general

Development rules for TT Studio, a web application for managing and interacting with AI models on Tenstorrent hardware.

In plain words
What is it for?
Use them when building TT Studio features involving its React frontend, Django API, model types, containers, hardware, or remote endpoints.
Why use it?
They give contributors shared project context, architecture constraints, licensing requirements, and implementation conventions.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/tenstorrent/tt-studio/general
Clone the repo
git clone --depth 1 https://github.com/tenstorrent/tt-studio

Made for: Cursor.

Per session 948 This file is loaded in full into every session.
When invoked 948 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00948 $0.00948
Opus 5 $0.00474 $0.00474
Sonnet 5 $0.00190 $0.00190
Haiku 4.5 $0.00095 $0.00095

Measured 2d ago against content hash 028a79aaa989, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

general scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/general.mdc · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TT Studio General Development Rules

You are an expert developer working on TT Studio, a web-based AI model management and interaction platform for Tenstorrent hardware.

Project Context

TT Studio is designed to:

  • Provide an intuitive GUI for deploying AI models on Tenstorrent hardware
  • Support multiple AI model types: Chat (LLMs), Vision (YOLO), Speech (Whisper), Image Generation
  • Handle automatic hardware detection and containerized model execution
  • Integrate with TT Inference Server and TT-Metal framework
  • Offer both local hardware and remote API endpoint connectivity

SPDX License Requirements

MANDATORY: Every new file MUST include appropriate SPDX headers:

Python files:

# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: © 2026 Tenstorrent AI ULC

JavaScript/TypeScript files:

// SPDX-License-Identifier: Apache-2.0
// SPDX-FileCopyrightText: © 2026 Tenstorrent AI ULC

Architecture Overview

  • Frontend: React + TypeScript + Vite (port 3000)
  • Backend: Django REST API (integrated with frontend)
  • TT Inference Server: FastAPI (port 8001)
  • Containerization: Docker for model isolation
  • Hardware: Tenstorrent AI accelerators (auto-detected)

Development Workflow

  1. Setup & Environment

    • Use python run.py for all setup and management (NOT startup.sh)
    • Automatic submodule handling - no manual git submodule commands needed
    • Environment variables: JWT_SECRET, HF_TOKEN, DJANGO_SECRET_KEY, TAVILY_API_KEY
    • Support both --dev and production modes
  2. Code Quality Standards

    • Follow TypeScript strict mode settings
    • Use ESLint configuration with header requirements
    • Implement proper error handling for AI model operations
    • Consider hardware availability in all model-related features
  3. Testing Philosophy

    • Focus on business logic and user workflows
    • Test AI model deployment and inference flows
    • Mock hardware dependencies appropriately
    • Test error scenarios (hardware unavailable, model failures)

Read the full file on GitHub · 131 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 131 lines · 948 tokens per session scan A 028a79aaa989

Subscribe to this mod's changes

general is a cursor rule published in the GitHub repository tenstorrent/tt-studio (49 stars, last pushed 4d ago), licensed Apache-2.0. It adds 948 tokens to every session, about $0.0047 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.