For developers, building AI factories demands coordinated planning across systems to optimize AI Factories. NVIDIA Omniverse Libraries and OpenUSD enable developers to to create digital twin soluti…

A modern specification language and model checker for concurrent and distributed systems. Faster than TLA+/TLC.

Static low-bandwidth search at scale

Steal SSH host private keys and /etc/shadow via the ptrace_may_access mm-NULL bypass + pidfd_getfd. Pre-31e62c2ebbfd kernels.

Muliti-level sandboxing for AI coding agent using VM + immutable OS + gVisor + scoped containers

A highly opinionated, zero-configuration linter and formatter.

Minimal CSS Framework for semantic HTML

A Go implementation of OpenHistogram log-linear histograms

Capability-oriented version of the Rust standard library

LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization

Minimalist ML framework for Rust

Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

The best-in-class HTTP Debugger for macOS. Capture HTTP/HTTPS from macOS, iOS, Android with a few clicks ✅

Zeek is a powerful network analysis framework that is much different from the typical IDS you may know.

Self-contained Machine Learning and Natural Language Processing library in Go

onnx-go gives the ability to import a pre-trained neural network within Go without being linked to a framework or library.

An alignment auditing agent capable of quickly exploring alignment hypothesis

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

A Go (golang) library wrapping microsoft/onnxruntime.

duckdb-go provides a database/sql driver for the DuckDB database engine.

Sandboxed Rhai script execution engine with Cedar policy authorization for every system operation.

Pure Go PostgreSQL Parser. 100% compatible with PostgreSQL 17.7 AST and regression tests.

Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action …

Agent Harness for Large Language Model Agents: A Survey. Survey on LLM agentharnessengineering with a taxonomy. 110+papers, 23 systems analyzed.

Deterministic U2F token project

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.

Broccoli turns Linear tickets into shipped PRs — powered by Claude and Codex, running on your own Google Cloud or Blaxel containers.

Lattice // Salt // Facet