Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Implementation for OAgents: An Empirical Study of Building Effective Agents
| Date | Stars |
|---|---|
| 2026-07-31 | 328 |
| 2026-08-06 | 328 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<h2>An Empirical Study of Building Effective Agents, OPPO PersonalAI Lab.</h2>
</div>
<div align="center">
<a href='https://arxiv.org/pdf/2506.15741'><img src='https://img.shields.io/badge/Paper OAgents-arXiv-d63031?logo=arxiv&logoColor=white'></a>
<a href='https://arxiv.org/pdf/2506.12928'><img src='https://img.shields.io/badge/Paper TTS-arXiv-d63031?logo=arxiv&logoColor=white'></a>
<a href='https://arxiv.org/abs/2508.02694'><img src='https://img.shields.io/badge/Paper Efficient Agents-arXiv-d63031?logo=arxiv&logoColor=white'></a>
<a href='https://www.python.org/downloads/release/python-31210/'><img src='https://img.shields.io/badge/Python-3.12-green'></a>
<a href='https://github.com/OPPO-PersonalAI/OAgents/blob/main/LICENSE'><img src='https://img.shields.io/badge/License-Apache%202.0-blue'></a>
</div>
This is the official repository for our papers
- 🤖 **[OAgents](https://arxiv.org/abs/2506.15741): An Empirical Study of Building Effective Agents**
- 🚀 **[Scaling](https://arxiv.org/abs/2506.12928) Test-time Compute for LLM Agents**
- 💸 **[Efficient Agents](https://arxiv.org/abs/2508.02694): Building Effective Agents While Reducing Cost**
<div align="center">
<img src="./assets/oagents.png" width="80%" height="auto" />
</div>
---
## News 📰
**[2025.08.06]** Released the [efficient agents](https://github.com/OPPO-PersonalAI/OAgents/tree/main/Efficient_Agents) codebase.
**[2025.06.23]** Released the initial codebase.
---
## Introduction 📚
Agentic AI has gained significant attention, but current research lacks standardization, making fair comparisons difficult. In this work, we conduct a systematic study on key design choices in agent frameworks using the GAIA and BrowseComp benchmarks. We introduce a robust evaluation protocol to ensure reproducibility and identify crucial components for effective agents. Based on our findings, we develop and open-source OAgents, a modular foundation agent framework that achieves state-of-the-art performance among open-source projects, promoting future research in Agentic AI.
---
## Setup 🔍
To get started, follow the steps below:
### Install dependencies
Run the following command to install the required dependencies from the `requirements.txt` file:
```bash
pip install -r ./oagents/example/oagents_deep_research/requirements.txt
```
### Install `oagents`
```bash
cd oagents
pip install -e ./.[dev]
```
### Configuration `.env` File
We provide a template file named `.env_template` for your convenience. You can copy this file and rename it to `.env`, then fill in your actual API keys and service addresses. For example:
```bash
cp .env_template .env
```
Then edit the `.env` file with your credentials.
#### 🔍 Search and Crawling Services
The agent uses the following external services for web search and content crawling. Please configure the corresponding API keys:
- **Search Engine: SerpApi**
Used for performing web searches. Get your API key from [SerpApi](https://serpapi.com/) and set it as:
```
SERP_API_KEY=<your-serp-api-key>
```
- **Web Crawler: Jina AI Reader**
Used for accessing and parsing web content. Sign up at [Jina AI](https://jina.ai/) to obtain an API key and set it as:
```
JINA_API_KEY=<your-jina-api-key>
```
---
## Evaluation of OAgents on GAIA 📕
### Main Usage
#### Step 1: Prepare the Data
Download the GAIA dataset and place it under the following directory:
```
./oagents/example/oagents_deep_research/data/gaia
```
The expected directory structure is as follows:
```
├── data
│ ├── gaia
│ ├── test
│ └── validation
```
#### Step 2: Test run on GAIA
You're now all set to run on GAIA! First, go to main part of GAIA evaluation.
```bash
cd ./oagents/example/oagents_deep_research
```
Simply execute the run_gaia.py script, like so:
```bash
python run_gaia.py --model_id gpt-4.1 --model_id_search gpt-4.1 --run_name gpt-4.1-gaia
```
If you'd like to use different questions or dataseExcerpt of 9,321 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:7a130ffee1bc4f10, llm:Repository description: 'Implementation for OAgents: An Empirical Study of Building Effective Agents' (Python).
matched fp:7a130ffee1bc4f10, llm:Repository description: 'Implementation for OAgents: An Empirical Study of Building Effective Agents' (Python).
matched fp:7a130ffee1bc4f10, llm:Repository description: 'Implementation for OAgents: An Empirical Study of Building Effective Agents' (Python).