convez.ai
MCP Server
sandraschi

ittybittyvideos

sandraschi/ittybittyvideos

Ver no GitHub
InicialPluginScore · de 0 a 100

tiny tool, big videos. topic in, video out. no film degree required. webapp, windows app and mcp server for agent use

Instalação

$npx convez-ai sandraschi/ittybittyvideos

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
2
Forks
0
Acompanhando
0
Saúde
28%
Último commit
há 3 semanas
Versão
v0.2.0
Issues abertas
1
Contribuidores
1

README

A tradução para o português deste README ainda está na fila.

ittybitty

Topic or script in → narrated video out. Shorts for TikTok and Reels, or longer chaptered explainers — with stock footage, your Jellyfin/Plex home videos, or local AI clips.

License Status · 中文 README

Alpha — under construction. APIs, pipelines (R3 screening, R9 talker), and the Windows installer may change between releases. Not production-ready. See alpha release checklist before going public or tagging.

Three ways to use it (pick one):

Windows appWeb dashboardMCP server
ForEveryday use on your PCBrowser UI while you develop or self-hostCursor, Claude, other MCP clients
You getInstaller + desktop shortcut; backend starts automaticallyGenerate, Jobs, Depot, Settings, Helpvideogen_* tools for agents
StartDownload installerRun locally or use the app aboveConnect MCP

Same engine under all three: Python backend on port 11054, React dashboard on 11055 when running the dev stack.


Contents

Windows appInstaller — no Python required
Web dashboardBrowser UI (dev or bundled in desktop app)
MCP serverAgent automation
What you needKeys and optional extras
Footage sourcesWhere B-roll comes from
vs MoneyPrinterTurboWhy pick ittybitty
More helpConfig, troubleshooting, API docs
Marketing siteGitHub Pages one-pager (also website/ locally)

Windows app

Best if you just want to make videos.

  1. Download the latest pre-release installer from Releases (tag v0.2.0-alpha.* or newer)
  2. Run the installer → launch ittybitty from Start or your desktop shortcut
  3. In Settings, add a free stock API key (Pexels, Pixabay, or Coverr) → Generate with a topic or paste a script

The installer bundles the web dashboard and Python backend — no separate Python or Node install.

Install folder: %LOCALAPPDATA%\ittybitty\
If the backend fails to start: %LOCALAPPDATA%\ai.fleet.ittybitty\logs\backend-spawn.log


Web dashboard

The React UI: Generate, Plan (mid-length), Jobs, Depot, Publish, Settings, Help, Logs.

Already using the Windows app? You're in the dashboard — nothing else to install.

Running on your dev machine (live reload, for contributors):

git clone https://github.com/sandraschi/ittybittyvideos.git videogen-mcp
cd videogen-mcp
.\start.bat

Open http://127.0.0.1:11055. The script starts the dashboard and the API together.

Needs Python 3.10+, FFmpeg, and Node.js — see INSTALL.md.


MCP server

For AI agents that should generate or plan videos over the Model Context Protocol.

  1. Start the backend (Windows app running, or .\start.bat -BackendOnly, or uv run python -m videogen_mcp.server)
  2. Point your MCP client at http://127.0.0.1:11054/mcp

Example prompts: "Generate a 45-second video about Vienna coffee culture" · "Plan a 5-minute sourdough tutorial" · "Call videogen_help first"

Tool list and REST API: docs/TOOLS.md (16 MCP tools; catalog at /api/v1/tools) · Claude Desktop / MCPB: INSTALL.md


What you need

ForYou need
Most workflowsFFmpeg on PATH + free stock API key (Pexels, Pixabay, or Coverr)
Topic → scriptDeepSeek or OpenAI key, or paste your own script
Home videos as B-rollJellyfin or Plex URL + token (Settings)
Local AI clips (GPU)CUDA ~24 GB + .\start-localgen.bat

The in-app Help page walks through each step.


Footage sources

Pick one in Settings → Footage (free tier = no GPU):

  • Pexels — free stock (default)
  • Pixabay — free stock (MPT parity)
  • Mixkit — free 1080p clips, no API key
  • NASA — public-domain space/science footage, no API key
  • Jellyfin / Plex — cut clips from your library (vacation, pets, …)
  • Veo / Omni — Google cloud (config)
  • LocalGen — Wan 2.2 on your GPU

Finished videos land in ./output/ and appear in Depot.


How this differs from MoneyPrinterTurbo

MoneyPrinterTurbo popularized topic → short video. ittybitty targets the same job with fleet tooling: agents, longer formats, your own libraries, and a path to local GPU — still alpha, so expect rough edges.

MoneyPrinterTurboittybitty (alpha)
How you run itWeb UIWindows app + web dashboard + HTTP MCP
LengthMostly shorts (~60s)Shorts + 3–15 min chapters (planner + videographer rules)
FootagePexels, Pixabay, Coverr (+ local/social)Same three + Mixkit + NASA (no key) + Jellyfin/Plex + LocalGen + Veo/Omni
Agents—videogen_* tools for Cursor, Claude, fleet MCP clients
Library & jobs—SQLite depot, job history, publish handoff
Edit intelligenceAssembly / concatHook, pacing, B-roll, transitions; R1 karaoke subs; R2 beat snap + ducking; R3 screening (experimental)
ArchitectureMonolithPlugin registry — swap LLM, stock, and TTS providers
Desktop—NSIS installer (Windows, backend bundled)
StatusMature OSSAlpha — checklist

中文说明与中国本地栈(通义千问、CosyVoice 等):README-zh.md


Sample output

GSD puppy discovers snow

"German Shepherd puppy discovers snow for the first time" -- generated in ~55 seconds. Download full MP4 (17 MB)

Quick test render:

py scripts/smoke_render.py

docs/examples/README.md


More help

DocWhen to read it
INSTALL.mdAll install paths, MCPB, verification
docs/CONFIGURATION.mdEnv vars and providers
docs/TROUBLESHOOTING.mdSomething broke
docs/ALPHA-RELEASE-CHECKLIST.mdGoing public / alpha tag
docs/PROMPT-DIRECTOR.mdR10 trope templates (mermaid)
docs/EXEMPLARS-RESEARCH.mdViral Short formats + mid expansion
docs/TOOLS.mdMCP tools and REST API
docs/DEVELOPMENT.mdTests, Tauri build, CI
SPEC.mdArchitecture and roadmap
CHANGELOG.mdVersion history

Fleet docs: mcp-central-docs/projects/ittybitty


MIT · sandraschi · v0.2.0

Repo folder videogen-mcp, Python package videogen_mcp — kept for MCP tool compatibility.

Ver o original no GitHub

Bom para

Relacionados