Highlights
Lists (1)
Sort Name ascending (A-Z)
- All languages
- Assembly
- C
- C#
- C++
- CSS
- Cairo
- Clojure
- CoffeeScript
- Coq
- Cuda
- Dart
- Dockerfile
- Elixir
- Fluent
- FreeMarker
- Go
- HCL
- HTML
- Haskell
- Java
- JavaScript
- Jupyter Notebook
- Lean
- Lua
- MDX
- Makefile
- Markdown
- Nix
- Odin
- PHP
- PLpgSQL
- Python
- Ruby
- Rust
- Scala
- Shell
- Solidity
- Starlark
- Swift
- TeX
- TypeScript
- V
- Vim Script
- Visual Basic .NET
- Zig
Starred repositories
NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.
Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.
The orchestrator for agentic workloads. A fast, high-density and scalable orchestrator for every workload an agent needs.
Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat.
A free, open source, and extensible speech-to-text application that works completely offline.
Accelerate high-latency GEO inflight Wi-Fi via warm BBR TCP multiplexing + 1-RTT Ground-TLS + zlib (zero dependencies)
NVIDIA Kubernetes Engine (NVKE). A management plane for GPU Kubernetes on bare metal.
Ceph is a distributed object, block, and file storage platform
A research prototype for zero-knowledge proofs of AI inference. Not maintained.
A library for integration-testing against docker containers from within Rust.
Open source SDK to build Muse gadgets
AMD SEV-SNP PoC with SVSM, KBS proxy, virtio-blk device, and stateful vTPM
Home for Cluster API, a subproject of sig-cluster-lifecycle
An agentic skills framework & software development methodology that works.
Scalar is an open-source API platform: 🌐 Modern REST API Client 📖 Beautiful API References …
A thread-per-core async Rust runtime with IOCP/io_uring/polling.
Open source inference engine that tunes its kernels on your hardware to find the fastest way to run each model. 2x faster than Ollama. Works on Apple Silicon, NVIDIA, AMD, Intel, or just a CPU.
Tools for post-mortem debugging of the tokio runtime
agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL).
AI agents running research on single-GPU nanochat training automatically
OpenShell is the safe, private runtime for autonomous AI agents.
Attested confidential inference k8s framework
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Terminal interface to find, download, and stream movies, TV shows, and live TV using local media players.
Agent Executor (AX) is Google's open agentic orchestration runtime