OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Workflow Agents

PenShot

PenShot is a Python multi-agent system that converts scripts and other narrative text into sequenced storyboard descriptions and text-to-video prompts. It uses a LangGraph workflow, retrieval and memory mechanisms to help preserve character, scene and plot details across segments, and offers SDK, REST API, MCP, function-calling, A2A and LangGraph integrations.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

PenShot — OpenViST project profile in Workflow Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use PenShot when narrative material needs to be organized into sequenced shots and text-to-video prompts, especially when continuity across segments matters or the workflow needs an API or agent-protocol integration.

Who it is for

  • Screenwriters and video-production teams preparing scripts for AI video workflows.
  • Developers integrating script-to-shot and prompt generation into applications or agent workflows.

Documented uses

  • Break a screenplay, anime script, short drama or novel into shot-level segments.
  • Generate structured visual prompts for downstream text-to-video models.
  • Carry character and scene details across multiple script segments.
  • Expose shot and prompt generation through application or agent integrations.
Before you choose

Requirements & limits

The project is presented as open source under the MIT license. Its repository documents Python 3.10 or later and configuration for LLM, embedding-model and Redis services.

  • The documented setup requires configuration for an LLM, an embedding model and Redis.
  • Python 3.10 or later is indicated in the repository.
  • PenShot generates shot descriptions and prompts; the project describes video models as downstream targets.
  • Integration options include Python SDK, REST API, MCP, function calling, A2A and LangGraph nodes.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare PenShot’s model and Redis configuration

Set up the documented environment variables needed before using PenShot’s narrative-to-shot workflow.

Before you start

  • Python 3.10 or later, as indicated by the project README.
  • An LLM endpoint and API credentials.
  • An embedding-model endpoint and API credentials.
  • A Redis instance and its connection URL.

Steps

  1. Install the package with the command below.

    Documented command
    pip install penshot

  2. Copy the example environment file with cp .env.example .env.

  3. Set the LLM base URL, API key and model name in the PenShot configuration.

  4. Set the embedding base URL, API key and model name, then configure PENSHOT_REDIS_URL for Redis.

Expected outcome

The environment variables for the LLM, embedding model and Redis are configured for a subsequent PenShot integration.

Guide limitations

  • These steps cover installation and configuration only; they do not demonstrate running a conversion.
  • The selected model services and Redis must be available to the environment using the configured endpoints and credentials.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
neopen/story-shot-agent · Official homepage title · retained in its source language
How we review sourcesSuggest a correction