# sentient-agi/ROMA

Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.

Repository: https://github.com/sentient-agi/ROMA
Canonical: https://ross.abutalabs.com/products/roma
Language: Python
License Family: other
Last push: 2026-02-16T21:30:31+00:00

## Health v2 (maintenance only)
Score: 51/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 67, release rhythm 41, longevity 34
- inputs: {"age_days": 478, "days_push": 198, "days_rel": 316, "gap_med": 47, "n_releases_24m": 2}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5174, forks 777 (observed 2026-08-28T04:09:11.710804+00:00)

## What it is
ROMA (Recursive Open Meta-Agent) is a Python meta-agent framework for building hierarchical, high-performance multi-agent systems. It enables recursive decomposition of tasks into subtasks handled by specialized agents.

## Use cases
- build multi-agent systems in python
- recursively decompose complex tasks across agents
- create hierarchical agent workflows
- orchestrate llm agents for research tasks
- build a meta-agent that spawns sub-agents

## When to choose
- you want a framework for hierarchical multi-agent orchestration
- you need recursive task decomposition with specialized sub-agents
- you prefer Python and want a popular, actively developed agent framework

## When to avoid
- you need a production-hardened framework - it is a beta release
- you need a permissively licensed dependency - no license is specified
- you only need a simple single-agent chatbot

## Facets
- artifact type: framework
- maturity: experimental
- function: agent-framework, llm-inference, workflow-automation
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cross-platform
- tags: multi-agent, hierarchical-agents, meta-agent, recursive-task-decomposition, beta, ai-agents

## Member repositories
- sentient-agi/ROMA (main) score 51

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:11.710804+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 2026-08-29T18:01:50.485875+00:00, confidence not recorded.
  - readme: https://github.com/sentient-agi/ROMA (fetched 2026-08-28T04:09:11.710804+00:00, sha 28285642b28a)
- Data as of 2026-08-30T08:39:29.467469+00:00.