ai-agent

tt-metal: Accelerate AI Kernel Development with Proven Library

tt-metal gives founders a high‑performance TT‑NN operator library and low‑level kernel model to speed up GPU‑based AI workloads. Ideal for teams building LLMs, diffusion or video generation on Tenstorrent hardware. 1.7k+ GitHub stars.

From the repo · “:metal: TT-NN operator library, and TT-Metalium low level kernel programming model.”

1,717 stars+11★ this week780 forksPythonGuide quality 9/10 · reviewed Oct 6Updated 10/22/2026100% free · open source
What it does

TT-Metal provides a low-level kernel programming model for founders to leverage GPU acceleration with C++

When to use it
  • •You need fine-grained control over GPU acceleration for a specific AI task
  • •Your application requires optimized performance and customization of neural network operators
  • •You're working with a team that prefers C++ for building high-performance computing applications
Ready-to-paste prompt
Compile an example TT-Metal program with `g++ -o example example.cpp -I./include -L./lib -ltt-metal`
Heads up: Ensure you have a compatible C++ compiler and GPU drivers installed, as TT-Metal requires specific versions for optimal performance
Saves to your device
Use with Claude
New

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

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/tt-metal && curl -fsSL https://workflowstacks.com/api/skills/tt-metal/claude-skill -o ~/.claude/skills/tt-metal/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.

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

31
top-level files
20
folders
2321.1M
source size
Apache-2.0
license
Key files
.pre-commit-config.yaml
README.md
File tree
.cursor/
.github/
cmake/
contributing/
dockerfile/
docs/
infra/
model_tracer/
models/
releases/
scripts/
tech_reports/
tests/
third_party/
tools/
tt_metal/
tt_py_test_utils_common/
tt_stl/
tt-train/
ttnn/
.clang-format
.clang-format-ignore
.clang-tidy
.codechecker.json
Quick Actions
Details
Creator
tenstorrent
Language
Python
Category
ai-agent
Published
2/13/2023

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/tt-metal.svg)](https://workflowstacks.com/skills/tt-metal?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.