osehmathias
Follow
Stars
DeepSeek LLM: Let there be answers
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
RAG that intelligently adapts to your use case, data, and queries
S-LoRA: Serving Thousands of Concurrent LoRA Adapters
Scheduling infrastructure for absolutely everyone.
Rust library for generating vector embeddings, reranking locally
Advanced data structures for handling temporal segments with attached labels.
TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models.
Chromium Binary for AWS Lambda and Google Cloud Functions
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
Claude Memory: Long-term memory for Claude
shanti is making her own website and putting it here
Papermark is the open-source DocSend alternative with built-in analytics and custom domains.
A concise but complete full-attention transformer with a set of promising experimental features from various papers
Vim plugin for LLM-assisted code/text completion
Blazing fast graph RAG service, specifically designed to deliver context to voice AI and other low latency applications in under 50 ms
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
A lightweight, dependency-free Python library (and command-line utility) for downloading YouTube Videos.
📃 A better UX for chat, writing content, and coding with LLMs.
Zep: Long-Term Memory for AI Assistants (Python Client)
58 MB Google Chrome to fit inside AWS Lambda Layer compressed with Brotli
Chromium (x86-64) for Serverless Platforms