RD-Agent Docker & Self-Hosted Deployment

GitHub

Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly...

15,249 stars Python Python 48 files ยท ~66,779 tokens #agent#ai#automation#data-mining#data-science#development#llm#research
1. Pull Image (DOCKERHUB) docker pull microsoft/RD-Agent:latest
2. Docker Run (1-Click Launch) docker run -d --name rd-agent --restart always microsoft/rd-agent:latest
3. Podman Run podman run -d --name rd-agent --restart always microsoft/rd-agent:latest
4. Skopeo Inspect (Zero-Pull Manifest) skopeo inspect docker://docker.io/microsoft/rd-agent:latest
5. ORAS Pull (OCI Artifact) oras pull microsoft/rd-agent:latest
rdagent/scenarios/rl/env/docker/miniwob/Dockerfile 
# MiniWoB ่ฎญ็ปƒ+่ฏ„ๆต‹้•œๅƒ
FROM autorl-bench/base:latest

WORKDIR /workspace

# ้ขๅค–ๅฎ‰่ฃ…๏ผšๆต่งˆๅ™จ + selenium + miniwob
RUN apt-get update && apt-get install -y --no-install-recommends \
    chromium chromium-driver \
    fonts-liberation \
    libnss3 libxss1 libasound2 libgbm1 \
    libx11-6 libxext6 libxrender1 libxtst6 \
    libgtk-3-0 \
    && rm -rf /var/lib/apt/lists/*

RUN pip install --no-cache-dir \
    miniwob \
    gymnasium \
    selenium

ENV CHROME_BIN=/usr/bin/chromium \
    CHROMEDRIVER_BIN=/usr/bin/chromedriver

CMD ["bash"]