Search
palimpsests
Assault Consulting
A layered local-LLM inference engine: from thin wrapper to your own serving service, under one abstraction.
tensorstudio
Ian
Early-stage tensor and model toolkit for AI, ML, and LLM workflows.
@lazyapps/readmodelstorage-mongodb
Oliver Sturm
MongoDB-backed read model storage for LazyApps
cre-router
Yasmin Moslem
Cluster, Route, Escalate: a cascaded framework for cost-aware LLM serving
skribe
Fredrik Linaker
LLM-powered estimators that inscribe prediction logic as standalone Python functions
@keystrokehq/llmwhisperer
wells-keystroke
No description available
@keystrokehq/openai
wells-keystroke
No description available
@keystrokehq/ragic
wells-keystroke
No description available
@keystrokehq/ragie
wells-keystroke
No description available
langchain-apple-foundation-models
Rajan Sharma
LangChain chat model provider for Apple's on-device Foundation Models framework
@byu-oit/umzug-storage-dynamodb
Jamie Visker
DynamoDB storage for Umzug migration logs.
storage-s3
Gary Crye
A small module for storing values in AWS S3
pi-gpt
davidroman0O
Native Pi extension: drive your ChatGPT/Codex account (chat, deep research, account, models) as Pi tools, scoped to the current project.
...moreriemannmol
RiemannMol: properties-guided molecule generation over the atom (plain-SMILES) and fragment (SAFE) latent backends
ipynbcleaner
Daniel Dias Pereira
Clean Jupyter notebooks for LLMs and lightweight sharing.
@waits/lively-storage
ryanwaits
CRDT storage types for Lively real-time collaboration
langchain-concentrate
LangChain integration for Concentrate.ai — a unified LLM gateway with the OpenAI Responses API.
dload-ml
Dataset management, storage, caching and streaming for ML training
@vikasagarwal101/zai-cli
ilikethesound
CLI for Z.AI capabilities: vision analysis, web search, web reader, and GitHub repo exploration. Patched fork with socket-leak, timeout, retry, and count fixes.
...more@xtuis/cli
xtuis
Agent-first CLI for xtuis.cn push notifications