Sovereign AI · made in India · zero dependence

Software that builds itself.
And never leaves India.

code.in is the sovereign AI platform that plans, writes, ships and attests your software — on frontier-class specialised models, on in-country compute, with zero foreign dependency. Your code. Your data. Your borders.

100% built & hosted in India · residency attested on every build
zero
foreign APIs. ever.
100%
in-country, always
10×
faster delivery
100%
in-country
0
foreign APIs
1
sovereign model
10×
faster builds
audit trail
Residency attested Build signed Append-only audit RBAC at build time Zero dependence In-country deploy Residency attested Build signed Append-only audit RBAC at build time Zero dependence In-country deploy

Why sovereign

Platform sovereignty in the agentic era

Most tools send your prompt abroad, run it on a foreign model, and deploy it abroad. code.in keeps every byte inside India's borders.

EVERY OTHER TOOL

Your prompt exits the border

your prompt foreign model deployed abroad

Data leaves the country the moment you hit send. You don't control the model, the compute, or where the build lands.

CODE.IN

Stays in India, start to finish

your prompt sovereign model deployed in-country

Residency attested, build signed. The whole pipeline — model, compute, deploy — lives inside India.

residency attestedbuild signed

The platform

Agentic engineering, 10× faster

There's more to engineering than writing code. code.in compresses delivery so your teams can do what AI can't — decide what to build next.

codein terminal
dev@code.in:~$ codein build "rail booking portal"
planned the architecture — Next.js + Postgres
wrote the code, wired the database
Hindi + English, RBAC, append-only audit log
pushed to git, deployed to India infra
→ live: https://rail.code.in build passed · residency: india

The evidence

Every build ships with proof

Not a promise. A signed, tamper-evident record you can hand to procurement.

BUILD RECORD · India, verified
Systemrail-booking
Environmentindia, production
Data classConfidential
Residencyin-country, attested
Access modelRBAC, 5 roles
Foreign APInone
RESIDENCY

Attested on every build

Every deployment produces a signed residency record confirming your code never left India's borders.

AUDIT LOG

Append-only, tamper-evident

Every action is logged in sequence. Nothing is editable. The trail is the proof.

ACCESS CONTROL

RBAC defined at build time

Roles and permissions are mapped as the system is engineered, not bolted on after.

Benchmarks

Closing the gap to the frontier — and open labs

Same harness, same discipline, measured on the same benchmark the frontier labs use. Every code.in number below is a real scored run of our own sovereign harness — a different model per track, no third-party scaffold.

SWE-bench Verified · 500 tasks
ModelLaneScore
Claude Opus 5Closed frontier96.0%
Claude Opus 4.8Closed frontier88.6%
DeepSeek V4 ProOpen weight80.6%
Qwen3.7 MaxOpen weight80.4%
MiniMax M2.5 (own harness)Open weight80.2%
code.in + MiniMax M2.5OURSOpen weight70.0%

Our sovereign harness drove MiniMax M2.5 to 70.0% (350/500) on SWE-bench Verified — trailing the same model's 80.2% on its own harness, with the open-weight frontier at ~80 and the closed frontier at ~88–96. We're closing the gap with a model-agnostic harness and smart tokenomics: swap in any open-weight model, pay only for what you resolve, and run it all in-country.

SWE-bench Lite · 300 tasks
ModelLaneScore
code.in + GLM 5.3 FlashOURSOpen weight63.0%
Claude Opus 4.6Closed frontier62.7%
MiniMax M2.5 (native)Open weight56.3%
GPT-5Closed frontier54.3%

On Lite, our harness with GLM 5.3 Flash scores 63.0% (189/300) — leading the table, ahead of MiniMax M2.5's native 56.3% and Claude Opus 4.6's 62.7%. We're already ahead on the smaller split.

Two tracks tell one story. On SWE-bench Lite we already lead — 63.0% with GLM 5.3 Flash. On SWE-bench Verified we trail the frontier by ~10–25 points with the same harness. Closing that gap is scaffold work: reproduce-test-first, regression filtering, best-of-N, hierarchical localization. We port the patterns, not the code, and run them all inside India.

Who it's for

For institutions where compromise isn't an option

100%
In-country. Always.
0
Foreign APIs. Ever.
1
Sovereign model. For India.
Audit trail. Every build.

Start building.
Stay sovereign.

$ npm i -g codein-cli