benjiyaya /Calliope

Local-first Agentic Idea-to-video Studio Using ComfyUI + FastAPI + SvelteKit

★ 302⑂ 72👁 8⑃ 34● 55▤ 20
PythonMITCreated 2026-07-27
下载:Calliope 1.7.0 — agent engine rewrite and gap fixesCalliope-1.7.0 ↓1.7.02026-11-14
+1
日增长
302
stars
72
forks
8
watchers
34
prs
55
issues
20
releases

README

Calliope

Calliope is a local-first story-to-video studio. You type a story idea; Calliope drafts a storyline with beats, characters, and locations, writes a screenplay-faithful per-scene script, then breaks each scene into shot clips and generates one video per clip by driving your own ComfyUI install. When the clips are done, one click stitches them into a finished film with crossfades and matched loudness (ffmpeg). Everything runs on your machine: projects live in SQLite, media lives in folders, and no cloud service is involved beyond the LLM endpoint you point it at.











 Demo

From Script to Video Locally Using Calliope 1.5 https://youtu.be/JcGqt3DYn6c

 Install — from source (npm + Python)

Prerequisites

- Python 3.11+
- Node.js 18+ (npm)
- A running ComfyUI install, with the models your workflows need already set up
- An OpenAI-compatible LLM endpoint — local (LM Studio, Ollama, etc.) or hosted
- ffmpeg on PATH — needed for film export

1. Backend (FastAPI)

bash
cd calliope-backend
python -m venv .venv
.venv\Scripts\pip install -e ".[dev]"
.venv\Scripts\python -m calliope.main --host 127.0.0.1 --port 8247


Optionally copy calliope_config.example.json to calliope_config.json and edit it before starting (LLM endpoint, ComfyUI URL). You can also configure everything later in the app's Settings page. Never commit calliope_config.json — it stores your API key.

2. Frontend (SvelteKit)

bash
cd calliope-web
npm install
npm run dev


Open http://127.0.0.1:5173. The dev server proxies /api to the backend on 127.0.0.1:8247.

 First run

Open the app, go to Settings, and set:

1. LLM — one or more OpenAI-compatible endpoints (base URL, model name, API key). Save several, then pick which one is Active.
2. ComfyUI — the base URL of your running ComfyUI (e.g. http://127.0.0.1:8188). Workflow jobs go through the Comfy SDK to comfy-api-proxy (default http://127.0.0.1:8189, Settings → Comfy → Comfy API URL). With ComfyUI already on 8188:

bash
pip install comfy-api-proxy
comfy-api-proxy --comfyui http://127.0.0.1:8188 --port 8189


Comfy Router is optional. Save a Comfy API key under Settings → Comfy, turn on Use Comfy API provider (Router), and the video and asset pickers offer MiniMax H3 and FLUX 3. No key, or the switch left off, means every job stays on your local workflow.
3. Agent (optional) — assign a specific LLM per agent role (see below)

Leave Dry-run off — it is meant for testing and produces placeholder results instead of real generations.

 Queue settings

In Settings → Queue you can tune how the worker talks to ComfyUI:

- Concurrency — how many jobs run at once.
- Poll interval — how often Calliope checks ComfyUI for a finished job.
- Poll timeout (seconds) — how long Calliope keeps waiting on ComfyUI for a single job before failing it. Default is 1800 (30 minutes). Long video generations can easily exceed 10 minutes, so raise this for heavy workflows — or set it to 0 to wait indefinitely (until the job finishes or you cancel it)

Top issues

Discussions

Latest release

Calliope 1.7.0 — agent engine rewrite and gap fixes v1.7.0 2026-11-14
Release v1.7.0, 2026-11-14. The plugin harness is gone; the agent loop is a grant-scoped studio runtime, the capabilities it dropped are restored, and plain chat converses again.

 The agent loop has been rewritten

The old plugin harness (harness/loop|orchestrator|policy|registry|tools, harness/plugins/) is gone, replaced by a grant-scoped studio runtime (agent/runtime/ + agent/capabilities/):

- Your message is matched into scoped studio calls (story → script → assets → render → canvas). Each call runs ONE sub-agent that only sees its grant's tools, and the run is verified against the 

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON