bertaye/agentic-cuda-optimizer

A langgraph based workflow with a C++ CUDA suite to optimize CUDA kernels

AI agentsPython

2.7 Steady Magnitude out of 10 — how fast interest is growing, not a quality score. Star growth looks organic. Data as of September 25, 2026, 13:57 UTC.

Open on Seismograph Open on GitHub

About the project

An agentic CUDA kernel optimizer built on LangGraph that generates, validates, benchmarks, and iteratively refines kernels from a workload description, keeping the fastest correct variant.

Useful for

Generate and optimize a CUDA kernel for GEMM from a text workload description
Continue optimization from a previous run's best kernel via --initial-kernel
Profile candidates with Nsight Compute and feed counters into the next iteration

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

15 stars so far today, about 21 expected by the end of the day.
The repository is 1 day old and already has 12 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
Hacker News: “Show HN: Agentic CUDA Kernel Optimizer” — 22 points, 3 h ago.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 12
Today: 15 · ≈ 21 by evening
Forks: 0
Issues and pull requests: 0
Watchers: 0
Language: Python
Created: September 24, 2026
Last push: September 24, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Hacker News discussions

Show HN: Agentic CUDA Kernel Optimizer22 points, September 25, 2026

Spotted in

September 25, 2026Spotted on Hacker News

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/bertaye/agentic-cuda-optimizer.svg?lang=en)](https://gitnova.dev/en/r/bertaye/agentic-cuda-optimizer)

More in this category

8.6
paperclipai/paperclip
Open-source Node.js and React platform for orchestrating a team of AI agents: goals, org chart, budgets, tickets and audit. Suits teams running autonomous agents (Claude Code, Codex, Cursor, etc.) and wanting to manage…

BreakoutAI agentsTypeScript+645 stars today, ≈ 1,206 by evening
7.9
google/ax
A declarative orchestrator for running autonomous AI agent workloads in a cluster, using a Kubernetes-like model with Task, Workspace, Gateway, and Model manifests. It sandboxes agents, pre-wires their environment, and…

BreakoutAI agentsGo+357 stars today, ≈ 747 by evening
7.8
vectorize-io/hindsight
Hindsight is a long-term memory system for AI agents that stores facts and observations rather than just conversation history, reporting state-of-the-art results on the LongMemEval benchmark. It runs as a server…

BreakoutAI agentsPython+455 stars today, ≈ 909 by evening
7.6
NandhaKishorM/laya
Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.

CoolingAI agentsPython+563 stars today, ≈ 1,181 by evening
7.6
Contrastive-LM/CLM
CLM is a class of System One language models trained contrastively to connect states and actions; the repo serves CLM-8B behind a TypeSafe-compatible API for fast agent decision-making.

Early signalAI agentsPython+150 stars today, ≈ 346 by evening
7.0
strands-agents/harness-sdk
Open-source Python and TypeScript SDK for building and running AI agents: agent loop, tools, MCP, memory, multi-agent patterns and tracing in one package. Runs in your process with no hosted control plane and supports…

BreakoutAI agentsPython+66 stars today, ≈ 156 by evening