Lists (12)
Starred repositories
MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts
Reasoning-first post-training for tiny language models (140M) on a single GPU.
A GitHub Action for managing lifecycle policies and cleaning up orphaned images in AWS ECR. Ensures efficient use of ECR storage by automating routine maintenance tasks.
A GitHub Action to generate semantic version from a git repository's commit history.
Timoni is a package manager for Kubernetes, powered by CUE and inspired by Helm.
A smarter cd command. Supports all major shells.
Lambda durable functions SDK
Open-source temporary elevated access solution for AWS IAM Identity Center.
Terraform & OpenTofu Skill for AI Agents - testing, modules, CI/CD, and production patterns
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
A model-driven approach to building AI agents in just a few lines of code.
A comprehensive evaluation framework for AI agents and LLM applications.
Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.
Deploy Locust load testing framework on Amazon ECS
This guidance demonstrates how to deploy a comprehensive agentic application for advertising workflows using Amazon Bedrock AgentCore. The solution showcases advanced multi-agent collaboration acro…
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
an AWS Lambda python project managed by uv
The Tennis Serve Analysis App is a mobile application designed to revolutionize the way tennis players analyze and improve their serves. Leveraging machine learning algorithms and computer vision t…
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…
Amazon Bedrock Agentcore accelerates AI agents into production with the scale, reliability, and security, critical to real-world deployment.
Streaming ETL job cases in AWS Glue to integrate Iceberg and creating an in-place updatable data lake on Amazon S3
Data Lake as Code, featuring ChEMBL and OpenTargets
Build compute kernels and load them from the Hub.