Storyteller
AI Storyteller - where your imagination meets state-of-the-art AI creativity.
MCP
Locally
We need two instances:
MCP server
MEDIA server
ATM, the Marimo app has MEDIA server functionality. For local inference, we can use that.
As a pre-requisite, both processed, need to be given this:
export DISABLE_HTTPS_ENFORCEMENT=1
export DISABLE_AUTHENTICATION=1
export OPENAI_API_KEY='ollama'
export OPENAI_BASE_URL='http://127.0.0.1:11434/v1'
export STORYTELLER_MEDIA_PATH='/Users/me/repos/ai-storyteller/media'
export STORYTELLER_MEDIA_URL='http://localhost:8000/media/'
export STORYTELLER_OUTPUT_PATH='/Users/me/repos/ai-storyteller/output'
export STORYTELLER_OUTPUT_MEDIA_URL='http://localhost:8000/media/output/'
export STORYTELLER_TOOL_MODEL_PROVIDER='openai'
export STORYTELLER_TOOL_MODEL_NAME='gpt-5-mini'
export STORYTELLER_STORY_MODEL_NAME='o4-mini'
export STORYTELLER_IMAGE_DESCRIPTOR_MODEL_NAME='gpt-4.1-mini'Then start the MEDIA server (FastAPI/Playground):
make runThen start the MCP server in HTTP mode (FastAPI):
make mcpTo start the AI chat (with storyteller tool), type:
make chatLicense
MIT
1 maintainer
Metadata
1 maintainer
Release files for ai-storyteller 0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ai_storyteller-0.1.tar.gz | 124.7 kB | Without provenance | Details for ai_storyteller-0.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ai_storyteller-0.1-py3-none-any.whl | Python 3 | none | any | Details for ai_storyteller-0.1-py3-none-any.whl |
Total release size: 283.6 kB
Release files / ai_storyteller-0.1.tar.gz
| Download URL | ai_storyteller-0.1.tar.gz |
|---|---|
| Size | 124.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
264d2fd1e14eb5d93d585ac7d934a949db3c047286abeeb61b998a866a0318dd
|
|
BLAKE2b-256 checksum How to use checksums |
eb5daf577ea66b3d8d461323691b86dc572894287d4d6def62d39c7837e6e189
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.9
|
Release files / ai_storyteller-0.1-py3-none-any.whl
| Download URL | ai_storyteller-0.1-py3-none-any.whl |
|---|---|
| Size | 158.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
86508eee5a2ca36bbdfafcca117711e50537b81120b1982838a8ec883f2fdc49
|
|
BLAKE2b-256 checksum How to use checksums |
b3810d657f74b8e7accb0debbd903f39a90c1ee61f4ba0875354cf8502c95deb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.9
|
Security for ai-storyteller 0.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
