Lists (2)
Starred repositories
Examples on how to use various LLM providers with a Wine Classification problem
utilities for decoding deep representations (like sentence embeddings) back to text
Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.
TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM gateway, observability, optimization, evaluation, and experimentation.
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.
A flexible, adaptive classification system for dynamic text classification
The Cursor for Designers • An Open-Source AI-First Design tool • Visually build, style, and edit your React App with AI
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
Cellular Automata Accelerated in JAX (Oral at ICLR 2025)
lossily compress representation vectors using product quantization
A lightweight data processing framework built on DuckDB and 3FS.
A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.
🚀 The successor to oauthjs/oauth2-server. 🔒 Complete, compliant, maintained and well tested OAuth2 Server for node.js. Includes native async await and PKCE.
Synthetic data curation for post-training and structured data extraction
EvaByte: Efficient Byte-level Language Models at Scale
Shared data types for building collaborative software
anyon_e, a highly integrated, high end, open source laptop. Attempt the impossible.
Specification and documentation for the Model Context Protocol
A small TypeScript library that provides tolerable Mixin functionality.
Large Concept Models: Language modeling in a sentence representation space
general natural language facilities for node
OCR, layout analysis, reading order, table recognition in 90+ languages
FOLD file format for origami models, crease patterns, etc.
Replace 'hub' with 'ingest' in any GitHub URL to get a prompt-friendly extract of a codebase