Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the environment, repr…

Formally proving complex protocols and systems using TLA+ Proof System (TLAPS)

SysMoBench: Evaluating AI on Formally Modeling Complex Real-World Systems

Microsoft Azure Traces

Compare performance across sandbox, storage, browsers, and ai gateway providers.

Run your GitHub Actions locally 🚀

Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains

Embedded application kernel, inspired by gVisor

Specula: An agentic tool for finding deep bugs in system code using TLA+

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, an…

The lazier way to manage everything docker

🍊 A fast, keyboard-driven terminal UI to manage Docker containers, Compose stacks, and Swarm services with the ergonomics of K9s.

Synthetic data curation for post-training and structured data extraction

Can Language Models Rebuild Programs From Scratch?

Frozen — cross-agent persistent memory for coding assistants. Still works; the compressed-memory core now ships inside JuliusBrussee/caveman.

A collection of postmortems. Sorry for the delay in merging PRs!

🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.

Curated academic CV templates and guidelines for PhD students, researchers, and faculty job applicants.

A Chaos Engineering Platform for Kubernetes.

Can AI agents resolve production incidents?

KISS Sorcar: Keep it Simple, Stupid AI General Purpose Agent Framework for Long Horizon Tasks and AI Discovery

Train Ticket - A Benchmark Microservice System

Rex is a safe and usable kernel extension framework that allows loading and executing Rust kernel extension programs in the place of eBPF.

Little helper to run CNCF's k3s in Docker

A benchmark for LLMs on complicated tasks in the terminal

System Intelligence Benchmark