What is tt-studio CLAUDE.md?

A project guide for TT-Studio, a web interface for running artificial-intelligence models on Tenstorrent hardware. It describes the frontend, backend, inference service, agent service, databases, containers, ports, and startup command.

Starting, deploying, and developing TT-Studio, including its React frontend, Django backend, model inference services, Docker environment, and remote inference connections.

It gives contributors a map of the many services involved and clarifies which parts need local accelerator hardware. This reduces setup errors when running or changing the application.

How tenstorrent/tt-studio configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tenstorrent/tt-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tenstorrent/tt-studio/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/tenstorrent/tt-studio

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tenstorrent/tt-studio/claude-md/github.svg)](https://agentmods.dev/instructions/tenstorrent/tt-studio/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/tenstorrent/tt-studio/claude-md"><img src="https://agentmods.dev/badge/instructions/tenstorrent/tt-studio/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tenstorrent/tt-studio/claude-md"><img src="https://agentmods.dev/badge/instructions/tenstorrent/tt-studio/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,901 This file is loaded in full into every session.

When invoked 1,901 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01901	$0.01901
Opus 5.5	$0.00760	$0.00760
Sonnet 5.5	$0.00380	$0.00380
Haiku 4.5	$0.00190	$0.00190

Measured 21d ago against content hash 0d5b6a2b7e92, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tt-studio CLAUDE.md 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 21d 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.

CLAUDE.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TT-Studio

Web interface for running AI models on Tenstorrent hardware. It wraps TT Inference Server's packaging, containerization, and deployment automation around TT-Metal model execution. Full deployment needs a Tenstorrent accelerator (/dev/tenstorrent), but the frontend can also run against remote/cloud inference endpoints with no local hardware.

Use python run.py for everything — startup.sh is deprecated. There are no git submodules; run.py fetches the tt-inference-server artifact.

Architecture & ports

Service	Port	Runtime	What it is
Frontend	3000	Docker (Nginx in prod)	React 18 + TypeScript + Vite + Tailwind
Backend	8000	Docker	Django REST API via uvicorn (ASGI + Channels/WebSocket)
Inference server	8001	Host	FastAPI wrapper over tt-inference-server (`inference-api/`)
Agent	8080	Docker	LLM agent service (`app/agent/`)
ChromaDB	8111	Docker	Vector DB for RAG
Docker control	internal 8002	Docker (`tt_studio_network`)	JWT-secured Docker API wrapper (`docker-control-service/`)

Containers share the tt_studio_network bridge; the backend reaches Docker Control at http://docker-control:8002 and the inference API via host.docker.internal. Health checks: backend GET /up/ and GET /models/health/, inference server GET /health, frontend GET /.

Repo layout

app/backend/ — Django project. Apps: api (settings, ASGI/WSGI, URL routing), docker_control (image pulls, container deploy, model execution), model_control (model registry, inference, TTS), board_control (hardware detection / telemetry), vector_db_control (Chroma RAG), logs_control, wakeword_control (voice activation, WebSocket consumers), shared_config (model/device config, model sync). Routes in app/backend/api/urls.py.
app/frontend/ — React/TS/Vite app. Source under src/: components/, pages/, providers/, contexts/, hooks/, routes/, api/, lib/, types/. Backend proxy config in vite.config.ts.
app/agent/ — agent service. inference-api/ — FastAPI inference server.
docker-control-service/ — standalone Docker control service.
models/ — model definitions/config. dev-tools/ — license/header tooling.
dev-docs/ — developer docs. .cursor/rules/ — editor rules. .claude/skills/ — assistant skills.

Read the full file on GitHub · 119 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.

21d ago Changed · +7 lines · +150 tokens per session 0d5b6a2b7e92
1mo ago Changed · +5 lines · +180 tokens per session e6e943b20913
2mo ago First seen · 107 lines · 1,571 tokens per session scan A fce49e73cc78

Subscribe to this mod's changes

tt-studio CLAUDE.md is an instructions file published in the GitHub repository tenstorrent/tt-studio (52 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,901 tokens to every session, about $0.0076 per session on Opus 5.5. 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.

Planning React accelerator ai-agents backend-service chat-application ui-components

tt-studio CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tt-studio CLAUDE.mdtenstorrent/tt-studio	Instructions file	52	yesterday	Apache-2.0	A	1,901	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

tt-studio: Instructions file for Claude Code