Starred repositories
A flexible distributed key-value database that is optimized for caching and other realtime workloads.
Command line artificial intelligence - Your local LLM context-feeder
A fast, accurate and multilingual fuzzy search library for the frontend.
Inline autocomplete for input fields, ideal for apps which require a quick data entry.
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
Official Repository for "Glyph: Scaling Context Windows via Visual-Text Compression"
ProtTrans is providing state of the art pretrained language models for proteins. ProtTrans was trained on thousands of GPUs from Summit and hundreds of Google TPUs using Transformers Models.
👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.
Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders
Probabilistic time series modeling in Python
Rapid fuzzy string matching in Python using various string metrics
[NAACL'21 & ACL'21] SapBERT: Self-alignment pretraining for BERT & XL-BEL: Cross-Lingual Biomedical Entity Linking.
A next-generation HTTP stealth proxy which perfectly cloaks requests as the Chrome browser across all layers of the stack.
Pure C++ implementation of several models for real-time chatting on your computer (CPU & GPU)
AirLLM 70B inference with single 4GB GPU
SQLite-Vector is a cross-platform, ultra-efficient SQLite extension that brings vector search capabilities to your embedded database.
Superfast AI decision making and intelligent processing of multi-modal data.
Change data capture for a variety of databases. Please log issues at https://issues.redhat.com/browse/DBZ.
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
Awesome LLM Books: Curated list of books on Large Language Models
CEHR-GPT: Generating Electronic Health Records with Chronological Patient Timelines