airas 0.0.9

Add your description here

AIRAS

Quick Start

uv sync [--dev] [--extra mcp]

• --dev to install development packages
• --extra mcp to install MCP-related packages

MCP

Client setting in Claude Desktop

{
    "mcpServers": {
        "researchgraph": {
            "type": "stdio",
            "command": "uv",
            "env": {
                "UV_ENV_FILE": "/PATH/TO/REPOSITORY/.env"
            },
            "args": [
                "--directory",
                "/PATH/TO/REPOSITORY",
                "run",
                "src/researchgraph/mcp_server/mcp_server.py"
            ]
        }
    }
}

or Visual Studio Code

  "mcp": {
    "servers": {
      "researchgraph": {
        "type": "stdio",
        "command": "uv",
        "env": {
            "UV_ENV_FILE": "/PATH/TO/REPOSITORY/.env"
        },
        "args": [
            "--directory",
            "/PATH/TO/REPOSITORY",
            "run",
            "src/researchgraph/mcp_server/mcp_server.py"
        ]
      }
    }
  }

Roadmap

• Enhanced automation for end-to-end ML research
• Improved integration with external APIs (OpenAI, Devin, Firecrawl, GitHub)
• User-friendly web interface
• Advanced experiment tracking and visualization
• Community plugin system

Contact

We are exploring best practices for human-AI collaboration in automated AI research. Together, we're investigating how new research workflows—powered by both human insight and AI agents—can accelerate discovery, improve reproducibility, and give organizations a competitive edge in the age of autonomous research.

If you are interested in this topic, please feel free to contact us at [e-mail].

About AutoRes

This OSS is developed as part of the AutoRes project.

Citation

If you use AIRAS in your research, please cite as follows:

@software{airas2025,
  author = {Toma Tanaka},
  title = {AIRAS},
  year = {2025},
  publisher = {GitHub},
  url = {https://github.com/auto-res/airas}
}