The AI that
works with you.
Think, write, search and build with one AI that remembers what matters, and keeps the work as artifacts you can revise.
WATCH CRUXY
Pick a task to watch what Cruxy does with it, or type your own. Try Cruxy opens it in Cruxy, ready to send.
Build a launch plan for our new product.
- Searched the web · 6 sources
- Used the Q4 launch vault's instructions and memory
- Read positioning-notes.txt
- Created an artifact: Launch plan
I built the plan from your notes and the vault's instructions: goals, audience, channels and a four-week timeline. It's open on the right. Tell me what to change and I'll save it as a new version.
Launch plan
From positioning-notes.txt and the Q4 launch vault
- Goals
- [From your notes]
- Week 1
- Announce and open sign-up
- Week 2
- Launch post and demo
- Week 3
- Partner outreach
- Week 4
- Review and next steps
Interface preview. Every step shown is one Cruxy performs today; the file and the reply are illustrative.
Platform
One workspace for real work. Chat, memory, vaults and artifacts, with your own tools. Open any tile to see how it works.
By the numbers
Specific about what it does. Every number here is one Cruxy enforces today.
1M
tokens of context on Canto, the deep model, for long documents.
4
ways to pick a model: Fast, Balanced, Deep, or auto.
10
text or JSON files per message, 80 KB each.
AES-256
GCM encryption for secrets at rest, field by field.
Artifacts
Don't just get an answer. Get the work, written beside the chat and kept as versions.
Documents, code, charts and web pages generated alongside the conversation. Ask Cruxy to revise one, compare versions, or download it.
Launch Plan: 28 October
Decision: We ship on 28 October. No delays, no feature creep. Everything in this plan supports that date.
Goals
- Reach 100 active users within the first three days.
- Keep system uptime above 99.5% during launch week.
- Prove that new users complete the core workflow without support.
Week 1: Lock Core & Stress Test
- Freeze features and push the final release candidate by Monday.
- Run load and failure drills across production infrastructure.
- Owner: Engineering & Product | Metric: Critical bugs (target: 0 by Wednesday)
Week 2: Warm the Funnel
- Send launch teasers and onboard the early access cohort.
- Finalize support playbooks and prepare customer onboarding guides.
- Owner: Growth & Customer Ops | Metric: Waitlist-to-beta conversion (target: 30%)
Week 3: Final Polish & Go Live
- Dry-run launch messages and monitor pre-launch traffic patterns.
- Owner: All hands (Founder leads comms) | Metric: First 48-hour activation rate (target: 40%)
- Rollback trigger: Revert to the previous stable release if uptime drops below 99% or activation falls under 25% in the first 24 hours.
Use cases
Made for the way you work. From a first draft to a shipped fix, with the same context all the way through.
Turn scattered notes into a plan.
Attach your notes, keep the context in a vault, and get a plan you can revise without starting over.
PRODUCTS USED
- 01Attach your notesText and JSON files, up to 10 per message.
- 02Cruxy reads the vault and searchesThe vault's instructions and memory, plus current results from the web, with links.
- 03The plan opens as an artifactAsk for changes. Every version is kept, ready to compare or download.
Developers
Build on the same platform. An OpenAI-compatible API for chat, a CLI that works in your repo, and your own tools over MCP.
import OpenAI from 'openai';
const cruxy = new OpenAI({
baseURL: 'https://api.cruxy.ai/v1',
apiKey: process.env.CRUXY_API_KEY,
});
const res = await cruxy.chat.completions.create({
model: 'auto',
messages: [{ role: 'user', content: 'Summarize this ticket' }],
});$cruxy run "fix the failing tests in the auth module"cruxy › fix the failing tests in the auth module! cruxy wants to run tests: pnpm test (destructive) $ pnpm test in /home/dev/web [y] once · [a] always allow test runs of exactly `pnpm test` this session · [t] reject & instruct · [n] no: a✗ tests failed · 2 of 42 failed · 3.1s · pnpm test ✗ signs a session token src/auth/session.test.ts:18 expected "ok" received undefined ✗ rejects an expired token src/auth/session.test.ts:41 why (inferred) TOKEN_SECRET is not set in the test environmentInterface preview. CLI output is real; model replies are illustrative.
OpenAI-compatible API
Point your existing SDK at api.cruxy.ai/v1 and set the model to auto. Chat completions and models today, with the moderation API alongside.
Cruxy Code CLIBeta
Plans the change, asks before it runs a command or edits a file, runs your tests, and checkpoints every run so /undo-last can restore it.
npm i -g @cruxy/cliEditor pluginsComing soon
Cruxy Code inside VS Code and JetBrains, with the same approvals and checkpoints. Planned.
Models
The right intelligence for the work. Auto picks a model for each request. Or choose one yourself.
Pricing
Start free. Upgrade when the work grows.
Free
Explore Cruxy
₹0
per month
Join the waitlist- Models · Saga
- Context window · 256K
- Usage · Limited
- Storage · 1 GB
- AI chat · Limited
- Web search with cited sources · Limited
- Projects with instructions and files · Up to 3
- Works: documents, code and pages Cruxy creates for you · Up to 3
- API access
Core
Everyday AI work
₹399
per month
Join the waitlist- Models · Epos and Saga, with Auto
- Context window · 1M
- Usage · 1/4 of Advanced
- Storage · 10 GB
- AI chat
- Web search with cited sources
- Projects with instructions and files
- Works: documents, code and pages Cruxy creates for you
- API access
Advanced
RecommendedThe complete personal workspace
₹1,499
per month
Join the waitlist- Models · Epos, Saga and Canto, with Auto
- Context window · 1M
- Usage · 1×, the baseline
- Storage · 25 GB
- AI chat
- Web search with cited sources
- Projects with instructions and files
- Works: documents, code and pages Cruxy creates for you
- API access
Pro
4× Advanced capacity
₹8,999
per month
Join the waitlist- Models · Epos, Saga and Canto, with Auto
- Context window · 1M
- Usage · 4× Advanced
- Storage · 100 GB
- AI chat
- Web search with cited sources
- Projects with instructions and files
- Works: documents, code and pages Cruxy creates for you
- API access
Max
8× Advanced capacity
₹17,999
per month
Join the waitlist- Models · Epos, Saga and Canto, with Auto
- Context window · 1M
- Usage · 8× Advanced
- Storage · 500 GB
- AI chat
- Web search with cited sources
- Projects with instructions and files
- Works: documents, code and pages Cruxy creates for you
- API access
Prices in INR, including GST.
Trust
Built for teams, careful with data. Each row is something Cruxy does today.
Teams
- Owner and admin roles for your organization, on every planLive
- Shared vaults with instructions and memoryLive
- Personal memories that only you can seeLive
Security
- Encrypted in transit, with HSTSTLS
- Secrets encrypted at rest, field by fieldAES-256-GCM
- Database backups encrypted, kept 30 daysBackups
- Report a vulnerability[email protected]
Questions
Good to know.
An AI workspace for thinking, writing, searching and building. It keeps context in memory and vaults, searches the web with links to the pages it used, and hands back documents, code and web pages as artifacts you can revise.
Coming soon
What we are building next.
Cruxy Cowork, a coworker on your desktop. Cruxy Bench, browser chat with Cruxy Code. Cruxy Guard, automatic pull request review. And editor plugins for Cruxy Code.
Hear when each one ships
Start working with Cruxy.
Free on the web. No card required. Bring a task and see what it hands back.