feat: add sandbox overview page #90
Open
+204
−128
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Create new sandbox overview page as the entry point for the Sandbox section - Move lifecycle content (timeout, shutdown, get info) to dedicated lifecycle page - Update navigation to include new lifecycle page - Update Concepts component with sandbox overview and lifecycle cards - Verify and correct default configuration values (2 vCPUs, 2 GiB RAM, 22 GiB storage) - Fix startup time to ~100ms Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Keep cards inline in sandbox overview page instead of modifying shared component. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Use Sandbox.create() instead of Sandbox() in Python - Use expression '1 + 1' instead of print() to match result.text usage Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
mlejva
requested changes
Jan 29, 2026
docs/sandbox.mdx
Outdated
| | Internet | Enabled | | ||
|
|
||
| <Note> | ||
| These are defaults for the [code-interpreter](https://github.com/e2b-dev/code-interpreter) template. Custom templates can have different CPU/RAM configurations. |
Member
There was a problem hiding this comment.
Custom templates
Would add link to the custom templates section.
docs/sandbox.mdx
Outdated
| ## Retrieve sandbox information | ||
|
|
||
| You can retrieve sandbox information like sandbox ID, template, metadata, started at/end at date by calling the `getInfo` method in JavaScript or `get_info` method in Python. | ||
| A sandbox is an isolated cloud VM that starts in **~100ms**. Each sandbox has its own filesystem, can run processes, and has internet access. Sandboxes are designed to run AI-generated code safely. |
Member
There was a problem hiding this comment.
Suggested change
| A sandbox is an isolated cloud VM that starts in **~100ms**. Each sandbox has its own filesystem, can run processes, and has internet access. Sandboxes are designed to run AI-generated code safely. | |
| A sandbox is an agentic runtime which is an isolated cloud VM under the hood. Sandboxes can start in as little as **~100ms**. Each sandbox has its own [filesystem](/docs/filesystem), can start [processes](/docs/commands), and has internet access with [configurable firewall](https://e2b-ratart-e2b-docs-updates.mintlify.app/docs/sandbox/internet-access#fine-grained-network-control). | |
| Sandboxes are designed to run thousands of AI agents safely with access to the real-world tools as on your own computer. |
- Update intro text with links to filesystem, commands, and firewall - Add link to custom templates in Note section - Change description to "Secure runtime environments for AI agents"
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
/docs/sandbox/lifecyclepage