# Claude Code

> A coding harness with memory, desktop scheduling, and cloud sessions. Tracked as adjacent because its primary scope is software work.

- **Maker:** Anthropic
- **Catalogue type:** Coding tool (adjacent)
- **Website:** https://code.claude.com/docs/en/overview
- **Source code:** unknown — no public repository recorded
- **Also known as:** unknown — no other names recorded
- **Evidence:** 11 sources, checked 2026-10-21 to 2026-10-21
- **Profile:** https://agentlist.wiki/agent/claude-code/
- **This record:** https://agentlist.wiki/agents/claude-code.md

## Key facts

| Field | Value | Status | Sources |
| --- | --- | --- | --- |
| Availability & access | Available | documented | 1 |
| Price & usage costs | Subscription or API usage | documented | 8 |
| Included in another plan | Claude Pro / Max; API option | documented | 8 |
| Where it runs | Terminal, IDE, desktop, and cloud sessions | documented | 1 |
| Open source & license | unknown | unknown | — |
| Controls your computer | unknown | unknown | — |
| Its own computer | unknown | unknown | — |
| Works while your computer is off | unknown | unknown | — |
| If the vendor stops | unknown | unknown | — |
| Remote shut-off | unknown | unknown | — |
| What you keep | unknown | unknown | — |
| Company type | Major AI lab | documented | 10 |
| Launch date | Feb 24, 2025 | documented | 11 |

Status marks — `documented`: Supported by official documentation; not independently tested. `limited`: Only partial or conditional support established. `unknown`: Not established by reviewed sources; does not mean unsupported.

## Company & launch

*Who makes it and when it arrived. Company type and funding are context, not a quality score: an open-source project and a public company carry different risks, not better or worse ones.*

- **Company type** `documented` — Major AI lab [10]
- **Company stage** `documented` — Series H [10]
- **Disclosed funding** `documented` — US$65B · Series H · May 28, 2026 [10]
- **Launch date** `documented` — Feb 24, 2025 · Research preview [11]

**Launch history**

- 2025-02-24 · Research preview [11]

## What it can do

*What this agent can actually operate — a machine of its own, yours, or neither. Computer control is three separate questions, and most products answer only some of them.*

- **What stands out** `documented` — Works directly in a codebase; can be scripted in CI or controlled from a phone. [5, 6]
- **Computer use** `limited` (partial or conditional only) — Local desktop control: macOS and Windows through Desktop, macOS through CLI; CLI requires Pro/Max and interactive use. [2]
- **Controls your computer** `unknown` — Not specified — no reviewed source answers this, which is a gap in the catalogue rather than a "no".
- **Its own computer** `unknown` — Not specified — no reviewed source answers this, which is a gap in the catalogue rather than a "no".
- **Works while your computer is off** `unknown` — Not specified — no reviewed source answers this, which is a gap in the catalogue rather than a "no".
- **Browser control** `documented` — Chrome extension for browser automation. [1]
- **Voice & ambient listening** `unknown` — Not specified — no reviewed source answers this, which is a gap in the catalogue rather than a "no".
- **Background work & triggers** `limited` (partial or conditional only) — Desktop recurring tasks; configuration dependent [1]

## Apps & access

*Where you reach it and on what. A messaging integration is not a native app, so the two are tracked apart; an app listed here is a real first-party client.*

- **Native desktop apps** `documented` — Native Claude desktop app for macOS and Windows; Linux desktop is in beta. [3, 4]
- **iPhone & Android apps** `documented` — Claude apps for iOS and Android can start and steer cloud or remotely connected sessions; code runs elsewhere. [5]
- **Web & messaging** `documented` — Terminal, IDE, desktop, browser, mobile [1]
- **Messaging services** `unknown` — Not specified — no reviewed source answers this, which is a gap in the catalogue rather than a "no".
- **Native hardware** `unknown` — Not specified — no reviewed source answers this, which is a gap in the catalogue rather than a "no".
- **Developer API** `documented` — Agent SDK for Python and TypeScript, plus non-interactive CLI execution. [6]

## Models & plans

*What you pay and what runs underneath. Where an agent is bundled into a larger subscription, the price shown is that subscription's — there is no separate fee for the agent.*

- **Models & providers** `documented` — Claude models via subscription, API, or supported cloud providers. [7]
- **Bring your own model** `documented` — Claude subscription or own Anthropic API credentials; supported cloud providers include Amazon Bedrock, Google Cloud, and Microsoft Foundry. [1, 7, 8]
- **Included in another plan** `documented` — Included with eligible Claude subscriptions, including Pro and Max; shared plan limits or separate API billing. [8]
- **Price & usage costs** `documented` — Eligible Claude subscription usage or pay-as-you-go API billing. [8]

## Vendor lock-in

*How hard it is to leave, and what survives if the company does. Almost no hosted vendor publishes a shutdown commitment, so an answer here is usually read from the architecture rather than from a promise.*

- **If the vendor stops** `unknown` — Not specified — no reviewed source answers this, which is a gap in the catalogue rather than a "no".
- **Remote shut-off** `unknown` — Not specified — no reviewed source answers this, which is a gap in the catalogue rather than a "no".
- **What you keep** `unknown` — Not specified — no reviewed source answers this, which is a gap in the catalogue rather than a "no".

## Ownership & control

*What it asks before acting, what it remembers, and who else can see it. These are the questions that decide whether you would hand it your inbox.*

- **Open source & license** `unknown` — Not specified — no reviewed source answers this, which is a gap in the catalogue rather than a "no".
- **Where it runs** `documented` — Terminal, IDE, desktop, and cloud sessions [1]
- **Passwords & credentials** `unknown` — Not specified — no reviewed source answers this, which is a gap in the catalogue rather than a "no".
- **Approval before actions** `documented` — Configurable permission rules; manual approvals or automatic action review. [9]
- **What it remembers** `documented` — Project instructions and cross-session auto memory [1]
- **Edit & export your data** `unknown` — Not specified — no reviewed source answers this, which is a gap in the catalogue rather than a "no".
- **Privacy & isolation** `unknown` — Not specified — no reviewed source answers this, which is a gap in the catalogue rather than a "no".
- **Availability & access** `documented` — Multiple surfaces with account requirements [1]

## Plans

unknown — no published plan or price list is recorded. See the Price & usage costs claim above.

## Native apps and web access

*Messaging services are channels, not native apps, and are listed separately below.*

| Platform | Status | Detail | Sources |
| --- | --- | --- | --- |
| Web | Available | Terminal, IDE, desktop, browser, mobile | 1 |
| macOS | Available | Native Claude desktop app for macOS and Windows; Linux desktop is in beta. | 3, 4 |
| Windows | Available | Native Claude desktop app for macOS and Windows; Linux desktop is in beta. | 3, 4 |
| Linux | Beta | Native Claude desktop app for macOS and Windows; Linux desktop is in beta. | 3, 4 |
| iOS | Available | Claude apps for iOS and Android can start and steer cloud or remotely connected sessions; code runs elsewhere. | 5 |
| Android | Available | Claude apps for iOS and Android can start and steer cloud or remotely connected sessions; code runs elsewhere. | 5 |

## Messaging services

unknown — no messaging service is recorded for this agent.

## Hardware

`unknown` — no dedicated hardware is established by the reviewed sources.

## Data reach

*What personal data this agent can reach, and whether anyone else could reach the same source.*

unknown — no first-party or exclusive data reach is recorded for this agent.

## Discussion

unknown — no dated public threads are recorded for this agent.

## Feedback snapshot

unknown — no attributed feedback snapshot is recorded for this agent.

## Updates

**Where updates come from:** unknown — no update source has been recorded for this agent.

No dated catalogue updates mention this agent yet.

## Sources

1. [Claude Code overview](https://code.claude.com/docs/en/overview) — checked 2026-10-21
2. [Let Claude use your computer](https://code.claude.com/docs/en/computer-use) — checked 2026-10-21
3. [Claude Code desktop application](https://code.claude.com/docs/en/desktop) — checked 2026-10-21
4. [Claude Desktop on Linux (beta)](https://code.claude.com/docs/en/desktop-linux) — checked 2026-10-21
5. [Claude Code on mobile](https://code.claude.com/docs/en/mobile) — checked 2026-10-21
6. [Run Claude Code programmatically](https://code.claude.com/docs/en/headless) — checked 2026-10-21
7. [Claude Code deployment options](https://code.claude.com/docs/en/third-party-integrations) — checked 2026-10-21
8. [Use Claude Code with your Pro or Max plan](https://support.claude.com/en/articles/11145838-use-claude-code-with-your-pro-or-max-plan) — checked 2026-10-21
9. [Configure Claude Code permissions](https://code.claude.com/docs/en/permissions) — checked 2026-10-21
10. [Anthropic announces Series H financing](https://www.anthropic.com/news/series-h) — checked 2026-10-21
11. [Anthropic introduces Claude Code](https://www.anthropic.com/news/claude-3-7-sonnet) — checked 2026-10-21