MCPcopy Index your code
hub / github.com/NOM-Network/Melba-Toast-AI

github.com/NOM-Network/Melba-Toast-AI @main

Chat with this repo
repository ↗ · DeepWiki ↗ · + Follow
87 symbols 221 edges 7 files 0 documented · 0%
What it actually does AI analysis from the code graph — generated when you open this
loading…
README

Melba-Toast-AI

WIP Inference program to interact with large language models of the GGUF format. Requirements: A working installation of llama-cpp-python, ChromaDB and NRCLex is needed. Mistral models of the GGUF format found on Huggingface currently appear to be broken, the model files need to be downloaded, turned into GGUF and quantized locally.

License

This code is licensed under a AGPL 3.0 (and later) license

Core symbols most depended-on inside this repo

log
called by 6
src/melbaToast.py
accessMemories
called by 5
src/melbaToast.py
newDBEntry
called by 5
src/memoryDB.py
warnAndExit
called by 4
src/LLMCore.py
response
called by 3
src/LLMCore.py
getEmotion
called by 3
src/melbaToast.py
entryExists
called by 3
src/memoryDB.py
metadataQueryDB
called by 3
src/memoryDB.py

Shape

Method 70
Class 11
Function 6

Languages

Python100%

Modules by API surface

src/melbaToast.py41 symbols
src/LLMCore.py24 symbols
src/memoryDB.py12 symbols
src/LLMUtils.py5 symbols
src/initMemoryDB.py4 symbols
src/llmbackendClient.py1 symbols

For agents

$ claude mcp add Melba-Toast-AI \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact