Stars
The Balanced Routing Table (BART) adapts D.E. Knuth's Allotment Routing Table (ART) algorithm to deliver comparable lookup speeds with superior update efficiency and a significantly smaller memory …
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
A simple to deploy but feature rich S3 object storage server for your filesystem
a fast, GPU-accelerated, full-featured IDE and terminal multiplexer, suitable both for automatic and manual programming.
Router that virtually distributes inference across connected devices in the home.
A high-performance inference engine for AI models
Open source solutions for SOC2, GDPR, and ISO27001
Unlocking Lossless Speedups in LLMs via Discrete Diffusion
Exo is an agent + harness architecture that is fully recursive, able to safely edit all aspects of itself at runtime to get better at your tasks.
MoQ-native transport and observability API for robotics teams
AXI, AXI stream, Ethernet, and PCIe components in System Verilog
Open source FPGA-based NIC and platform for in-network compute
Lightpanda: the headless browser designed for AI and automation
LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure
Powerful system-level package manager for Linux, macOS and Windows written in Rust – building on top of the Conda ecosystem.
libSQL is a fork of SQLite that is both Open Source, and Open Contributions.
Resolve production issues, fast. An open source observability platform unifying session replays, logs, metrics, traces and errors powered by ClickHouse and OpenTelemetry.
ClickStack - the open-source observability stack for OpenTelemetry at scale
ClickHouse® is a real-time analytics database management system
Source-available LLM router and AI cost optimizer. Routes simple prompts to cheap or local models and complex ones to premium models, automatically. Drop-in OpenAI-compatible proxy for Claude Code,…
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
Born is a modern ML framework for Go — train and deploy models as single binaries. Pure Go, zero CGO, GPU accelerated.