# Agentuity v1 Reaches Beta

> **Update:** Agentuity v1 is now live! [Read the launch announcement →](/content/blog/agentuity-v1-is-here/index.html)

We're excited to announce that **Agentuity v1 has reached beta**. Since launching the [public preview](/content/changelog/2025-12-09/index.html) in early December the team has been heads-down building, and this release marks a major step toward our official launch:

- _Sandbox infrastructure_ for isolated code execution in any language
- _SSH access_ to running agents for live debugging
- _Framework-agnostic frontend_ with type-safe RPC
- _Built-in authentication_ powered by BetterAuth
- _First-class evaluations_ to test agent quality
- [And much more!](https://github.com/agentuity/sdk/releases/tag/v0.1.0)

Here's a look at some of the highlights.

## Sandbox Infrastructure

Sandboxes give your agents isolated Linux containers with their own filesystem, network, and configurable resources. Your agents are written in TypeScript, but sandboxes can run _any_ language: Python, Node.js, shell scripts, or anything available via `apt install`.

Use [sandboxes](https://agentuity.dev/services/sandbox) for code execution agents, AI coding assistants, automated testing, or validating generated code before returning it to users.

```
# List your sandboxes
agentuity cloud sandbox list

# SSH into a sandbox
agentuity cloud ssh --sandbox
```

On the SDK side, sandboxes integrate naturally with your agent code. Each sandbox gets dedicated memory, CPU, and disk, all visible from the CLI.

## Type-Safe Frontend and RPC

We introduced the [`@agentuity/frontend`](/content/blog/december-19-2025-update#framework-agnostic-frontend-package/index.html) package and [type-safe API calling](/content/blog/december-19-2025-update#type-safe-api-calling/index.html) in our December 19 update. Since then, we've added type-safe path and query parameters with automatic extraction from route definitions, ergonomic positional arguments for path params, and fixed optional params handling in the `useAPI` hook.

```
import { createAPIClient } from '@agentuity/react';

const api = createAPIClient();

// Type-safe path params with positional arguments
const user = await api.users.userId.get('123');
const member = await api.organizations.orgId.members.memberId.get('org-456', 'user-789');

// Type-safe query params
const results = await api.search.get({ query: { q: 'agents', limit: '10' } });
```

For the full API, check out the [RPC client docs](https://agentuity.dev/frontend/rpc-client).

## Built-in Authentication

The `@agentuity/auth` package provides [first-class authentication](https://agentuity.dev/frontend/authentication) powered by [BetterAuth](https://www.better-auth.com/). It includes API key support, organization management, JWT tokens, and CLI commands for setup:

```
# Initialize auth in an existing project
agentuity project auth init

# Manage API keys
agentuity auth apikey
```

On the server side, protect your routes with middleware:

```
import { createSessionMiddleware } from '@agentuity/auth';

router.get('/api/profile', createSessionMiddleware(auth), async (c) => {
  const user = c.var.user;
  return c.json({ id: user.id });
});
```

## Workbench

We covered [Workbench setup](/content/blog/december-19-2025-update#workbench-updates/index.html) in our December 19 update. Since then, we've added execution metadata (token counts and duration) in thread messages, URL deep linking so you can share workbench URLs with pre-selected agents, and minification-safe schema detection for production builds. You can now also run Workbench against live deployed agents directly from the [web app](https://app.agentuity.com/). Run `agentuity dev` and open `/workbench` to try it locally.

## Built-in Evals Suite

New to the beta: a [first-class evaluations system](https://agentuity.dev/agents/evaluations) for testing your agents. Evals are automated tests that run after your agent completes, validating output quality and monitoring performance without blocking responses.

The `@agentuity/evals` package ships with **12 preset evaluations** including politeness, safety, PII detection, conciseness, adversarial prompt detection, and more. You can also write custom evals for your specific use cases.

Evals come in two types:

- **Binary** (pass/fail) for yes/no criteria like safety checks
- **Score** (0-1) for quality gradients like relevance or helpfulness

Results appear in the [web app](https://app.agentuity.com/), so you can track agent quality over time. No external tooling required.

## SSH into Running Agents

Need to debug a live agent? You can now SSH directly into running cloud agents and sandboxes:

```
# SSH into a running deployment
agentuity cloud ssh

# Copy files from a running agent
agentuity cloud scp download /path/to/file ./local-file
```

This makes debugging production issues much easier. No more guessing what's happening inside your agent. For setup instructions, see the [debugging docs](https://agentuity.dev/reference/cli/debugging).

## Explore the SDK (and More)

The new [SDK Explorer](https://agentuity.dev/) is an interactive playground for learning the Agentuity platform. Browse live examples covering services (KV, Vector, Object Storage, AI Gateway), I/O patterns (streaming, SSE, durable streams), and more. Each example includes plain-language explanations of the concepts involved, plus reference code you can copy and drop into your own projects.

## Also Shipping

Beyond the highlights above, here's what else we've been building:

**VS Code Extension**

- Agent, Data, and Deployment explorers in the sidebar
- AI chat participant for workspace-aware assistance
- Dev server lifecycle management from the IDE
- 8 new language model tools for managing agents and deployments

**GitHub Integration**

- `agentuity git link` and `git unlink` commands
- Connect repos for automatic deployments
- `agentuity integration github connect`/`disconnect`

**Configuration System**

- Next.js-style `agentuity.config.ts` with Vite HMR and plugin support
- Custom Bun plugins, Tailwind CSS, and compile-time constants
- All build phases respect custom configuration

**New Default Template**

- The `agentuity create` command now scaffolds a translation agent demo
- Includes AI Gateway integration, React frontend with Tailwind, thread state, and evals
- A hands-on starting point for exploring the platform

**Developer Experience**

- Rust-style TypeScript error formatting
- Async lazy-loaded thread state (eliminates 100-150ms latency)
- Ergonomic positional arguments for RPC path params
- Improved DNS developer experience for custom domains

**Stability**

- 52 bug fixes including dev server stability, hot reload, type inference, and S3 compatibility
- Better process cleanup and stale process detection
- Terminal cursor restoration and CI-friendly output

All changes are backward compatible.

## Upgrade Now

Ready to try the beta? Run:

```
agentuity upgrade
```

Or if you're starting fresh:

```
curl -fsSL https://agentuity.sh | sh
```

Once you're on the beta, try out a few of the new features:

- Launch Workbench with `agentuity dev` and open `/workbench`
- List your sandboxes with `agentuity cloud sandbox list`
- Add evals to your agents using the `@agentuity/evals` package

* * *

## Resources

- [v1 Documentation](https://agentuity.dev/)
- [SDK Explorer](https://agentuity.dev/)
- [Web App](https://app.agentuity.com/)
- [Discord Community](https://discord.gg/agentuity)
- [GitHub SDK](https://github.com/agentuity/sdk)
- [Full Changelog](https://github.com/agentuity/sdk/releases/tag/v0.1.0)

We'd love your feedback as we work toward 1.0. Happy building!