Launching 15 Aug  
तक्ष · Taksha — India's sovereign AI engineer

India's AI engineer. Your code never leaves the country.

A sovereign coding agent, served from India — or air-gapped inside your perimeter. It edits, runs, verifies and finishes real tasks in the editor your developers already use, and an independent referee stamps every claim.

Invite-only · your source never touches a third-party cloud.
The system, live

One coding request, measured end to end

Editor → shield → the measured router — the tier is chosen from graded runs, never a guess. The completion streams back, an independent referee checks it, and a signed Trust Receipt rides home with it.

The problem

Every keystroke your team sends to a foreign coding cloud is your source code leaving India. Taksha is the answer — the same agentic workflow, on a model you own, on soil you choose.

🇮🇳

Sovereign by design

Built in India, served from India. Your source code never crosses a border — data residency as a network fact, not a policy promise.

🛡️

A model we own

Not a rented frontier API. A model family we own, fine-tune and operate — the intelligence layer answers to you, not a foreign cloud.

⚖️

The independent referee

Every completion can be verified by a check the model never sees — your build, your tests — and stamped ✅ verified or ⚠️ unverified. No other coding assistant does this.

📊

Measured, not marketed

We publish our benchmark table — including the cells we lose. Same tasks, same graders, against GPT-5.5, Claude and Gemini. Ask any vendor for theirs.

🧩

Works in your editor

One-click VS Code extension, plus any OpenAI-compatible client (Zed, Aider, SDKs, curl).

🔎

Governed by default

Per-developer keys and metering, org limits, SSO, audit — the controls BFSI and government actually require, built in.

See it work

Agentic coding — in your editor, on your model

taksha · yantra · region: india
// migrate this VB.NET module to Angular + .NET reading LegacyOrders.vb … planning 4 edits created orders.component.ts (+82) created orders.service.ts (+41) updated app.module.ts (+6 −2) tests pass · X-Credits-Remaining: 14,382,905

Real multi-file, tool-using agent runs — nothing leaves your region.

The model family

The Taksha family — Fast · Pro · Max, and the Adhunik, Pariksha and Kriti specialists

Explore the models →
5× credits
The general model most teams live in
20× credits
Frontier-class + 160K context
5× credits
परीक्षा — tests that actually catch bugs
5× credits
कृति — interfaces that actually work, available now
soon
यन्त्र — for teams building agentic AI, in development
5× credits
आधुनिक — legacy to modern, available now

Taksha is the engineering member of the AgentAnywhere sovereign model family — alongside Manthan · Kuber · Seva · Tatva · Astra · Sanjaya.

The Measured Router

taksha-auto — routed by measurement, with the receipt in every response

Raw table (JSON) →

Set your model to taksha-auto and each request is routed to the model that measures best on its task class — by the table below, generated from execution-graded battery ledgers, never hand-edited. Every response says what routed where, and why:

x-taksha-router: web-endpoint -> taksha-max (balance) x-taksha-router-receipt: web-endpoint: max measured 8/17 on the graded battery (3 ledger files)
Loading the live routing table…

This is the live table the router reads — every cell is pass/n from graded runs, citing the ledger files behind it (hover a cell). A cell routes only with n ≥ 8; unclassified requests take the default tier, stated honestly, never a guess. A "—" means that tier hasn't accumulated n ≥ 8 graded runs on that class yet — Max is the newest tier, so its cells fill in as its ledgers land; we'd rather show you a dash than a number we didn't measure. Prefer thrift or the best measured rate? taksha-auto-cost and taksha-auto-quality tune the trade-off.

Sovereignty, not just privacy

Served from India. In your VPC. An owned model layer.

For regulated buyers, that's the difference between a policy promise and a network fact — every completion served from a model we own, on hardware in your jurisdiction. Taksha is part of AgentAnywhere Sovereign — agentic AI that never leaves your borders, signed proof on every call.

Pricing

Invite-only preview. Then your team. Then your VPC.

See full pricing →
Pilot
Invite
Free during the invite-only preview. Real scarcity — limited seats per machine.
Team
Waitlist
Pooled seats for startups and teams. Per-developer metering, org console.
Enterprise Dedicated
₹ on request
Your own dedicated serve. BFSI/Defence-ready. Annual commit.
Max add-on
Metered
Frontier-class node with 160K context, provisioned on demand.
FAQ

Straight answers

Does my source code leave India?

No. Taksha is served from India — or air-gapped inside your perimeter. Your source code never crosses a border: data residency as a network fact, not a policy promise.

How is Taksha different from other coding assistants?

Every completion can be verified by an independent check the model never sees — your build, your tests — and stamped verified or unverified. And routing is measured, not marketed: the routing table is generated from execution-graded battery ledgers and published live, including the cells we lose.

Which editors and tools does Taksha work with?

A one-click VS Code extension, plus any OpenAI-compatible client — Zed, Aider, SDKs, or curl — against one /v1 endpoint.

What is taksha-auto?

The measured router. Set your model to taksha-auto and each request is routed to the tier that measures best on its task class — a cell only routes with n ≥ 8 graded runs, and every response says what routed where, with the receipt.

Give your developers AI. Keep your code.