Search
tvplotlines
Extract plotlines from TV series synopses using LLM
ccr-review
Cross-Context Review: Model-agnostic LLM bias elimination through session isolation
quantcrush
TurboQuant
Crush any LLM to 6x smaller in one command. GGUF, GPTQ, AWQ.
breathe-memory
Context optimization and associative memory for LLM applications
evalflow
pytest for LLMs - catch prompt regressions before they reach production
kganalytica
Knowledge graph construction, comparison, and similarity toolkit for LLM contextual understanding
rivus-vario
Tim Chklovski
Multi-model pipeline engine — compose LLM strategies as YAML recipes
graphreduce
Wes Madrigal
Leveraging graph data structures for complex feature engineering pipelines.
nn-gpt
LLM-Based Neural Network Generator
lmurg
LLM-Based Neural Network Generator
litellm-detector
Filesystem-only LiteLLM package detector with terminal UX and advisory checks.
arxiv-to-prompt
Takashi Ishida
transform arXiv papers into a single latex prompt for LLMs
datastew
Tim Adams, Mehmet Can Ay
Datastew is a python library for intelligent data harmonization using Large Language Model (LLM) vector embeddings.
dissect.fat
A Dissect module implementing parsers for the FAT and exFAT file systems, commonly used on flash memory based storage devices and UEFI partitions
...morebertrend
Jérôme Picault
BERTrend analyses topic evolution over time using state-of-the-art transformer models: topic modelling and LLM
routelayer
Unified LLM routing with automatic fallback, cost-aware model selection, and semantic caching.
lix-open-cache
Reusable session management and multi-layer Redis caching for conversational AI
pyutilxyz
Alireza Sadeghi
Internal utility package for communication, storage, and integration with Microsoft services.
kydon-gpt
A PyTorch-based GPT model implementation with configurable architecture
langchain-sqlserver
An integration package to support SQL Server in LangChain.