https://github.com/davidmosiah/short-video-agent-kit
Agent-first short-form AI video generation CLI and MCP server for Sora, Veo, xAI and Seedance
https://github.com/davidmosiah/short-video-agent-kit
agent-tools agentic-workflows ai-agents claude codex creator-tools dry-run gemini local-first mcp mcp-server model-context-protocol sora veo video-generation video-tools xai
Last synced: 19 days ago
JSON representation
Agent-first short-form AI video generation CLI and MCP server for Sora, Veo, xAI and Seedance
- Host: GitHub
- URL: https://github.com/davidmosiah/short-video-agent-kit
- Owner: davidmosiah
- License: mit
- Created: 2026-05-05T11:54:14.000Z (2 months ago)
- Default Branch: main
- Last Pushed: 2026-05-23T18:20:49.000Z (about 2 months ago)
- Last Synced: 2026-05-23T20:15:20.597Z (about 2 months ago)
- Topics: agent-tools, agentic-workflows, ai-agents, claude, codex, creator-tools, dry-run, gemini, local-first, mcp, mcp-server, model-context-protocol, sora, veo, video-generation, video-tools, xai
- Language: JavaScript
- Homepage: https://www.npmjs.com/package/short-video-agent-kit
- Size: 156 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Security: SECURITY.md
- Agents: AGENTS.md
Awesome Lists containing this project
README
Short Video Agent Kit
One agent-first CLI + MCP for short-form AI video.
Sora · Veo · xAI · Seedance — dry-run by default, paid generation when explicitly enabled.
> ⭐ **If this agent-first tool helps your workflow, please star the repo.** Stars make this tooling easier for other builders to discover and help Delx keep shipping open infrastructure.
> 🧱 Part of the [Delx agent stack](https://github.com/davidmosiah) — 15 open-source MCP servers across **body, reach and coordination**.
---
Provider-neutral short-form AI video toolkit for agents. It gives Codex, Claude, Cursor, Hermes, OpenClaw and other MCP clients one interface for building dry-run payloads and, when explicitly enabled, generating vertical video through Sora/OpenAI, Gemini Veo, xAI/Grok and Seedance/PiAPI-style providers.
Use it when an agent needs one safe interface for prompt-to-video payload validation and optional paid generation across multiple providers.
## Why It Is Agent-First
Video generation can be expensive and prompt-sensitive. This package makes agents start with safe steps:
- inspect provider readiness
- return privacy boundaries
- build payloads without spending credits
- require `--live` or `SHORT_VIDEO_DRY_RUN=false` before provider calls
- keep prompts and outputs in local user-controlled paths
## Install
```bash
npm install -g short-video-agent-kit
```
Or run directly:
```bash
npm exec --yes --package=short-video-agent-kit -- short-video-agent-kit doctor
```
## Quickstart
No API key needed to try it — generation is dry-run by default, so the kit returns the exact provider-neutral plan it *would* send without spending a credit.
Build a Sora plan for an 8-second vertical teaser:
```bash
short-video-agent-kit generate \
--provider openai_sora \
--prompt "Vertical 8-second product teaser for a minimalist water bottle, soft studio light, slow dolly-in" \
--output ./output/teaser.mp4
```
Real output (no provider call, no credits spent):
```json
{
"ok": true,
"dry_run": true,
"next_step": "Pass --live or set SHORT_VIDEO_DRY_RUN=false to call the provider API.",
"provider": "openai_sora",
"endpoint": "POST /v1/videos",
"payload": {
"model": "sora-2",
"prompt": "Vertical 8-second product teaser for a minimalist water bottle, soft studio light, slow dolly-in",
"seconds": "8",
"size": "720x1280"
}
}
```
Same prompt, different provider — the plan re-targets the endpoint and parameter shape for you. `payload` returns just the plan (no `dry_run` wrapper):
```bash
short-video-agent-kit payload --provider gemini_veo --prompt "Same teaser, 9:16, cinematic"
```
```json
{
"provider": "gemini_veo",
"endpoint": "POST /models/{model}:predictLongRunning",
"payload": {
"instances": [
{
"prompt": "Same teaser, 9:16, cinematic"
}
],
"parameters": {
"aspectRatio": "9:16",
"durationSeconds": 8
}
}
}
```
Check which providers are wired up (keys are detected, never printed):
```bash
short-video-agent-kit doctor
```
```json
{
"ok": false,
"dry_run": true,
"providers": {
"openai_sora": { "configured": false, "env_keys": ["OPENAI_API_KEY"], "models": ["sora-2"] },
"gemini_veo": { "configured": false, "env_keys": ["GEMINI_API_KEY", "GOOGLE_API_KEY"], "models": ["veo-3.1-fast-generate-preview"] },
"xai_grok": { "configured": false, "env_keys": ["XAI_API_KEY"], "models": ["grok-imagine-video", "grok-imagine-image"] },
"seedance_piapi": { "configured": false, "env_keys": ["PIAPI_KEY", "SEEDANCE_API_KEY"], "models": ["seedance-2-fast-preview"] }
},
"output_dir": "./output",
"next_steps": [
"Set one provider key: OPENAI_API_KEY, GEMINI_API_KEY, XAI_API_KEY or PIAPI_KEY."
]
}
```
When you are ready to actually render, set a provider key and re-run `generate` with `--live` (or `SHORT_VIDEO_DRY_RUN=false`).
## CLI
```bash
short-video-agent-kit manifest --client codex
short-video-agent-kit doctor
short-video-agent-kit privacy-audit
short-video-agent-kit payload --provider gemini_veo --prompt-file prompt.txt
short-video-agent-kit generate --provider openai_sora --prompt "Vertical product teaser" --output ./output/teaser.mp4
short-video-agent-kit generate --provider openai_sora --prompt-file prompt.txt --output ./output/teaser.mp4 --live
```
Supported providers:
- `openai_sora`
- `gemini_veo`
- `xai_grok`
- `seedance_piapi`
## MCP
```bash
short-video-mcp
```
HTTP transport:
```bash
SHORT_VIDEO_MCP_TRANSPORT=http short-video-mcp
```
Hermes-style config:
```yaml
mcp_servers:
short_video:
command: npx
args: ["-y", "short-video-agent-kit"]
sampling:
enabled: false
```
Recommended first calls:
1. `short_video_connection_status`
2. `short_video_privacy_audit`
3. `short_video_build_payload`
4. `short_video_generate`
## Agent Surfaces
| Tool | Purpose |
|---|---|
| `short_video_agent_manifest` | Install/runtime guidance for Codex, Claude, Cursor, Hermes and OpenClaw |
| `short_video_connection_status` | Provider readiness without API keys |
| `short_video_privacy_audit` | Prompt, output and reference-asset boundaries |
| `short_video_build_payload` | Provider-specific payload without paid generation |
| `short_video_generate` | Dry-run by default, live only when explicitly requested |
## Copy-Paste Agent Prompt
```text
Use short-video-agent-kit. First call short_video_connection_status and short_video_privacy_audit.
Build the payload before generation. Only set live=true if I explicitly confirm a paid provider call.
```
## Configuration
Copy `.env.example` to `.env` and fill only the provider keys you plan to use. `.env`, `output/` and `.agent-data/` are ignored by Git.
## Safety Model
- Dry-run is the default.
- API keys are never returned by tools.
- Paid generation requires `--live`, MCP `live=true`, or `SHORT_VIDEO_DRY_RUN=false`.
- Reference images must be user-owned or licensed.
- Outputs are written to local paths controlled by the user.
## Development
```bash
npm install
npm test
npm run check
```
---
## 📧 Contact & Support
- 📨 **support@delx.ai** — general questions, integration help, partnerships
- 🐛 **Bug reports / feature requests** — [GitHub Issues](https://github.com/davidmosiah/short-video-agent-kit/issues)
- 🐦 **Updates** — [@delx369](https://x.com/delx369) on X
- 🌐 **Site** — [wellness.delx.ai](https://wellness.delx.ai)