Stars
real time face swap and one-click video deepfake with only a single image
Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
Portable interface to epoll, kqueue, event ports, and wepoll
Sudoku solving in python packaging
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
Asterinas is a secure, fast, and general-purpose OS kernel, written in Rust and providing Linux-compatible ABI.
Financial Markets Data Visualization using Matplotlib
⚙️ Layered configuration system for Rust applications (with strong support for 12-factor applications).
Solving the AI Coaching Vertical for Running: Now on the Apple App Store
AIHawk aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in a tailored way.
E1S - Easily Manage AWS ECS Resources in Terminal(~k9s for ECS) 🐱
A blazing fast AI Gateway with integrated guardrails. Route to 200+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
A framework for serving and evaluating LLM routers - save LLM costs without compromising quality
Enjoy the magic of Diffusion models!
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Supercharge Your LLM Application Evaluations 🚀
Very spicy additions to the Java programming language.
A high-performance, zero-overhead, extensible Python compiler with built-in NumPy support
Making botocore.exceptions.ClientError easier to deal with
🔥 2D and 3D Face alignment library build using pytorch
DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…
Training and serving large-scale neural networks with auto parallelization.
Standalone TFRecord reader/writer with PyTorch data loaders