
Starred repositories
Toolkit for linearizing PDFs for LLM datasets/training
This project aims to emulate some of the advanced reasoning capabilities seen in models like OpenAI's o1. It does not claim to replicate the exact functionality or performance of o1.
A fast Rust based tool to serialize text-based files in a repository or directory for LLM consumption
A tool which makes it easy to declaratively manage personal forks by automatically merging pull requests
A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具,将PDF转换成Markdown和JSON格式。
Common rust command-line macros and utilities, to write shell-script like tasks in a clean, natural and rusty way
This repository contains rules for continuous, GitOps driven Kubernetes deployments.
A tool to simulate Amazon EC2 instance metadata
Uncomplicated Observability for Python and beyond! 🪵🔥
Open source platform for AI Engineering: OpenTelemetry-native LLM Observability, GPU Monitoring, Guardrails, Evaluations, Prompt Management, Vault, Playground. 🚀💻 Integrates with 50+ LLM Providers,…
The production-scale datacenter profiler (C/C++, Go, Rust, Python, Java, NodeJS, .NET, PHP, Ruby, Perl, ...)
Langtrace SDK for Python Applications
Langtrace 🔍 is an open-source, Open Telemetry based end-to-end observability tool for LLM applications, providing real-time tracing, evaluations and metrics for popular LLMs, LLM frameworks, vector…
Open-source observability for your LLM application, based on OpenTelemetry
Rules for installing debian-packages into Docker-Images with bazel
Extracts media files (AVI, Ogg, Wave, PNG, ...) that are embedded within other files.
Simple, minimal implementation of the Mamba SSM in one file of PyTorch.
Test your prompts, agents, and RAGs. Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with comma…
AeroSpace is an i3-like tiling window manager for macOS
by ex-googlers, for ex-googlers - a lookup table of similar tech & services
Riegeli/records is a file format for storing a sequence of string records, typically serialized protocol buffers.
A Vale-compatible implementation of the Google Developer Documentation Style Guide.