Skip to main content
AIDiveForge AIDiveForge

Elysia

FreemiumOpen SourceAPISelf-HostedAgentic

Weaviate's agentic RAG framework that auto-routes queries to the right data clusters and models with zero manual configuration.

$45/mo · Free tier: 1 cluster per user, 100,000 objects, 1 GB memory, 10 GB disk, 1 collection up to 3 tenants, 2,000 embeddings req/day, 1,000 Query Agent req/mo · Checked Oct 19, 2026

Similar tools

Get This Tool

License: BSD-3-Clause Any use incl. commercial
Local-run terms: Users can run Elysia locally with a locally running instance of Weaviate or can specify a unique REST and GRPC endpoint for custom Weaviate connections. The entire project is open source and designed with customization in mind. BSD-3-Clause license permits commercial use with proper attribution.

Screenshots 2

Summary

Elysia wraps Weaviate's vector database with an AI agent layer that decides which tools and data sources to use based on context—eliminating manual prompt engineering for multi-cluster or multi-provider setups. It addresses a real friction point: teams managing multiple data environments or LLM providers typically hand-code routing logic or maintain separate pipelines. You get seven display formats (tables, cards, tickets, conversations) and cost nothing to try. The catch is substantial: it's beta software with known issues, relies entirely on a live Weaviate cluster connection, and Weaviate doesn't claim production-grade maintenance for it yet.

Bottom line: *Use this if you're already invested in Weaviate and tired of manual routing; skip it if you need stability or don't have a cluster running.*

Hosted & API Pricing

The model is free to self-host. These are the creator's hosted/API options.

Weaviate Embeddings - SNOWFLAKE ARCTIC-EMBED-M-V1.5

via Weaviate Cloud
$0.03per 1M tokens

Access embedding models hosted in Weaviate Cloud. Simple, pay-as-you-go, GPU-powered.

  • SNOWFLAKE ARCTIC-EMBED-M-V1.5 model

Weaviate Embeddings - SNOWFLAKE ARCTIC-EMBED-M-V2.0

via Weaviate Cloud
$0.04per 1M tokens

Access embedding models hosted in Weaviate Cloud. Simple, pay-as-you-go, GPU-powered.

  • SNOWFLAKE ARCTIC-EMBED-M-V2.0 model

Weaviate Embeddings - MODERNVBERT

via Weaviate Cloud
$0.07per 1M tokens

Access embedding models hosted in Weaviate Cloud. Simple, pay-as-you-go, GPU-powered.

  • MODERNVBERT model

Weaviate Query Agent

via Weaviate Cloud
$30per organization monthly plan

Turn natural-language questions into precise Weaviate database operations. Free to try u2014 1,000 requests / month. $30 / organization u00b7 monthly plan includes 4,000 requests.

  • Free to try u2014 1,000 requests / month
  • 4,000 requests included with $30/mo plan
  • Unlimited additional requests, usage-based

Pricing may have changed since last verified. Check the official site for current plans.

Pricing Plans

Usage-BasedLast verified 2 weeks ago
Price
$45/mo
Free Tier
1 cluster per user, 100,000 objects, 1 GB memory, 10 GB disk, 1 collection up to 3 tenants, 2,000 embeddings req/day, 1,000 Query Agent req/mo

Free

Free

A fully managed AI Database to explore Weaviate features. Easiest way to get started, always free.

  • Always free u2014 1 cluster per user, upgrade to paid anytime
  • 100,000 objects u00b7 1 GB memory u00b7 10 GB disk
  • 1 collection, up to 3 tenants
  • Embeddings (2,000 req/day) + Query Agent (1,000 req/mo)
  • Basic Support

Flex

$45per month

Pay-as-you-go zero-commitment entry point to experiment and ship quickly. Ideal for prototypes, pilots, small use cases.

  • Pay-as-you-go, monthly, no commitment
  • Shared cloud cluster with full core DB toolkit + replication
  • Baseline security with RBAC
  • Highly available clusters u2014 99.5% uptime
  • Query Agent free tier + usage-based; Embeddings usage-based
  • Standard support u2014 next-business-day Sev 1

Premium

Custom

Prepaid contract for teams scaling AI in production who need predictable pricing and enhanced reliability.

  • Prepaid contract with predictable spend
  • Choice of shared or dedicated deployment
  • Trusted reliability u2014 up to 99.95% uptime
  • Global coverage on AWS, GCP & Azure
  • Query Agent free tier + usage-based; Embeddings usage-based
  • Enterprise support u2014 as fast as 1-hour Sev 1 + dedicated Technical Account Team

View full pricing on weaviate.io →

Pricing may have changed since last verified. Check the official site for current plans.

Find your fit

Before you choose Elysia

More options in Agent Frameworks. Compare pricing, platforms, and features side by side.

Browse Agent Frameworks

Pros

  • Decision agent dynamically decides which tools to use based on environment and context
  • Seven different display formats including tables, product cards, tickets, conversations, documents, and charts
  • Everything comes in a single pip-installable package
  • Entire project is open source and designed with customization in mind
  • Flexible model integration with support for multiple LLM providers and local models

Cons

  • May not be maintained with the same rigor as production software
  • Still in beta phase with some known issues
  • Requires connection to Weaviate cluster for full functionality

About

Platforms
Python (pip-installable), Web application (FastAPI backend, Next.js frontend)
Languages
Python
API Available
Yes
Self-Hosted
Yes
Last Updated
May 1, 2026

Best For

Who it's for

  • Bringing agentic AI to your data
  • Users who want to create multiple configs that allow switching between data clusters or model providers easily
  • Teams needing intelligent data search with context awareness
  • Applications requiring dynamic data display based on content and context, with support for tables, product cards, tickets, conversations, documents, and charts

What it does well

  • Building e-commerce chatbots
  • Internal company knowledge expert systems
  • Agentic retrieval-augmented generation (RAG) applications
  • Agentic RAG ready to go
  • Custom tool building and agentic workflows

Integrations

OpenAICohereHuggingFaceOpenRouterWeaviatelocal models via OllamaLiteLLM-supported providers

Compare Elysia

Frequently Asked Questions

Is Elysia free?
Elysia offers a free option alongside paid upgrades. Pricing: $45/mo. Check the current allowances and terms before choosing a plan.
Is Elysia open source?
Yes. Elysia is open source — the source repository is at https://github.com/weaviate/elysia.
Does Elysia have an API?
Yes. Elysia exposes a developer API. See the official documentation at https://weaviate.io for details.
Can I self-host Elysia?
Yes. Elysia supports self-hosting on your own infrastructure.
When was Elysia released?
Elysia was first released in 2025.
What platforms does Elysia support?
Elysia is available on: Python (pip-installable), Web application (FastAPI backend, Next.js frontend).

Weaviate's agentic RAG framework that auto-routes queries to the right data clusters and models with zero manual configuration.

Elysia wraps Weaviate's vector database with an AI agent layer that decides which tools and data sources to use based on context—eliminating manual prompt engineering for multi-cluster or multi-provider setups. It addresses a real friction point: teams managing multiple data environments or LLM providers typically hand-code routing logic or maintain separate pipelines. You get seven display formats (tables, cards, tickets, conversations) and cost nothing to try. The catch is substantial: it's beta software with known issues, relies entirely on a live Weaviate cluster connection, and Weaviate doesn't claim production-grade maintenance for it yet.

*Use this if you're already invested in Weaviate and tired of manual routing; skip it if you need stability or don't have a cluster running.*

Share This Tool

Compare This Tool
Contribute