# Trae IDE / TraeCode Download Choose TraeCode for a coding workspace or TraeWork for task-oriented AI assistance. Get the current release directly from TRAE. Canonical URL: https://aiidelist.com/blog/traeide-download Language: en Published: 2026-10-03 Updated: 2026-10-03 > Editorial snapshot from September 2026. Prices, models and interface labels may change; this is a practical guide, not a live product feed. Choose TraeCode for a coding workspace or TraeWork for task-oriented AI assistance. Get the current release directly from TRAE. ## Platform support | Product | Platform | What to check | | --- | --- | --- | | TraeCode | macOS 12.0+ · Apple Silicon | Match the architecture shown in the official selector. | | TraeCode | Windows 10 / 11 · x64 | Match the architecture shown in the official selector. | | TraeCode | Linux · .deb | Select the package format for your distribution; verify its architecture. | | TraeCode | Linux · .rpm | Select the package format for your distribution; verify its architecture. | | TraeWork | Web | Open TraeWork Web from the official TRAE website. | | TraeWork | Mobile | Use the store link offered by TRAE for your device and region. | ## System requirements & architecture The download center lists macOS 12.0+ and Windows 10/11, alongside Linux packages for TraeCode. Requirements and available architectures may change. Use the current download selector rather than a version number copied from a third-party page. ## Apple Silicon or Intel? Check “About This Mac” for your chip or processor. The currently visible official selector offers Apple Silicon. If you have an Intel Mac, confirm availability with TRAE instead of installing an old mirrored build or an incompatible ARM package. ## Install and get started 1. Open the official download center and select TraeCode or TraeWork. 2. Choose the operating system and architecture that match your device. 3. On macOS, open the downloaded disk image and follow its installation steps. On Windows, run the official installer and verify its publisher. 4. On Linux, install the .deb or .rpm with your distribution’s package manager. Review dependencies before continuing. 5. Launch the app, sign in, then check your plan and model access before starting a large task. ## TraeWork: desktop, web and mobile The official center lists macOS and Windows desktop options, web access and mobile entry points. Choose the current option for your device; mobile availability can vary by store and region. ## Before and after installation Where should I download TRAE? TRAE’s official international website is trae.ai. Use its download center and support channels for installation files and account issues. Is TRAE free? There is a limited Free plan. Paid plans and model usage are separate from downloading the app. Check the current pricing guide and official plan page before subscribing. How do I update TRAE? Save your work, use the client’s update option when available, or return to the official download center. Recheck extensions and integrations after a major update. How do I uninstall it? Quit the app and use your operating system’s normal application removal process. On Linux, use the package manager that installed it. Back up settings first; remove user data only if you intend to reset it. What if installation fails? Check OS support and architecture, record the exact error and verify the file came from TRAE. Do not disable system protections or run an unverified installer to work around a warning. Can TraeWork replace an IDE? Choose according to the task. Engineering work that depends on project navigation, debugging and extensions is a reason to keep a coding environment. Compare TraeWork and TraeCode before switching. ## Related guides ## A complete first task: change, verify and review 1. Choose a small repository that already builds. Save a clean Git checkpoint and write down the command that currently passes. This gives you a baseline for distinguishing an existing problem from a generated regression. 2. Describe one observable result: for example, add a required field to an existing form and show an error without submitting invalid data. Include the relevant files, existing validation helper and the behavior that must stay unchanged. 3. Ask for a short plan before editing. Check that it names the affected components, data flow and verification command. Resolve missing context before allowing a broad refactor. 4. Review the diff in small batches. Check dependencies, generated files, environment variables and error handling as well as the visible result. Run the project checks and exercise both the successful and failing paths. 5. Inspect the usage record after the task. Record the accepted outcome, review time and usage consumed. Repeat on a second representative task before choosing a paid plan or moving a team workflow. ## A task brief you can adapt ```text Goal: describe the user-visible change. Context: list the relevant files and existing implementation. Constraints: keep the public API and use the existing dependencies. Verification: run the repository's documented checks and test the failure path. Completion: summarize changed files, checks performed and remaining limitations. ``` ## When the result is not usable A successful request does not prove the code works. If the agent edits the wrong files, reduce the scope and supply the entry point explicitly. If a command fails, reproduce it in the same terminal environment before changing the prompt. If an MCP connection fails, separate server startup, credentials and client configuration. If usage is exhausted, check the account balance and selected model before repeating the same request. Keep a failed patch small enough to revert without losing unrelated work. ## Common questions before you switch ### Does a paid subscription mean unlimited agent work? No. Subscription price, included usage, model access and additional usage are different things. A plan with unlimited autocomplete does not imply unlimited model requests or cloud tasks. ### Should I connect every MCP server at once? Start with the one integration needed by your current task. Confirm that it starts, exposes the expected tools and receives only the intended project context before adding another. ### How should I compare two AI editors? Use the same repository, task and acceptance checks. Compare correct changes, review effort, setup friction and recorded usage. A long feature list does not establish which editor produces better code for your project. ## Related TRAE guides - [TRAE product overview](/ide/trae) - [TraeCode Guide](/blog/traeide-traecode) - [TraeWork Guide](/blog/traeide-traework) - [TRAE Pricing: TraeCode & TraeWork](/blog/traeide-pricing) - [TRAE Models & Model Access](/blog/traeide-models) - [TraeWork vs TraeCode (Trae IDE)](/blog/traeide-traework-vs-traecode) - [Trae MCP Setup & Troubleshooting](/blog/traeide-mcp) - [Rules for AI Coding Workflows](/blog/traeide-rules)