Lexical Autoresearch

Expert AI

Rented Intelligence. Done Right.

~3M tokens/month free

That's 20 questions everyday

with up to ~500M tokens/month

Pay only when you scale

ML based Knowledge Engineering for Modern R&D.

Create, find and edit technical documents
|

 #1
R&D CLI
12M+
Word AEC Wiki
6,500+
Users
20%
Daily time saved

Expert AI — Professional Research & Consulting
Research Domains:
● Architecture & Design
● Planning & Environment
● Social Science & Policy
● Engineering & Building
● Science & Research
Models: /model ssv.asia/free (default)
Ctrl+C returns to this menu
Thinking level: high
~
0.0%/128k (auto) ssv.asia/foundation ● high
Trusted by Scientists and Engineers from Premier Institutions of the Republic of India
Trusted Institutions
New · Free

Expert AI CLI
Frontier R&D in your terminal

Install in seconds. Get grounded, source-cited research, a curated architecture knowledge engine, and frontier models — pay only when you need more, with 6-hour passes from ₹60. The freemium precursor to Expert AI Terminal Pro.

$npm i -g expert-ai Copy

Get 10 messages and 10 MCP queries everyday - no card required. Only a free ssv.asia account

Frontier AI models Grounded research answers Architecture knowledge engine Expert deep dives Pay-as-you-go (UPI) Runs in your terminal

Community

Start free, no card

Free10 msgs/day
10 messages every day
  • ~3,000,000 tokens / month
  • Fastest open-weight models
  • Expert-grade agentic chat inference
  • 10 MCP knowledge queries / day
Included on install

Researcher

Everyday research

₹60/ 6-hour pass
2,000,000 tokens
  • Free + pro models
  • Web search + local document research
  • Long-document depth and creation
Unlocks inside the CLI

Engineer

Heavy, agentic work

₹120/ 6-hour pass
4,000,000 tokens
  • Everything in Researcher
  • Agentic tool use
  • Bigger budgets for long sessions
Unlocks inside the CLI

Professional

Power users

₹180/ 6-hour pass
6,000,000 tokens
  • Everything in Engineer
  • Top token budgets, deep multi-hour sessions
  • Priority routing
Unlocks inside the CLI
Architecture

AEC Professional

For architects & AEC pros

₹180/ 6-hour pass
6,000,000 tokens
  • Architecture knowledge engine — answers grounded in a curated AEC corpus
  • Real citations to source documents
  • Auto-engages on technical queries
Unlocks inside the CLI
Most capable

Foundation

Your hardest tasks

₹360/ 6-hour pass
5,000,000 frontier tokens
  • Frontier model lineup
  • Expert deep dives for complex problems
  • Everything unlocked
Unlocks inside the CLI

Prefer a monthly membership?

For teams and daily professionals, we offer flat monthly plans — bigger budgets, per-seat billing and priority support, provisioned directly. Passes are pay-as-you-go; memberships are for continuous work.

Talk to us →

Free forever, up to 10 messages a day — grab a 6-hour pass whenever you need to keep going, or to unlock frontier models and the AEC knowledge engine.

How passes work

1

Install & start free

One command installs the CLI. Get 10 messages free — no sign-up card needed.

2

Buy a 6-hour pass

Need more? Pick a pass right inside the terminal and pay by UPI. Each pass is a 6-hour window with its own token budget.

3

Stacks, never resets

Buy again while active and it adds time + budget — you never lose what's left. Pay only when you actually use it.

Frequently Asked Questions

A free, install-in-seconds AI terminal — run npm i -g expert-ai, then x. It brings frontier AI and a cited, curated knowledge engine to your command line, and works alongside any chat model. It's the freemium precursor to the full Expert AI Terminal Pro.
Start with 10 free messages. Beyond that, buy a 6-hour pass inside the terminal via UPI — Researcher ₹60, Engineer ₹120, Professional ₹180, AEC Professional ₹180, or Foundation ₹360. Each pass is pay-as-you-go with its own token budget; passes stack and never reset. For continuous, everyday use we also offer monthly membershipstalk to us.
It connects the CLI to a curated architecture knowledge engine. Ask a technical AEC question and the terminal automatically retrieves the most relevant source material and answers with real citations — not generic guesses. Casual chat stays instant; the corpus engages only when your question is genuinely technical.
Foundation gives you the frontier model lineup plus on-demand expert deep dives for your most challenging tasks — detailed reviews and high-level consulting-grade answers when you need real depth.
A pass runs for 6 hours. If you buy another while one is active, the time and token budget add on top — nothing is wiped. There's nothing to cancel; you simply buy a pass when you need one.
Your prompts route securely through the Expert AI gateway — no provider API keys ever sit on your machine, and we don't sell or train public models on your data. For full local, offline data sovereignty, see Expert AI Terminal Pro.
Install the CLI — Free →

Start free in 30 seconds · 10 messages + 10 knowledge queries daily · buy a pass from ₹60 to keep going past your free messages

Zero to research · ~30 seconds

New to AI tools? Start in five simple steps

No setup headaches, no API keys, no jargon. If you can copy and paste one line, you can run frontier, source-cited research from your own computer.

1

Install Node.js (a one-time, free download)

Expert AI runs on Node.js — the same free tool that powers most modern apps. Download it once, click through the installer, and you're set for life.

Pick the LTS version. On Linux? Install via nvm. Already have Node? Skip to step 3.

2

Open a terminal — you already have one

A terminal is just a box where you type commands. Use whatever you're comfortable with — it works everywhere:

⊞ PowerShell (Windows) Terminal (macOS) ◧ VS Code ✳ Claude Desktop △ Antigravity ▷ Cursor ⌘ Any IDE terminal
3

Install Expert AI — one line, ~30 seconds

Paste this and hit Enter. That's the whole install.

$npm i -g expert-ai Copy
4

Type x — anywhere, anytime

From any folder in any terminal, just type x and press Enter to launch Expert AI. One letter — that's your shortcut to the whole engine.

$x Copy
5

Log in once, press 1, start asking

On first run it opens your browser to sign in with your free ssv.asia account — once. Back in the terminal, press 1 for Research and type your first question. You're now running grounded, cited AI research. That's it. 🎉

Why Expert AI is the research CLI to reach for

Built for people who need answers they can trust and cite — not just confident-sounding guesses.

Grounded & citedEvery research answer traces back to real source documents — verifiable, not hallucinated.
Curated AEC engineA 12M-word architecture & engineering corpus that auto-engages on technical questions.
Frontier models on tapReach top-tier models the moment a task needs real depth — no config, no keys.
Pay only when you use itFree every day, then simple UPI passes from ₹60. No subscription trap.
Lives in your workflowRuns in any terminal or IDE, right next to your files and your other tools.
🔒Keys never touch your machineEverything routes securely through the Expert AI gateway. Private by design.
WhatsApp
Look Inside

One command. Research engine.

Type x and you're driving an agentic core, a mesh of fast expert models, and a cited knowledge base — frontier-class results at a fraction of frontier prices. Run it solo, or pair it with your Claude or Codex subscription and switch over the moment you hit their limits.

/rAEC · Foundation

Research the knowledge base

Pull answers straight from the curated AEC corpus — building codes, standards and technical references — returned with source-document citations.

/sAny paid pass

Search the live web

Ground a reply in fresh web results — news, latest releases, current facts — summarised and cited inline, right inside your terminal.

Agentic coding harness

A purpose-built agentic harness developed and maintained by ssv.asia: it doesn't just chat — it reads and edits your local files, runs commands, and loops through multi-step tasks on its own, showing its thinking as it goes.

reads & edits filesruns toolsmulti-step loopsvisible reasoning

MoE model mesh

A cascade of mixture-of-experts models that activate only the parameters each query needs — so you get frontier-class answers at a fraction of the usual speed and cost, routed automatically per task.

sparse activationfrontier-classauto-routedlow cost / token

Grounded knowledge

A curated 12M-word AEC corpus and live web search wire straight into the model — every fact comes back with a real citation you can open, not a confident guess.

12M-word corpusreal citationslive web search
ssv.asia/freeHaiku + GPT class
Free₹0 / M tokens
Free forever

Best for quick everyday questions, drafts and fast iterations.

ssv.asia/proSonnet class + retrieval + search
₹30/ M tokens · flat in + out
≈ 96% cheaper than Sonnet

Best for general research, writing and balanced agentic work.

ssv.asia/aecSonnet class + retrieval + search
₹30/ M tokens · flat in + out
≈ 96% cheaper than Sonnet

Best for cited, code-accurate architecture & engineering answers.

ssv.asia/foundationOpus 4.8 + Fable 5 class
₹72/ M tokens · flat in + out
≈ 98% cheaper than Opus

Best for your hardest reasoning, deep analysis and long agentic runs.

How the routes compare

Capability Benchmark is approximate, for orientation. Speed reflects industry grade throughput; prices below are effective per-million-token rates vs. public frontier list prices (input + output averaged, ₹ approx).

ssv.asia/foundationOpus 4.8 + Fable 5 class
Reasoning
97
Agentic
95
Grounding
98
Speed
93
ssv.asia/aecSonnet class + retrieval + search
Reasoning
80
Agentic
70
Grounding
98
Speed
93
ssv.asia/proSonnet class + retrieval + search
Reasoning
82
Agentic
84
Grounding
58
Speed
95
ssv.asia/freeHaiku + GPT class
Reasoning
72
Agentic
64
Grounding
40
Speed
99

The same class of model, a fraction of the price

Blended list price per 1M tokens (input + output averaged). One flat rate — we don't charge more for output.

Claude Opus 4.8Anthropic API
~₹3,800 / M
Claude SonnetAnthropic API
~₹750 / M
GPT-4oOpenAI API
~₹525 / M
Expert AI · FoundationOpus 4.8 + Fable 5 class
₹72 / M −98%
Expert AI · Pro / AECSonnet class
₹30 / M −96%

How to use it in your R&D workflow

01
Already on Claude or Codex? Keep them.

Bring Expert AI in the moment you hit their usage limits, or to run extra research in parallel — without burning premium quota.

02
Everyday R&D, near-free.

Drafting, search, iteration and code exploration run on the fast free and pro routes for a fraction of frontier cost.

03
Call in the heavy hitters on demand.

Deep, cited domain research (AEC) or your hardest reasoning (Foundation) — Opus / Sonnet-class quality at up to 98% less than the frontier APIs.

Lexical Autoresearch

Start using Expert AI Terminal today, Purchase a dedicated installation for your machine

AI chat, AI Agents and knowledge systems built for rigorous domain expertise and sovereign data hosting.