- Hamilton, Ontario, Canada
- https://brendanduke.ca
Highlights
- Pro
Stars
- All languages
- Assembly
- C
- C#
- C++
- CMake
- CSS
- Common Lisp
- Crystal
- Cuda
- Cython
- Dockerfile
- Emacs Lisp
- F#
- Forth
- GLSL
- Go
- HCL
- HTML
- Haskell
- Java
- JavaScript
- Julia
- Jupyter Notebook
- Kotlin
- LLVM
- Lean
- Lua
- MATLAB
- MDX
- MLIR
- Makefile
- Markdown
- Mojo
- NASL
- Nix
- OCaml
- Objective-C
- Odin
- PHP
- PLpgSQL
- Perl
- PowerShell
- Python
- R
- Racket
- Rich Text Format
- Rust
- SWIG
- Sass
- Scala
- Shell
- Starlark
- Svelte
- Swift
- SystemVerilog
- Tcl
- TeX
- Tree-sitter Query
- TypeScript
- VBScript
- VHDL
- Verilog
- Vim Script
- Vue
- WebAssembly
- Zig
⌥ Coding agent with the IDE wired in. Built by Stencil Labs.
A clean, modular SDK for building AI agents with OpenHands V1.
🙌 OpenHands: AI-Driven Development
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
Halo is an open-source framework built by White Circle for training large language and multimodal models
A rich terminal UI for GitHub that doesn't break your flow.
AI-Driven Scientific, Algorithmic, and Systems Discovery
A helm plugin that shows a diff explaining what a helm upgrade would change
⎈ Multi pod and container log tailing for Kubernetes
FlyDSL is the Python front‑end of the project: a Flexible Layout Python DSL for expressing tiling, partitioning, data movement, and kernel structure at a high level.
Iterative agent harness improvement: run a coding agent on a hard task, generate the reusable tooling it was missing, qualify it, and replay fresh sessions with it activated. Works with Codex and C…
AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solution.
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
SANA & Sol: Efficient Generative Models and Full-Stack Training & Inference Engines for Image, Video, and World Modeling
TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration
Session-scoped /goal workflow for OpenCode with fail-closed persistence and an independent completion verifier. Maintenance mode: OpenCode 2.2.1+ ships a built-in /goal.
Ideogram 4: Open image model at the forefront of design
NVIDIA FastGen: Fast Generation from Diffusion Models
Conveniently export torch.compile compiled products into self-contained Python files