# weaviate/elysia

Python package and backend for the Elysia platform app.

Repository: https://github.com/weaviate/elysia
Canonical: https://ross.abutalabs.com/products/weaviate-elysia
Language: Python
License: BSD-3-Clause
License Family: permissive
Last push: 2026-02-06T15:37:07+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 66, release rhythm 55, longevity 36
- inputs: {"age_days": 506, "days_push": 208, "days_rel": 302, "gap_med": 4, "n_releases_24m": 8}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1923, forks 262 (observed 2026-08-28T04:05:55.347346+00:00)

## What it is
Elysia is an agentic platform and Python package from Weaviate where a decision agent dynamically chooses tools arranged in a decision tree, including pre-built tools for querying and aggregating data in Weaviate clusters. It ships as a pip-installable library with a built-in web app backend (started via `elysia start`) and supports custom tool definitions via a decorator API.

## Use cases
- query a weaviate collection with natural language
- build an agentic rag pipeline over my vector database
- create custom tools for an llm agent to call
- chat with my ecommerce data and aggregate results
- self-host an ai assistant frontend for data retrieval
- let an agent decide which retrieval tool to use dynamically

## When to choose
- your data lives in Weaviate and you want natural-language query/aggregation
- you want a decision-tree agent with custom Python tools
- you want a ready-made web app plus Python library for agentic retrieval

## When to avoid
- you need a production-stable, GA-quality system (it is in beta)
- your data is not in Weaviate and you don't want to write custom retrieval tools
- you need a lightweight single-call LLM client rather than an agent framework

## Facets
- artifact type: framework
- maturity: experimental
- function: agent-framework, rag, llm-inference, search-engine, web-framework, chatbot
- domain: artificial-intelligence, large-language-models, databases, web-development, developer-tools
- platform: python, self-hosted, cross-platform
- tags: decision-tree-agents, weaviate, vector-search, custom-tools, agentic-rag, beta, ai-agents, retrieval-augmented-generation, search, web-server, docker

## Member repositories
- weaviate/elysia (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:55.347346+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:09:39.308230+00:00, confidence not recorded.
  - readme: https://github.com/weaviate/elysia (fetched 2026-08-28T04:05:55.347346+00:00, sha c15fae424c18)
- Data as of 2026-08-30T08:39:29.467469+00:00.