Skip to content

Quickstart

  1. Install and start Runsight

    The fastest way is uvx:

    Terminal window
    uvx runsight

    Or use Docker:

    Terminal window
    docker run -p 8000:8000 -v "$(pwd)":/workspace ghcr.io/runsight-ai/runsight

    Don’t have uv? Install it first: curl -LsSf https://astral.sh/uv/install.sh | sh

    Open http://localhost:8000. The onboarding flow walks you through API key setup.

  2. Create a workflow file

    Create custom/workflows/my-first-flow.yaml:

    custom/workflows/my-first-flow.yaml
    version: "1.0"
    blocks:
    research:
    type: linear
    soul_ref: researcher
    write_summary:
    type: linear
    soul_ref: writer
    depends: research
    quality_review:
    type: gate
    soul_ref: reviewer
    eval_key: write_summary
    depends: write_summary
    workflow:
    name: Research & Review
    entry: research

    Three blocks: research calls an LLM, write_summary runs after it, and quality_review evaluates the summary.

  3. Define your souls

    Each soul_ref in the workflow points to a soul — the agent identity behind a block.

    Add a souls: section directly in the workflow file:

    custom/workflows/my-first-flow.yaml
    version: "1.0"
    souls:
    researcher:
    id: researcher
    role: Senior Researcher
    system_prompt: >
    You are an expert researcher. Given a topic, provide a concise,
    well-structured summary of the key findings, trends, and insights.
    provider: openai
    model_name: gpt-4.1-mini
    blocks:
    research:
    type: linear
    soul_ref: researcher
    workflow:
    name: My First Flow
    entry: research

    Extract the soul to its own file in custom/souls/. Any workflow can reference it by filename stem (soul_ref: researcher):

    custom/souls/researcher.yaml
    id: researcher
    role: Senior Researcher
    system_prompt: >
    You are an expert researcher. Given a topic, provide a concise,
    well-structured summary of the key findings, trends, and insights.
    provider: openai
    model_name: gpt-4.1-mini

    See Inline Souls and Soul Files for details.

  4. Run it

    1. Open the GUI at http://localhost:8000
    2. Your workflow appears on the Flows page (auto-discovered from custom/workflows/)
    3. Click the workflow to open it on the canvas
    4. Click Run