ROMA

<div align="center"> <img src="./assets/sentient-logo-new-M.png" alt="alt text" width="60%"/> <h1>ROMA: Recursive Open Meta-Agents</h1> </div> <p align="center"> <strong>Building hierarchical high-performance multi-agent systems made easy! (Beta) </strong> </p> <p align="center"> <a href="https://trendshift.io/repositories/14848" target="_blank"><img src="https://trendshift.io/api/badge/repositories/14848" alt="sentient-agi%2FROMA | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a> </p> <p align="center"> <a href="https://sentient.xyz/" target="_blank" style="margin: 2px;"> <img alt="Homepage" src="https://img.shields.io/badge/Sentient-Homepage-%23EAEAEA?logo=data%3Aimage%2Fsvg%2Bxml%3Bbase64%2CPHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHdpZHRoPSIzNDEuMzMzIiBoZWlnaHQ9IjM0MS4zMzMiIHZlcnNpb249IjEuMCIgdmlld0JveD0iMCAwIDI1NiAyNTYiPjxwYXRoIGQ9Ik0xMzIuNSAyOC40Yy0xLjUgMi4yLTEuMiAzLjkgNC45IDI3LjIgMy41IDEzLjcgOC41IDMzIDExLjEgNDIuOSAyLjYgOS45IDUuMyAxOC42IDYgMTkuNCAzLjIgMy4zIDExLjctLjggMTMuMS02LjQuNS0xLjktMTcuMS03Mi0xOS43LTc4LjYtMS4yLTMtNy41LTYuOS0xMS4zLTYuOS0xLjYgMC0zLjEuOS00LjEgMi40ek0xMTAgMzBjLTEuMSAxLjEtMiAzLjEtMiA0LjVzLjkgMy40IDIgNC41IDMuMSAyIDQuNSAyIDMuNC0uOSA0LjUtMiAyLTMuMSAyLTQuNS0uOS0zLjQtMi00LjUtMy4xLTItNC41LTItMy40LjktNC41IDJ6TTgxLjUgNDYuMWMtMi4yIDEuMi00LjYgMi44LTUuMiAzLjctMS44IDIuMy0xLjYgNS42LjUgNy40IDEuMyAxLjIgMzIuMSAxMC4yIDQ1LjQgMTMuMyAzIC44IDYuOC0yLjIgNi44LTUuMyAwLTMuNi0yLjItOS4yLTMuOS0xMC4xQzEyMy41IDU0LjIgODcuMiA0NCA4NiA0NGMtLjMuMS0yLjMgMS00LjUgMi4xek0xNjUgNDZjLTEuMSAxLjEtMiAyLjUtMiAzLjIgMCAyLjggMTEuMyA0NC41IDEyLjYgNDYuNS45IDEuNSAyLjQgMi4zIDQuMiAyLjMgMy44IDAgOS4yLTUuNiA5LjItOS40IDAtMS41LTIuMS0xMC45LTQuNy0yMC44bC00LjctMTguMS00LjUtMi44Yy01LjMtMy40LTcuNC0zLjYtMTAuMS0uOXpNNDguNyA2NS4xYy03LjcgNC4xLTYuOSAxMC43IDEuNSAxMyAyLjQuNiAyMS40IDUuOCA0Mi4yIDExLjYgMjIuOCA2LjIgMzguOSAxMC4yIDQwLjMgOS44IDMuNS0uOCA0LjYtMy44IDMuMi04LjgtMS41LTUuNy0yLjMtNi41LTguMy04LjJDOTQuMiA3My4xIDU2LjYgNjMgNTQuOCA2M2MtMS4zLjEtNCAxLTYuMSAyLjF6TTE5OC4yIDY0LjdjLTMuMSAyLjgtMy41IDUuNi0xLjEgOC42IDQgNS4xIDEwLjkgMi41IDEwLjktNC4xIDAtNS4zLTUuOC03LjktOS44LTQuNXpNMTgxLjggMTEzLjFjLTI3IDI2LjQtMzEuOCAzMS41LTMxLjggMzMuOSAwIDEuNi43IDMuNSAxLjUgNC40IDEuNyAxLjcgNy4xIDMgMTAuMiAyLjQgMi4xLS4zIDU2LjktNTMuNCA1OS01Ny4xIDEuNy0zLjEgMS42LTkuOC0uMy0xMi41LTMuNi01LjEtNC45LTQuMi0zOC42IDI4Ljl6TTM2LjYgODguMWMtNSA0LTIuNCAxMC45IDQuMiAxMC45IDMuMyAwIDYuMi0yLjkgNi4yLTYuMyAwLTIuMS00LjMtNi43LTYuMy02LjctLjggMC0yLjYuOS00LjEgMi4xek02My40IDk0LjVjLTEuNi43LTguOSA3LjMtMTYuMSAxNC43TDM0IDEyMi43djUuNmMwIDYuMyAxLjYgOC43IDUuOSA4LjcgMi4xIDAgNi0zLjQgMTkuOS0xNy4zIDkuNS05LjUgMTcuMi0xOCAxNy4yLTE4LjkgMC00LjctOC40LTguNi0xMy42LTYuM3pNNjIuOSAxMzAuNiAzNCAxNTkuNXY1LjZjMCA2LjIgMS44IDguOSA2IDguOSAzLjIgMCA2Ni02Mi40IDY2LTY1LjYgMC0zLjMtMy41LTUuNi05LjEtNi4ybC01LS41LTI5IDI4Ljl6TTE5Ni4zIDEzNS4yYy05IDktMTYuNiAxNy4zLTE2LjkgMTguNS0xLjMgNS4xIDIuNiA4LjMgMTAgOC4zIDIuOCAwIDUuMi0yIDE3LjktMTQuOCAxNC41LTE0LjcgMTQuNy0xNC45IDE0LjctMTkuMyAwLTUuOC0yLjItOC45LTYuMi04LjktMi42IDAtNS40IDIuMy0xOS41IDE2LjJ6TTk2IDEzNi44Yy0yLjkuOS04IDYuNi04IDkgMCAxLjMgMi45IDEzLjQgNi40IDI3IDMuNiAxMy42IDcuOSAzMC4zIDkuNyAzNy4yIDEuNyA2LjkgMy42IDEzLjMgNC4xIDE0LjIuNSAxIDIuNiAyLjcgNC44IDMuOCA2LjggMy41IDExIDIuMyAxMS0zLjIgMC0zLTIwLjYtODMuMS0yMi4xLTg1LjktLjktMS45LTMuNi0yLjgtNS45LTIuMXpNMTIwLjUgMTU4LjRjLTEuOSAyLjktMS4yIDguNSAxLjQgMTEuNiAxLjEgMS40IDEyLjEgNC45IDM5LjYgMTIuNSAyMC45IDUuOCAzOC44IDEwLjUgMzkuOCAxMC41czMuNi0xIDUuNy0yLjJjOC4xLTQuNyA3LjEtMTAuNi0yLjMtMTMuMi0yOC4yLTguMS03OC41LTIxLjYtODAuMy0yMS42LTEuNCAwLTMgMS0zLjkgMi40ek0yMTAuNyAxNTguOGMtMS44IDEuOS0yLjIgNS45LS45IDcuOCAxLjUgMi4zIDUgMy40IDcuNiAyLjQgNi40LTIuNCA1LjMtMTEuMi0xLjUtMTEuOC0yLjQtLjItNCAuMy01LjIgMS42ek02OS42IDE2MmMtMiAyLjItMy42IDQuMy0zLjYgNC44LjEgMi42IDEwLjEgMzguNiAxMS4xIDM5LjkgMi4yIDIuNiA5IDUuNSAxMS41IDQuOSA1LTEuMyA0LjktMy0xLjUtMjcuNy0zLjMtMTIuNy02LjUtMjMuNy03LjItMjQuNS0yLjItMi43LTYuNC0xLjctMTAuMyAyLjZ6TTQ5LjYgMTgxLjVjLTIuNCAyLjUtMi45IDUuNC0xLjIgOEM1MiAxOTUgNjAgMTkzIDYwIDE4Ni42YzAtMS45LS44LTQtMS44LTQuOS0yLjMtMi4xLTYuNi0yLjItOC42LS4yek0xMjguNSAxODdjLTIuMyAyLjUtMS4zIDEwLjMgMS42IDEyLjggMi4yIDEuOSAzNC44IDExLjIgMzkuNCAxMS4yIDMuNiAwIDEwLjEtNC4xIDExLTcgLjYtMS45LTEuNy03LTMuMS03LS4yIDAtMTAuMy0yLjctMjIuMy02cy0yMi41LTYtMjMuMy02Yy0uOCAwLTIuMy45LTMuMyAyek0xMzYuNyAyMTYuOGMtMy40IDMuOC0xLjUgOS41IDMuNSAxMC43IDMuOSAxIDguMy0zLjQgNy4zLTcuMy0xLjItNS4xLTcuNS03LjEtMTAuOC0zLjR6Ii8%2BPC9zdmc%2B&link=https%3A%2F%2Fhuggingface.co%2FSentientagi" style="display: inline-block; vertical-align: middle;"/> </a> <a href="https://github.com/sentient-agi" target="_blank" style="margin: 2px;"> <img alt="GitHub" src="https://img.shields.io/badge/Github-sentient_agi-181717?logo=github" style="display: inline-block; vertical-align: middle;"/> </a> <a href="https://huggingface.co/Sentientagi" target="_blank" style="margin: 2px;"> <img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-SentientAGI-ffc107?color=ffc107&logoColor=white" style="display: inline-block; vertical-align: middle;"/> </a> </div> <div align="center" style="line-height: 1;"> <a href="https://discord.gg/sentientfoundation" target="_blank" style="margin: 2px;"> <img alt="Discord" src="https://img.shields.io/badge/Discord-SentientAGI-7289da?logo=discord&logoColor=white&color=7289da" style="display: inline-block; vertical-align: middle;"/> </a> <a href="https://x.com/SentientAGI" target="_blank" style="margin: 2px;"> <img alt="Twitter Follow" src="https://img.shields.io/badge/-SentientAGI-grey?logo=x&link=https%3A%2F%2Fx.com%2FSentientAGI%2F" style="display: inline-block; vertical-align: middle;"/> </a> </p> <p align="center"> <a href="https://www.sentient.xyz/blog/recursive-open-meta-agent">Technical Blog</a> • <a href="https://arxiv.org/abs/2602.01848">Paper</a> • <a href="https://www.sentient.xyz/">Build Agents for $$$</a> </p> </div>

📑 Table of Contents

• 🧠 Conceptual Overview
• 📦 Installation & Setup
• ⚡ Quickstart: End-to-End Workflow
• ⚙️ Configuration & Storage
• 🧰 Toolkits
• 🌐 REST API & CLI
• 🏗️ Core Building Block: BaseModule
• 📚 Module Reference
  • ⚛️ Atomizer
  • 📋 Planner
  • ⚙️ Executor
  • 🔀 Aggregator
  • ✅ Verifier
• 🎯 Advanced Patterns
• 🧪 Testing
• 💡 Troubleshooting & Tips
• 📖 Glossary

---

🎯 What is ROMA?

<div align="center"> <img src="./assets/roma_run.gif" alt="alt text" width="80%"/> </div> <br>

ROMA is a meta-agent framework that uses recursive hierarchical structures to solve complex problems. By breaking down tasks into parallelizable components, ROMA enables agents to tackle sophisticated reasoning challenges while maintaining transparency that makes context-engineering and iteration straightforward. The framework offers parallel problem solving where agents work simultaneously on different parts of complex tasks, transparent development with a clear structure for easy debugging, and proven performance demonstrated through our search agent's strong benchmark results. We've shown the framework's effectiveness, but this is just the beginning. As an open-source and extensible platform, ROMA is designed for community-driven development, allowing you to build and customize agents for your specific needs while benefiting from the collective improvements of the community.

🏗️ How It Works

ROMA framework processes tasks through a recursive plan–execute loop:

def solve(task):
    if is_atomic(task):                 # Step 1: Atomizer
        return execute(task)            # Step 2: Executor
    else:
        subtasks = plan(task)           # Step 2: Planner
        results = []
        for subtask in subtasks:
            results.append(solve(subtask))  # Recursive call
        return aggregate(results)       # Step 3: Aggregator

# Entry point:
answer = solve(initial_request)

1. Atomizer – Decides whether a request is atomic (directly executable) or requires planning.
2. Planner – If planning is needed, the task is broken into smaller subtasks. Each subtask is fed back into the Atomizer, making the process recursive.
3. Executors – Handle atomic tasks. Executors can be LLMs, APIs, or even other agents — as long as they implement an agent.execute() interface.
4. Aggregator – Collects and integrates results from subtasks. Importantly, the Aggregator produces the answer to the original parent task, not just raw child outputs.

📐 Information Flow

• Top-down: Tasks are decomposed into subtasks recursively.
• Bottom-up: Subtask results are aggregated upwards into solutions for parent tasks.
• Left-to-right: If a subtask depends on the output of a previous one, it waits until that subtask completes before execution.

This structure makes the system flexible, recursive, and dependency-aware — capable of decomposing complex problems into smaller steps while ensuring results are integrated coherently.

<details> <summary>Click to view the system flow diagram</summary>

flowchart TB
    A[Your Request] --> B{Atomizer}
    B -->|Plan Needed| C[Planner]
    B -->|Atomic Task| D[Executor]

    %% Planner spawns subtasks
    C --> E[Subtasks]
    E --> G[Aggregator]

    %% Recursion
    E -.-> B  

    %% Execution + Aggregation
    D --> F[Final Result]
    G --> F

    style A fill:#e1f5fe
    style F fill:#c8e6c9
    style B fill:#fff3e0
    style C fill:#ffe0b2
    style D fill:#d1c4e9
    style G fill:#c5cae9

</details><br>

🚀 Quick Start

Fastest Way: Minimal Installation (Recommended for Evaluation)

Get started in under 30 seconds with no infrastructure required:

# Install with uv (10-100x