by
AI-powered code assistance and autonomous software agents integrated into IDEs and terminals, delivering context‑aware autocomplete, task automation, and code generation to streamline development workflows.
Augment Code provides a platform that combines a proprietary context engine with frontier LLMs (including GPT‑5 and Sonnet 4) to give developers real‑time, code‑aware AI assistance. It enables autonomous agents that can plan, write, test, and open pull‑requests, while also offering smart autocomplete, terminal command execution, and deep IDE integrations.
Q: Which models does Augment Code support? A: It currently supports GPT‑5, Sonnet 4, and other frontier models via the Model Picker.
Q: Is my proprietary code safe? A: Yes. All code stays within your environment by default; any external model calls are encrypted and optional.
Q: Can I use Augment Code with private repos? A: Absolutely. The context engine indexes private repositories locally and never exposes them unless you explicitly allow it.
Q: What IDEs are supported? A: Visual Studio Code, JetBrains suite (IntelliJ, PyCharm, etc.), Vim, and Neovim.
Q: How do autonomous agents execute commands? A: Agents can run terminal commands automatically or with your approval, mimicking a real developer workflow.
Now supporting GPT-5 and Sonnet 4 →
Better Context. Better Agent.
Better Code.
The most powerful AI software development platform backed by the industry-leading context engine.
Take the lead with local or remote agents to complete tasks end-to-end. Agents can plan, build, and open PRs for you to review.
Trusted by engineers at
Proprietary context retrieval combined with cutting-edge frontier models give you code you can ship to production.
Read more: A real time index of your codebase
From autonomous coding agents to precise refinements with codebase-aware autocomplete, you can move quickly through any project with the help of AI.
Cutting edge retrieval understands your codebase–large or small.
Works in Visual Studio Code, JetBrains IDEs, Vim and Neovim.
Native support for the most essential tools in your workflow.
Agents can run commands in your terminal–with approval or automatically–to work just like you do.
Pull in additional context and work with 100+ external tools for your stack.
Add AI automation in your dev workflow or use our TUI to have the best agent in your terminal
Apply suggestions from chat intelligently to your code in one click.
Your code is secure and private by default.
Prioritize specific files in your code and reference third-party docs.
Start with a simple prompt and expand it with codebase-specific details for precise changes.
Customize Augment with your best practices and preferences.
Break complex problems into trackable steps without losing context
Add screenshots and wireframes to include additional context.
Augment Code is the rare platform that lives up to, and surpasses, AI hype.
Chintan Shah
VP Engineering
±
§
!
1
@
2
£
3
$
4
%
5
^
6
&
7
*
8
(
9
)
0
_
=
delete
Q
W
E
R
T
Y
U
I
O
P
{
[
}
]
|
\
A
S
D
F
G
H
J
K
L
:
;
"
'
~
`
Z
X
C
V
B
N
M
<
,
.
?
/
fn
⌃
control
⌥
option
⌘
command
⌘
command
⌥
option
◀
▲
▼
▶
Install Augment and try it for free.
Please log in to share your review and rating for this MCP.
Discover more MCP servers with similar functionality and use cases
by zed-industries
Provides real-time collaborative editing powered by Rust, enabling developers to edit code instantly across machines with a responsive, GPU-accelerated UI.
by cline
Provides autonomous coding assistance directly in the IDE, enabling file creation, editing, terminal command execution, browser interactions, and tool extension with user approval at each step.
by continuedev
Provides continuous AI assistance across IDEs, terminals, and CI pipelines, offering agents, chat, inline editing, and autocomplete to accelerate software development.
by github
Enables AI agents, assistants, and chatbots to interact with GitHub via natural‑language commands, providing read‑write access to repositories, issues, pull requests, workflows, security data and team activity.
by block
Automates engineering tasks by installing, executing, editing, and testing code using any large language model, providing end‑to‑end project building, debugging, workflow orchestration, and external API interaction.
by RooCodeInc
An autonomous coding agent that lives inside VS Code, capable of generating, refactoring, debugging code, managing files, running terminal commands, controlling a browser, and adapting its behavior through custom modes and instructions.
by lastmile-ai
A lightweight, composable framework for building AI agents using Model Context Protocol and simple workflow patterns.
by firebase
Provides a command‑line interface to manage, test, and deploy Firebase projects, covering hosting, databases, authentication, cloud functions, extensions, and CI/CD workflows.
by gptme
Empowers large language models to act as personal AI assistants directly inside the terminal, providing capabilities such as code execution, file manipulation, web browsing, vision, and interactive tool usage.