunes each link by itself.
Up to 2.5× less delay, already.
Our prototype runs on off-the-shelf hardware and already beats the published figures. The next board halves it again.
Why it matters
Less delay
For AI clusters spread across sites and for trading, every microsecond counts.
Longer reach
Natural Intelligence gets more distance out of the same fibre.
Links that tune themselves
Each link picks its own error correction and speed for your priority: lowest delay, highest rate or longest reach. Our Natural Intelligence decides in about 55 ns.
One design, many links
Because the chip design is ours, the same chip runs coherent, PAM4 or NRZ.
Proof
Our engine, Lumitrine, is the core of NIOPTINET. Six 4K movies, 16.1 GB in all, went from a normal PC through its two links and back.
| Delay per link, one way | 3.2 µs (commercial modules: 4.7–7.9 µs) |
|---|---|
| Speed, two links together | 55.3 Gb/s |
| 16.1 GB of real files | 2.7 s |
| Files identical after the trip | 6 of 6 |
Lab bench, October 2026. On the bench the links run over short cables; real fibre spans come next, with pilot partners.
Where we are
| Core engine | Working in hardware |
|---|---|
| Next board (AMD Versal RF) | Target ≈1.6 µs per link |
| Coherent transceiver | In development |
| Pilot partners | Choosing a few now |
Test NIOPTINET on your link.
A mutual NDA comes first. Then a short test plan, our bench, and your link.