Ava Supernova
AvaSupernova
open-source AI that does the work

I remember what matters to you

I'm Ava — an open-source AI that actually does things: build software, write and design, teach you anything, run your training and meals, and handle the admin you keep putting off. I remember your work and how you like things across every session, I run wherever you do — editor, desktop, phone, terminal — and I'm free and private by default: on any model, or fully offline on your own machine.

free foreverlocal firstopen sourceno account needed
Ava Supernova · memory
What did we decide about the database?
Ava
You chose Drizzle over Prisma. I kept the reasoning:
From your decisions
Drizzle over Prisma — zero-overhead types, no codegen step
Decided three weeks ago. Still in context.
Ava Supernova
you › review this project and tell me what you think

Scout scanning 47 files across 6 directories

Architect analyzing patterns — Next.js 15, React 19, Tailwind 4

Verifier checking dependencies — 23 packages, 0 vulnerabilities

Challenger found 3 things worth addressing

Your project is well-structured. Here's what I'd improve...

One Ava, four doors

Same agent, same memory — wherever you work.

Live now

Health & training, in the same agent

An 860-dish global recipe library. 170 canonical exercises. Three skill levels per dish. Ava-authored technique guides and demo imagery. Free, like everything else.

Shipped

  • 860-dish recipe library across 71 regions
  • Three skill levels per dish — beginner, intermediate, expert
  • 170 canonical exercises across the core movement patterns — squat, hinge, push, pull, lunge, carry, core, plyometric, cardio, mobility, yoga, breathwork
  • Ava-authored technique guides, beginner cues, common mistakes, plus hero and demo imagery

On the way

  • Personalised meal plans that know your pantry, taste history, and training schedule
  • Adaptive workouts that respond to logged soreness, sleep, energy
  • Mobility and breathwork sequences for recovery
  • Companion intake — weekly logs feeding Ava’s memory so recommendations sharpen with you
Orchestrated Routing

Three fleets. One agent. Pick a strategy, Ava picks the model.

You talk. Ava classifies what you need and dispatches to the right specialist for each subtask. Three orchestration strategies, all available on every plan.

Maestro

Production-tuned

Tier-differentiated Qwen fleet. Qwen 3.7 Plus on the heavy slots, Qwen 3.5 Flash on chat and image-gen orchestration, Qwen 3.7 Plus on vision. Most cost-efficient, deepest production soak.

  • Qwen 3.7 Plus coordinator
  • 1M context, native MCP function calling
  • Terminal-Bench leader on real agent loops

Supernova

Polyglot ensemble

DeepSeek V4 Pro coordinates and dispatches: Qwen 3.7 Plus for Builder spawns, V4 Flash for chat + review, Qwen 3.7 Plus for vision. Frontier reasoning where it matters, flash-tier economics on the bulk.

  • DeepSeek V4 Pro coordinator
  • Best model for each role, not coordinator-only
  • Cost-aware: heavy where needed, light everywhere else

Aurora

European AI stack

Mistral-only, three-tier. Large 3 coordinator + heavy specialists, Medium 3.5 for Builder + vision + long-form, Small 4 for chat + intent gate. Open weights end-to-end. Never leaves European infrastructure.

  • Mistral Large 3 + Medium 3.5 + Small 4
  • GDPR-strict, AI Act compliant, sovereign by design
  • Open weights end-to-end — no closed model in the loop
Simple, honest pricing

Start free. Upgrade only when you outgrow it.

Every plan has every feature — all seven modes, every tool, memory, the creative studio, all of it. You only ever pay for more usage, never to unlock anything. And the people who subscribe are exactly what keeps Ava free and open for everyone who can't.

Free

$0/mo
300 credits / month

No card, no hoops. Enough to try every mode, model and tool.

Most popular

Pro

$19/mo
5,000 credits / month

For daily drivers — more monthly headroom, faster limits.

Ultra

$39/mo
10,000 credits / month

Heavy building, creative work and media generation.

Enterprise

$79/mo
20,000 credits / month

Teams and power users — highest limits, top priority.

Usage is measured in credits — a chat turn is about 2, an image about 12. Same simple meter on every model.

Or bring your own model keys — or run fully local on Ollama or LM Studio — and pay us nothing at all. Same agent, same memory, $0.

See full pricing
Bring Your Own Keys

All three modes. Every major model. Or your own local stack.

BYOK works with all three orchestrated modes — same agent, same memory, same personas, just running on keys you own. Or skip orchestration entirely and drive a single model directly.

Cloud models — your key

Bring a key for any major provider and run unmetered: Kimi K2.7 Code, Claude Opus 4.8 / Sonnet 5, DeepSeek V4, Mistral Large 3 / Medium 3.5, Zhipu GLM-5.2, Qwen 3.7 Plus, MiniMax M3.

Kimi K2.7 CodeOpus 4.8DeepSeek V4Mistral Large 3GLM-5.2Qwen 3.7 PlusMiniMax M3

Local + offline

Ollama, LM Studio, vLLM, or any OpenAI-compatible endpoint. Full agent — 60 tools, 24 personas, 5-layer memory — with $0 ongoing cost. The floor is free, not a free trial.

OllamaLM StudiovLLMOpenAI-compatible

BYOK keys live in your OS keychain. Never sent to our servers. Never logged.

See what she actually does

Not another chatbot with a file reader. A partner that plans, builds, teaches and creates — running a whole team of specialists on the hard parts.

> build a REST API for auth
Scout scanning codebase...
Architect designing approach...
Builder writing src/routes/auth.ts
Tests... 12/12 passed ✓
Code Mode

Build it with me

Describe what you want. Specialists plan, verify and challenge, then build — every change shown before it happens. Full autonomy when you want it.

> ?? teach me Italian from scratch
Building your curriculum...
Lesson 1: greetings and how Italian sounds
Ciao works for both hello and goodbye...
Ready for a quick quiz? 📝
Teach Mode

Learn anything. Free, forever.

Real curriculums, quizzes and progress tracking — code, a language, a whole new field. Five specialists teach you properly, not just dump facts.

> make a logo for a coffee brand
Design Studio → generating...
matte icon, your brand colours applied
rendered a 1080p promo clip + voiceover
saved to your library ✓
Design Studio

Make it — don't just describe it

Icons, images, video and voiceovers. Ava directs the tools and hands you finished assets, right in the app — no prompt-wrangling.

01

Free for everyone

300 credits every month — enough to try every model, mode, and tool. No credit card. No account required. Every mode works on the same credits — you only pay when you want more. Never for features.

02

Local first. Always.

Your data never leaves your machine unless you choose it. Memory, tasks, journal, settings — all local by default. Cloud sync is opt-in. No telemetry. No tracking. Your code is never used to train models.

03

Open source. Period.

Every line of code. The extension, the IDE, the companion, the CLI. Fork it, audit it, build on it. Trust is earned by transparency, not by marketing.

Seven modes. One mind.

Type a prefix. Change how she thinks.

>>
Code
Build
::
Plan
Architect
..
Chat
Talk
??
Teach
Learn
!!
Security
Protect
**
Brainstorm
Ideate
<<
Write
Author
Conductor
Orchestrates them
The moat

She forgets nothing

Five layers of intelligence. Not a chat log — a living understanding of who you are, how you think, and what you've decided.

01Extract

Key facts from every message. Real time.

02Reflect

Deep analysis at the end of meaningful sessions.

03Accumulate

Corrections and preferences compound over months.

04Analyse

Finds themes, contradictions, connections.

05Consolidate

Merges and sharpens. Never gets noisier.

We're not building another premium AI tool. We're building the one that makes the rest of them irrelevant.

Ready?

Install. Connect. She'll take it from there.

Open source. Local first. Community built. Always will be.