26io Techlab · Independent Ai studio

Three Ai products,
live today.

Evi plans its answer, then grades its own work against the sources it used. Kus makes small models answer like big ones. Revmosys tells you what actually changed on your website, not just what happened. No reseller markup on any of them — we design, build, and run every one ourselves, on infrastructure we operate.

Evi AiLive

Every assistant can sound confident. Evi grades itself.

It classifies your question, decides the answer's shape before writing a word, then scores its own reply against the sources it actually used — not a claim you have to take on faith.

It marks its own work
Every reply is scored out of 1 after streaming — against the plan, and against the search results it was actually given rather than its own training.
It plans the answer before writing it
The question is classified, then a separate pass picks the format, length and tone and lists what to cover. A debugging question leads with code; a maths question gets worked through; 'hi' gets one line.
Memory and documents come as standard
Long-term memory across chats and answers drawn from the PDFs you upload, tied back to the source text.
Evi
My React list re-renders on every keystroke. Why?
planned intent: technical_debug · format: code · detailed
The parent holds the input value, so
every keystroke re-renders the list.
self-scored 0.94 against plan
KusLive

Make a small model answer like a big one.

One API that searches trusted sources and answers with citations — turning weak or local LLMs into reliable ones.

Hierarchical parallel retrieval
A master router fans each query across three child RAGs and nineteen async source workers at once, so breadth costs latency only once.
Two-stage ranking
Hybrid BM25 + dense retrieval fused with RRF, then a FlashRank cross-encoder rerank. It runs on CPU, so accuracy costs nothing extra.
Answers in ~150ms when cached
A question close enough to one already answered returns from the semantic cache with no model call at all.
Your documents stay yours
A shared public knowledge base plus private per-tenant documents, isolated by API key.
kus · /v1/answer
POST /v1/answer
{ "query": "What is RAG?",
  "model": "local-llama" }
// → 200 OK
{ "answer": "Retrieval-Augmented…",
  "citations": [ "arxiv.org/abs/2005.11401",
               "…" ] }
RevmosysRevmosysLive

Most tools show you numbers. Revmosys tells you what broke.

One number, one sentence, one action — not a wall of charts nobody opens.

It won't cry wolf
A jump from 3 enquiries to 6 looks huge on paper — Revmosys knows that's still just noise, and says so instead of celebrating early.
Finds the real break
Fewer people showing up, or fewer of them following through? Revmosys tells you which one — never both at once, never a guess.
Checks what Ai assistants say about you
Every month, it asks the way a real customer would, and tells you whether your business gets recommended — and who gets named instead.
Revmosys · monthly read
Same visitors, fewer getting in touch
34/ 100range 26–42
9 enquiries from 425 visits · last 28 days
Visibility78
Conversion21
Volume36
Resilience52
⚠ Your phone number isn't visible on mobile
How we build

A small studio that ships whole products.

We build full products, not demos — every one is live or in active build, run on infrastructure we operate ourselves. Owning the whole stack is what keeps our costs down, so we can ship capable Ai at prices the incumbents can't match, and we design for trust: answers you can verify, data you control.

Own products, end to end

We design, build, and run each product ourselves — on infrastructure we operate, not a reseller's.

Affordable by design

We own the whole stack, so there's no reseller margin — capable Ai at prices the incumbents can't match.

Answers you can check

Grounded, cited answers and real document understanding — built so you can verify, not just hope.

Not built for the funded few

We start with the students and independent developers the industry prices out, then build for everyone else.

Who's behind 26io

Gokulakannan R

Founder

I design, build and run every 26io Techlab product end to end — Evi, a personal Ai assistant that plans its answer before writing it, and Kus, a retrieval API that makes small models answer reliably with citations. That means the model pipeline, the product, and the infrastructure it runs on. I'm currently researching a lightweight language model small enough to run almost anywhere and cheap enough for students and independent developers.

In the lab · ResearchEarly-stage R&D

We're building our own lightweight Ai model.

We're researching our own lightweight language model — small and cheap enough to run almost anywhere, yet tuned to punch above its weight. It's early-stage R&D, and it's where 26io is headed: an efficient model we'll offer through an affordable API, so students and developers get frontier-grade capability without frontier prices.

Start with Evi.

Our Ai assistant is live and free to try. One 26io account works across Evi and Kus.

Try Evi free →