A self-improving RLM agent for coding workflows and long-running autonomous tasks.

lightweight system-level observability for AI Agents

Tile primitives for speedy kernels

Model Express is a Rust-based component meant to be placed next to existing model inference systems to speed up their startup times and improve overall performance.

NVIDIA Inference Xfer Library (NIXL)

Tokio Telemetry you can run in production

🔥 LeetCode for PyTorch — practice implementing softmax, attention, GPT-2 and more from scratch with instant auto-grading. Jupyter-based, self-hosted or try online.

OpenShell is the safe, private runtime for autonomous AI agents.

Programmatic sandboxing tool

Open-source framework for the research and development of foundation models.

Create virtual machines and run Linux-based operating systems in Go using Apple Virtualization.framework.

An SDK in Go for the Firecracker microVM API

A Datacenter Scale Distributed Inference Serving Framework

OpenTelemetry Instrumentation for AI Observability

My learning notes for ML SYS.

Kubernetes Virtualization API and runtime in order to define and manage virtual machines.

Nix packages for AI coding agents and development tools. Automatically updated daily.

A lightweight inference engine supporting speculative speculative decoding (SSD).

The Modular Platform (includes MAX & Mojo)

Declaratively deploy your Kubernetes manifests, Kustomize configs, and Charts as Helm releases. Generate all-in-one manifests for use with ArgoCD.

Open-source observability for your GenAI or LLM application, based on OpenTelemetry

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

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…

Fast and easy to use database for logs, which can efficiently handle terabytes of logs

VictoriaMetrics: fast, cost-effective monitoring solution and time series database

JuiceFS is a distributed POSIX file system built on top of Redis and S3.

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.

✨ Making your shell magical

Session manager and task runner for tmux. Start your development environment within one command.

Collaboration in the age of agentic engineering