# agentuniverse-ai/agentUniverse

agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.

Repository: https://github.com/agentuniverse-ai/agentUniverse
Canonical: https://ross.abutalabs.com/products/agentuniverse
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, ai, llm, multi-agent, python, awesome, awesome-list, ai-agents, autonomous
Last push: 2026-07-28T08:18:07+00:00

## Health v2 (maintenance only)
Score: 70/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 94, release rhythm 45, longevity 61
- inputs: {"age_days": 862, "days_push": 36, "days_rel": 289, "gap_med": 46.5, "n_releases_24m": 7}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2343, forks 423 (observed 2026-08-28T04:06:39.484604+00:00)

## What it is
agentUniverse is a Python-based multi-agent framework built on large language models, providing extensible components for building individual agents and multi-agent collaboration patterns like PEER and DOE. It originates from AntGroup's real-world financial business practices and focuses on integrating domain expertise into agent workflows.

## Use cases
- build multi-agent applications with llms
- orchestrate agents that plan, execute, express and review tasks
- generate financial reports with data-intensive agent collaboration
- integrate domain expertise into ai agent workflows
- create industry analysis agents
- connect different llm vendors via simple configuration

## When to choose
- you need structured multi-agent collaboration patterns rather than a single agent
- you want battle-tested patterns from real financial business scenarios
- you need to plug in various llm vendors with minimal configuration
- you want to embed domain expert knowledge into agent pipelines

## When to avoid
- you need a lightweight single-agent chatbot without orchestration
- you prefer frameworks with larger ecosystems like langchain or autogen
- you need non-python environments
- you require fully autonomous agents without predefined collaboration patterns

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, prompt-engineering, chatbot
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cross-platform
- tags: multi-agent, llm, collaboration-patterns, python-framework, antgroup, ai-agents

## Member repositories
- agentuniverse-ai/agentUniverse (main) score 70

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:39.484604+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 2026-08-30T02:37:13.944829+00:00, confidence not recorded.
  - readme: https://github.com/agentuniverse-ai/agentUniverse (fetched 2026-08-28T04:06:39.484604+00:00, sha 3d6cf8611f8b)
  - registry_pypi: https://pypi.org/pypi/agentuniverse/json (fetched 2026-08-29T10:17:42.418584+00:00, sha 22ef24ec3a1b)
- Data as of 2026-08-30T08:39:29.467469+00:00.