Starred repositories
slime is an LLM post-training framework for RL Scaling.
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
Post-training with Tinker
Achieve state of the art inference performance with modern accelerators on Kubernetes
A flexible distributed key-value database that is optimized for caching and other realtime workloads.
MetricFlow allows you to define, build, and maintain metrics in code.
🦥 Easy and simple Prometheus SLO (service level objectives) generator
Making SLOs with Prometheus manageable, accessible, and easy to use for everyone!
A simple, easy-to-hack GraphRAG implementation
This demo shows a multi-turn conversation with an AI agent running inside a Temporal workflow.
A one stop repository for generative AI research updates, interview resources, notebooks and much more!
12 Lessons to Get Started Building AI Agents
A pure Go implementation of Gil Tene's HDR Histogram.
A High Dynamic Range (HDR) Histogram
Anthropic's Interactive Prompt Engineering Tutorial
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
Modern observability platform: 10x easier, 140x lower storage cost, petabyte scale. Open-source alternative to Elasticsearch/Splunk/Datadog for logs, metrics, traces, RUM, and more.
Welcome to the official repository of SINQ! A novel, fast and high-quality quantization method designed to make any Large Language Model smaller while preserving accuracy.
Home to the Signal Protocol as well as other cryptographic primitives which make Signal possible.
Faster Whisper transcription with CTranslate2
World's most powerful open data catalog for building a high-performance, geo-distributed and federated metadata lake.
ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)
World's fastest and most advanced password recovery utility
Fast and memory-efficient exact attention