multi-agent

AKO4X: Accelerate GPU Kernel Tuning with Multi‑Agent Campaign Loops

Optimize your GPU kernels faster using AKO4X’s extensible, closed‑loop multi‑agent system—ideal for founders needing performance gains without deep manual tuning.

From the repo · “Agentic Kernel Optimization — advanced & eXtensible: a closed-loop, campaign-based multi-agent system for optimizing GPU kernels (benchmark-swappable; default flashinfer-bench).”

83 stars+2★ this week14 forksPythonGuide quality 8/10 · reviewed Oct 23Updated 9/15/2026100% free · open source
What it does

AKO4X optimizes GPU kernels using a closed-loop multi-agent system, allowing startup founders to improve the performance of their GPU-based applications

When to use it
  • •When you need to optimize GPU kernels for deep learning or other compute-intensive workloads
  • •When you want to automate the optimization process using a closed-loop system
  • •When you need to benchmark and compare the performance of different GPU kernels
Ready-to-paste prompt
python run.py --bench flashinfer-bench --kernel your_kernel_name --agents 4 --epochs 10
Heads up: Make sure you have the necessary GPU drivers and CUDA version installed, as AKO4X relies on GPU acceleration to function properly
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/ako4x && curl -fsSL https://workflowstacks.com/api/skills/ako4x/claude-skill -o ~/.claude/skills/ako4x/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How AKO4X: Accelerate GPU Kernel Tuning with Multi‑Agent Campaign Loops works
Codeflow
Free to inspect

AKO4X: Accelerate GPU Kernel Tuning with Multi‑Agent Campaign Loops is a large Python project (~46k lines across 72 code files). It is a full software project: use it through its install path rather than reading it end to end. Last commit a month ago, MIT license, no tests found.

Size
Large codebase
~46k lines · 72 code files · ~6 h to skim
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Python
No API keys detected
Python 100%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    CLAUDE.md
    The instructions the AI actually follows
  3. 3
    pyproject.toml
    Dependencies and the commands it exposes
  4. 4
    ako4x/__init__.py
    Inside ako4x/ — the main logic begins here
What's in each folder
READMENo tests foundDocumentedNo CIMIT licenseUpdated 1 mo ago
Quick Actions
Details
Creator
TongmingLAIC
Language
Python
Category
multi-agent
Published
3/23/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/ako4x.svg)](https://workflowstacks.com/skills/ako4x?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.