RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]

A free, open source, and extensible speech-to-text application that works completely offline.

KEDA is a Kubernetes-based Event Driven Autoscaling component. It provides event driven scale for any container running in Kubernetes

A high-performance and light-weight router for vLLM large scale deployment

Full Networking Stack for Mojo🔥

High-performance JSON library for Mojo🔥 with GPU acceleration

Karpenter is a Kubernetes Node Autoscaler built for flexibility, performance, and simplicity.

Light, fluffy, and always free - The AWS Local Emulator alternative

Easily and securely send things from one computer to another 🐊 📦

C++ port of Microsoft VibeVoice built on ggml

Open-Source Frontier Voice AI

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

On-prem/LAN Layer 2 & 4 availability monitoring with realtime guarantees & decaying alert pacing. Multithreaded high speed availability checking for SNMP, PING, TCP/UDP, QUIC & HTTP/S resources inc…

The open source control plane for agentic engineering.

GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a git repository (Github, Gitlab, Azure, Local) or…

AI gateway / AI control plane / AI proxy written in Go. Unified OpenAI-compatible and Anthropic-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI, Ollama, vLLM and more. A LiteLLM alternative…

Open source AI clip generator: turns long videos into viral 9:16 shorts with AI moment detection, face tracking, subtitles and dubbing. Self-host free with Docker (MIT), or use the cloud with GPU s…

Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

An autonomous novel writing pipeline, by Hermes Agent

Simple bookmark manager built with Go

A vector index built on TurboQuant, written in Rust with Python bindings

Assign issues to Claude Code, Codex, Cursor, and 17 more coding agents like teammates — open-source and self-hostable.

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

The universal proxy platform

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…

The best-benchmarked open-source AI memory system. And it's free.

Chromium running inside your terminal

Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential controls.