# Free alternatives to Agentic CUDA Kernel Optimizer

Agentic CUDA Kernel Optimizer: A langgraph based workflow with a C++ CUDA suite to optimize CUDA kernels

Agentic CUDA Kernel Optimizer itself: Free (its own site, checked 2026-11-20).

24 products that do a similar job and cost nothing to start: 21 free outright, 3 with a free plan. Closest in meaning first. Each price was read from the product's own site on the date shown.

Page: https://nowfound.app/free-alternatives/agentic-cuda-kernel-optimizer
All alternatives, paid too: https://nowfound.app/alternatives/agentic-cuda-kernel-optimizer.md
About Agentic CUDA Kernel Optimizer: https://nowfound.app/launch/agentic-cuda-kernel-optimizer.md

| # | Product | Price | Checked | What it does |
|---|---|---|---|---|
| 1 | [Demo of Agent Based Model on GPU with CUDA and](https://nowfound.app/launch/demo-of-agent-based-model-on-gpu-with-cuda-and-opengl-window) | Free | 2026-11-21 | Demo of agent based model on GPU with CUDA and OpenGL (Windows/Linux) Agent instances on GPU memory Uses SSBO for instanced objects (with GLSL 450 shaders) CUD… |
| 2 | [RightNow CLI](https://nowfound.app/launch/rightnow-cli) | Free | 2026-11-21 | RightNow CLI is an open-source command-line tool that uses Claude to assist with CUDA kernel development. |
| 3 | [Tiny-vLLM](https://nowfound.app/launch/tiny-vllm-high-performance-llm-inference-engine-in-c-and-cud) | Free | 2026-11-20 | Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM |
| 4 | [GPT-2 implemented using graphics shaders](https://nowfound.app/launch/gpt-2-implemented-using-graphics-shaders) | Free | 2026-11-21 | Back in the old days, people used to do general-purpose GPU programming by using shaders like GLSL. This is what inspired NVIDIA (and other companies) to event… |
| 5 | [Matrix Multiplication with Half the](https://nowfound.app/launch/matrix-multiplication-with-half-the-multiplications) | Free | 2026-11-21 | Algebraic enhancements for GEMM & AI accelerators. |
| 6 | [GitNexus (Akon Labs)](https://nowfound.app/launch/gitnexus-akon-labs) | Free plan, paid from $29/mo | 2026-09-05 | The open-source kernel for coding agents |
| 7 | [Cuq](https://nowfound.app/launch/cuq-formal-verification-of-rust-gpu-kernels) | Free | 2026-11-21 | A pipeline that translates Rust GPU code into formal Coq models, as a foundation for memory model proofs |
| 8 | [Cerebrium](https://nowfound.app/launch/cerebrium) | Free plan | 2026-11-21 | If you haven’t noticed, GPUs are scarce right now. The global boom in inference has demand growing faster than supply can keep up, and at Cerebrium ... |
| 9 | [dsc](https://nowfound.app/launch/i-built-a-tensor-library-from-scratch-in-c-cuda) | Free | 2026-11-21 | DSC is a tensor library built from scratch in C++ with CUDA support, designed for running small language models locally. |
| 10 | [Boldly go where Gradient Descent has never gone](https://nowfound.app/launch/boldly-go-where-gradient-descent-has-never-gone-before-with) | Free | 2026-11-21 | Trying to do gradient descent using automatic differentiation over branchy programs? Or to combine them with neural networks for end-to-end training? Then this… |
| 11 | [80% faster, 50% less memory, 0% loss of](https://nowfound.app/launch/80-faster-50-less-memory-0-loss-of-accuracy-llama-finetuning) | Free | 2026-11-21 | This project provides an optimized implementation for finetuning Llama models using QLoRA and LoRA techniques on local GPUs. |
| 12 | [Agent Kernel](https://nowfound.app/launch/agent-kernel-three-markdown-files-that-make-any-ai-agent-sta-47486287) | Free | 2026-11-21 | Minimal kernel to make any AI coding agent stateful. Clone, point your agent, go. |
| 13 | [DSH Desktop](https://nowfound.app/launch/dsh-desktop) | Free | 2026-11-11 | Official app for DeepSeek’s open-source agent harness |
| 14 | [HyperFrames Studio (Desktop)](https://nowfound.app/launch/hyperframes-studio-desktop) | Free plan, paid from $25/mo | 2026-11-04 | The First Video Editor built for Agents |
| 15 | [Luminal](https://nowfound.app/launch/luminal-open-source-search-based-gpu-compiler) | Free | 2026-11-21 | Luminal is an open-source GPU compiler that automatically generates optimized GPU kernels for AI models. |
| 16 | [A free, GPU-accelerated Texas Hold'em GTO](https://nowfound.app/launch/a-free-gpu-accelerated-texas-hold-em-gto-solver-in-c-cuda) | Free | 2026-11-20 | TexasSolver GPU is the world’s first GPU solver for poker, combining strategy study, decision practice, node locking, tree configuration, and batch solving in… |
| 17 | [Richard](https://nowfound.app/launch/richard-a-cnn-written-in-c-and-vulkan-no-ml-or-math-libs) | Free | 2026-11-21 | This started out as a personal effort to learn more about machine learning. It's currently a CLI app where you give it a JSON file specifying your network arch… |
| 18 | [Finyuus](https://nowfound.app/launch/finyuus) | Free | 2026-11-20 | A code-first language for durable, governed AI workflows |
| 19 | [Flow](https://nowfound.app/launch/flow-a-dynamic-task-engine-for-building-ai-agents) | Free | 2026-11-21 | Flow is a task engine for building AI agents that uses dynamic task queues instead of static graph structures. |
| 20 | [Hopper](https://nowfound.app/launch/hopper) | Free | 2026-11-20 | Hopper is an agentic development environment designed for mainframe and COBOL systems. |
| 21 | [devpit](https://nowfound.app/launch/devpit) | Free | 2026-10-22 | A native control room for your Claude Code agents |
| 22 | [cuTile Rust](https://nowfound.app/launch/cutile-rust-safe-data-race-free-gpu-kernels-in-rust) | Free | 2026-11-20 | cuTile Rust provides a safe, tile-based kernel programming DSL for the Rust programming language. It features a safe host-side API for passing tensors to async… |
| 23 | [NanoEuler](https://nowfound.app/launch/nanoeuler-gpt-2-scale-model-in-pure-c-cuda-from-scratch) | Free | 2026-11-20 | NanoEuler is a GPT-2 scale language model built from scratch in pure C and CUDA. |
| 24 | [An ncurses CUDA-based fluid simulation](https://nowfound.app/launch/an-ncurses-cuda-based-fluid-simulation) | Free | 2026-11-21 | This project is an ncurses-based fluid simulation that leverages CUDA for computational performance. |
