Mammouth Code
Mammouth Code is Mammouth AI's terminal-based coding agent.
➡️ Get your API key — required to use Mammouth Code.
This project is open source and available on GitHub.
Installation
Run one of the following commands in your terminal.
curl -fsSL "https://code.mammouth.ai/install.sh" | bashirm "https://code.mammouth.ai/install.ps1" | iexUse in your Terminal
Simply type mammouth to run the coding agent.
Default model
The first time you set up Mammouth Code, it uses mammouth-recommended as the default model — a shortcut that always routes to whatever model Mammouth currently considers the best for its price. See Mammouth Recommended for details.
Use in your IDE
For the best experience, open Mammouth Code in the integrated terminal of your IDE (VS Code, Cursor, WebStorm, etc.):
- Open the integrated terminal in your IDE
- Navigate to your project directory
- Run:
mammouth
That's it — Mammouth Code will start an interactive session right in your terminal.
Continue a previous session
There are 2 ways to continue a previous session:
- Run
mammouthas usual, then use the/sessionscommand to switch to an old session. - Run
mammouth -cto continue the last session used in the current folder.
Update
To update Mammouth Code to the latest version:
mammouth upgradeThis will fetch and install the latest version, replacing the old one while keeping your configurations and sessions intact.
Uninstall
To completely remove Mammouth Code from your system:
mammouth uninstallThis will remove Mammouth Code along with its configurations and sessions.
Token Consumption in Mammouth Code
Mammouth Code dynamically injects system prompts depending on what you ask it to do — which explains the ~10k additional tokens you may notice.
What might look like "heavy" prompts actually saves tokens on larger projects: they allow the LLM to read only the relevant files, rather than loading your entire codebase into context. That overhead looks significant when working on a single file, but the real purpose is to route the request to the right tool for the task at hand.
A simple rule of thumb:
- 📁 Use Mammouth Code if your project has 10+ files, or if you're working with a long context — which covers most real-world programming projects.
- 💬 Use the standard Mammouth interface if you're dealing with a manageable context: two or three files, ~500 lines max (e.g., trying to understand a specific function — unless you're deep into triple-inherited OOP classes 😄).
Usage Tracking Accuracy
The price and token consumption estimator shown in the terminal might not always reflect the exact cost in real-time. To track your actual API usage, please check the dashboard at mammouth.ai/app/account/api.
Note on Claude Haiku: This smaller model is currently used to generate session titles. This will be configurable in a future update.
Model Effort Levels
When using Mammouth Code, you can switch model variants by pressing Ctrl+P and selecting Switch model variant (or Ctrl+T for quick cycling through the variant). This lets you choose an effort level for supported models.
What are effort levels?
Effort levels control extended thinking — how much time and tokens the model spends reasoning before responding.
| Level | Reasoning | Best For |
|---|---|---|
| Default | Off | Standard tasks, fastest response, lowest token cost |
| Low | On (minimal) | Simple tasks that benefit from light reasoning |
| Medium | On (moderate) | Most tasks — good balance of speed and depth |
| High | On (maximum) | Complex problems, architecture decisions, hard bugs |
Higher effort means more thorough reasoning but slower responses and higher token consumption.
INFO
Not all models support effort levels. Extended thinking is only available on select models. For models that don't support it, this option will not be available.
When to use each level
- 🟢 Default — Quick edits, simple questions, file navigation
- 🔵 Low — Refactoring, small feature additions
- 🟡 Medium — Multi-step tasks, debugging, code reviews
- 🔴 High — Complex algorithms, architectural decisions, hard-to-reproduce bugs