automation

RD-Agent: Automate R&D

Boost productivity with RD-Agent. Ideal for founders in AI and data-driven industries.
14,402 stars1,868 forksPythonGuide quality 8/10Updated 9/1/2026100% free · open source
What it does

RD-Agent is a tool that automates repetitive tasks and boosts productivity for founders in AI and data-driven industries by integrating with their development workflow.

When to use it
  • When you need to automate data processing pipelines
  • When you want to integrate AI models into your application
  • When you need to automate testing and deployment of your AI-driven products
Ready-to-paste prompt
rd-agent run --config config.json --task my_data_processing_task
Heads up: RD-Agent requires Python 3.7 or later to be installed, and the `pyyaml` library must be installed separately with `pip install pyyaml`
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/rd-agent && curl -fsSL https://workflowstacks.com/api/skills/rd-agent/claude-skill -o ~/.claude/skills/rd-agent/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How RD-Agent: Automate R&D works
Codeflow
Free to inspect

RD-Agent: Automate R&D is a very large project (~77k lines across 588 code files, plus 37 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size
Very large codebase
~77k lines · 588 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Python
Needs API keys (.env)
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    pyproject.toml
    Dependencies and the commands it exposes
  3. 3
    .env.example
    The API keys and settings you must provide
  4. 4
    rdagent/app/cli.py
    Inside rdagent/ — the main logic begins here
What's in each folder
rdagent/Core code — the actual logic694 files
web/Frontend / UI110 files
docs/Documentation35 files
requirements/Folder5 files
constraints/Folder2 files
test/Tests — proof it works39 files
.github/CI / automation (GitHub Actions)11 files
.devcontainer/Editor / agent settings4 files
READMEHas testsDocumentedCI checksMIT licenseUpdated this month
Quick Actions
Details
Creator
microsoft
Language
Python
Category
automation
Published
4/3/2024

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.