Memory that works across every AI model.
Portable, model-neutral memory that keeps user context consistent across chats, apps, and LLMs — no lock-in, no hacks.
Works with your favorite models
See Sovant in Action
Watch how Sovant captures, organizes, and recalls memory seamlessly across different AI models and apps.
What Developers Get
Everything you need to capture, inspect, and recall context across models.
Dashboard
Monitor, manage and track your project's memory activity in one place.
Demo Chat
Conversations that don't forget. Context persistence across models.
Memory Explorer
Inspect, search and refine memories for precise recall.
How It Works
Three simple steps to give your AI portable, cross-model memory.
Install SDK
Drop in the TypeScript or Python SDK — no infra or vendor lock-in.
Capture memories
Persist facts, events, and conversations with one call — Sovant keeps them across sessions and providers.
Query memory
Retrieve the right context in any app, with any LLM — portable and model-neutral.
Built for Developers
A powerful API that makes AI memory portable and persistent.
Universal Compatibility
Works with any model or application
Semantic Search
Instantly retrieve relevant context
Type-Safe SDKs
Full TypeScript & Python support with auto-completion
npm i @sovant/sdk
// index.ts
import { Sovant } from '@sovant/sdk';
const client = new Sovant({
apiKey: process.env.NEXT_PUBLIC_SOVANT_API_KEY!,
baseUrl: 'https://sovant.ai',
});
// Create a memory
await client.memory.create({
content: 'User prefers dark mode UI',
type: 'preference',
tags: ['ui', 'theme'],
});
// Semantic search
const results = await client.memory.search({
query: 'user theme preference',
limit: 5,
});
console.log(results);Simple, Transparent Pricing
Start free, scale as you grow
Free
Perfect for testing and small projects
- 1,000 API requests per month
- 7-day retention
- Basic memory storage
Pro
For production applications
- Unlimited API requests
- Advanced memory indexing
- Priority support
- Custom retention policies
- Analytics dashboard
- 99.9% uptime SLA
Building in Public
We're actively developing Sovant with your feedback. Here's what's coming next.
Product Roadmap
Beta
CurrentCore memory API with semantic search
Smarter grouping
Automatic context clustering and tagging
More LLMs
Extended model compatibility
Ecosystem
Integrations, plugins, and developer tools
Community & Feedback
Join us on GitHub
Contribute, report issues, or follow along with Sovant's progress building portable, cross-model memory.
Share your Feedback
Help shape Sovant during beta — tell us where portable memory helps (or hurts) in your workflow.