HHostingByteSoftware
Ctrl K
ComunidadGuías…

README.md

Rama main · réplica de lectura del repositorio original.

Archivo original ↗Preguntar a KiBot
<p align="center">
  <img src="website/static/img/astrabox-mark.svg" alt="AstraBox" width="72" height="72" />
</p>

<h1 align="center">AstraBox</h1>

<p align="center">
  <strong>The open-source, self-hosted alternative to Claude Managed Agents.</strong>
</p>

<h3 align="center"><a href="https://demo.astrabox.ai/">Try AstraBox online →</a></h3>

<p align="center">
  Explore the console and run an Agent in a sandbox.<br />
  The demo has its own model, network and session limits.
</p>

<p align="center">
  Open source · Self-hosted · Apache-2.0
</p>

<p align="center">
  <a href="https://github.com/Colton-z/AstraBox/actions/workflows/ci.yml"><img src="https://github.com/Colton-z/AstraBox/actions/workflows/ci.yml/badge.svg" alt="CI" /></a>
  <a href="LICENSE"><img src="https://img.shields.io/badge/license-Apache--2.0-blue.svg" alt="Apache-2.0" /></a>
  <a href="https://www.astrabox.ai/"><img src="https://img.shields.io/badge/docs-English-4f46e5" alt="Documentation" /></a>
  <a href="https://www.astrabox.ai/zh-Hans/"><img src="https://img.shields.io/badge/文档-简体中文-4f46e5" alt="Chinese documentation" /></a>
</p>

<p align="center">
  <strong>English</strong> · <a href="README.zh-CN.md">简体中文</a>
</p>

<p align="center">
  <img src="docs/img/demo-session.gif" alt="A Session in the AstraBox console: the Agent writes a Python script in its sandbox, runs it, and streams back the output" />
</p>

AstraBox runs the Agent programs you already use (Claude Code, Codex,
DeepSeek Harness, Pi and Hermes) as cloud Agents on your own infrastructure,
with a model service compatible with the selected Agent program. It handles
sandboxes, streaming, state and credentials, so you do not have to turn an
Agent program into a service yourself.

```bash
curl -fsSL https://raw.githubusercontent.com/Colton-z/AstraBox/main/scripts/install.sh | bash
```

One command on a Linux host or WSL 2 with Docker. The installer asks which
model service to use and prints the console address, <http://127.0.0.1:8088>.
See the [Quickstart](#quickstart) for requirements.

- **The vendor's own Agent program** — each Agent runs the real Claude Code,
  Codex or other program inside its sandbox, so the program's own tools and
  session format carry over.
- **Starts in seconds, survives a lost sandbox** — prewarmed sandboxes start
  conversations quickly, and each program's native session is kept in the
  platform database and restored into a new sandbox on the next message. A
  confirmed sandbox loss fails the affected execution; AstraBox does not
  automatically replay its task.
- **Protected credentials** — with protected delivery enabled, credentials are
  injected at the egress boundary and the Agent sees a placeholder.
- **Reachable from anywhere** — the web console, HTTP API, CLI, MCP, schedules,
  signed webhooks, and messaging platforms such as Slack, Discord, Telegram,
  WhatsApp and LINE.

Already looking at Claude Managed Agents? See
[how AstraBox compares](docs/compare-claude-code-self-hosted.md).

**One platform for team Agents and personal Assistants.** An
[Agent](docs/authoring-agents.md) is a reusable cloud Agent for teams and
automation, started from the web console, the API, schedules, webhooks,
messaging platforms or an MCP client. An [Assistant](docs/assistants.md) is one
person's long-lived cloud workspace: all of its conversations share one
workspace and the Agent program's state.

## Core concepts

| Concept | Description | Analogy |
| --- | --- | --- |
| **Environment** | A deployment boundary with its own Agents, access rules, credentials, conversations, jobs and runtime resources | "An isolated business environment" |
| **Agent** | A reusable configuration for a cloud Agent powered by an installed Agent program | "Cloud teammate" |
| **Assistant** | A personal workspace with native memory, Skills and jobs shared across its conversations | "Personal cloud assistant" |
| **RuntimeProfile** | An Environment-local recipe selecting the Agent program, sandbox image, model connection, network access and lifecycle | "Desk and toolbox" |
| **Session** | One stateful Agent execution, including its messages, Events, and current state | "A specific piece of work" |
| **Event** | The real-time output and state changes produced by a Session | "Live progress feed" |

Through these resources, developers can run interactive or long-running tasks,
connect remote or local MCP servers, Plugins, Skills, and repositories, trigger
Agents from schedules, webhooks, APIs, and messaging platforms, and protect
access with authentication, authorization, isolated sandboxes, and managed
credentials.

[Explore AstraBox capabilities →](docs/capabilities.md)

## Find, share and connect Agents

- **Agent pages and share links** — open `/agents/{agent_id}` for an Agent
  and share that page. Recipients sign in when required and start their own
  conversation under the existing access rules. A share link does not grant access.
- **Existing-conversation A2A** — discover your own Agent conversations by their
  generated titles and Agent names, then send work to a selected conversation
  with its native context intact. An Agent administrator configures whether its
  Agent can discover no targets, all accessible Agents, or selected Agents.
  This does not expose another user's conversations or channel conversations.
- **Scoped administration** — Agent administrators manage their Agents'
  triggers and runs, inspect session logs, and export logs for the Agents they
  administer. Platform-wide settings remain with platform administrators.

See [Agent authoring](docs/authoring-agents.md), [A2A](docs/a2a.md),
[Sessions](docs/sessions.md) and [automation](docs/deployments.md).

## Enterprise infrastructure included

Each Environment has its own deployment state and business database. Separate
Environments use distinct database roles and credentials, even when they share
a PostgreSQL service. RuntimeProfiles configure execution inside an Environment;
they do not create another Environment. See [deployment isolation](docs/deploy.md#environments).

One deployment brings up the pieces a team usually assembles by hand:

- **Artifacts** — Agents and Assistants publish durable, versioned pages with share links and live data. See the [artifact guide](docs/artifacts.md).
- **Model gateway** — [LiteLLM](https://github.com/BerriAI/litellm) is bundled
  and on by default: one route name per model, upstream keys held on the
  server, budgets and usage logs, and any Anthropic, OpenAI-compatible or local
  provider behind it. See [Connect a model](docs/models.md).
- **Team login** — [Casdoor](https://github.com/casdoor/casdoor) is
  pre-integrated as the identity provider: OIDC, organizations and roles, and
  sign-in through the identity providers an administrator adds in Casdoor, such
  as Google, Microsoft Entra ID, Okta, GitHub, SAML or LDAP. The installer turns
  it on with `ASTRABOX_INSTALL_TEAM_LOGIN=casdoor`, and a clone
  with one Compose overlay; see [Team login](docs/team-login.md).
- **Isolated sandboxes** — [OpenSandbox](https://github.com/opensandbox-group/OpenSandbox)
  on one Docker host or a Kubernetes cluster, with warm capacity so
  conversations start in seconds.
- **Credentials outside the sandbox** — enable protected delivery to inject
  Vault credentials at the sandbox's egress boundary, with placeholders in
  the Agent program. See [credential protection](docs/egress-credential-injection.md).
- **Channels and triggers** — schedules, signed webhooks and messaging
  platforms through official [Satori](https://github.com/satorijs/satori)
  adapters.

## Manage it from a terminal, or let a coding agent do it

The `astrabox` CLI configures and uses a local or remote deployment without the
web console. Its results can be printed as JSON, so a coding agent such as
Claude Code or Codex can run the same commands for you.

- **Configuration as code** — `astrabox init --from-deployment` exports a
  deployment's RuntimeProfiles and Agents to `astrabox.yaml`; `astrabox diff`
  previews an edit and `astrabox apply` creates or updates resources, never
  deleting any.
- **Tasks from the command line** — `astrabox run <agent> "<task>"` starts a
  Session, sends the task and streams the reply; `--session` continues an
  existing Session.
- **Output a program can read** — with `--output json` a command prints one
  JSON object whether it succeeds or fails, and each kind of failure has its
  own exit code.
- **MCP tools** — `astrabox mcp serve` offers schema, get, export, diff, apply,
  status and run as MCP tools over stdio.
- **Local or remote** — `astrabox up`, `down` and `logs` run the local Compose
  deployment from a source checkout; the other commands reach any deployment
  with `--endpoint` and a bearer token or OAuth client credentials.

Install the CLI from a source checkout with `make install`. Deployments
(schedule, webhook and messaging triggers) and answers to an Agent's questions
are managed in the web console or the HTTP API. See the
[CLI overview](docs/cli/overview.md).

## Included Agent programs

| Agent program | Sandbox image | Used for |
| --- | --- | --- |
| Claude Code | `ghcr.io/colton-z/astrabox-sandbox-claude-code` | Agent |
| Codex | `ghcr.io/colton-z/astrabox-sandbox-codex` | Agent |
| DeepSeek Harness | `ghcr.io/colton-z/astrabox-sandbox-deepseek-harness` | Agent |
| pi | `ghcr.io/colton-z/astrabox-sandbox-pi` | Agent |
| Hermes Agent | `ghcr.io/colton-z/astrabox-sandbox-hermes` | Assistant |

Other Agent programs can be added with a compatible sandbox image. See
[Add an Agent program](docs/writing-an-engine-adapter.md).

## Built to extend

Each replaceable part of AstraBox is a Python interface with a plugin
registration point. An installed package registers its implementation under
the matching entry-point group, and AstraBox selects it by name; an unknown
name fails with an error instead of falling back to a default.

| Extension point | Entry-point group | Built in |
| --- | --- | --- |
| Agent program | `astrabox.providers.engine` | Every included Agent program |
| Sandbox backend | `astrabox.providers.sandbox` | OpenSandbox on Docker or Kubernetes |
| Model service | `astrabox.providers.model` | LiteLLM gateway |
| Messaging platform | `astrabox.providers.channel` | Messaging platform gateway, generic JSON webhook |
| Identity provider | `astrabox.web.identity` | Local mode, OIDC, verified JWT, trusted identity headers |
| Secret Store | `astrabox.providers.secrets` | Local encryption, AWS KMS |
| Workspace storage | `astrabox.providers.storage` | Mounted volume, Amazon EFS |
| Remote MCP server source | `astrabox.providers.extensions` | Administrator records in AstraBox, LiteLLM MCP gateway |
| [Runtime preparation integrations](docs/providers/runtime-preparation.md) | `astrabox.providers.runtime_preparation` | Optional deployment-owned Agent resources, Session materials, preparation before each message and user prerequisites |
| [Channel response judges](docs/providers/channel-response.md) | `astrabox.providers.channel_response` | Built-in title-model judge; deployment-owned judge |

- **Interface version** — a plugin under `astrabox.providers.*` can set
  `seams_api_version` to the interface version it was built against; AstraBox
  refuses to load it when that differs from its own.
- **Conformance suites** — `astrabox.testing` ships reusable test suites for
  sandbox backends, workspace storage, messaging platforms, Agent programs and
  schedulers; bind one in the plugin's own tests.
- **Application extensions** — entry points for API routes, middleware,
  lifespan hooks and service implementations extend the application itself.

See [Add an Agent program](docs/writing-an-engine-adapter.md),
[Add a messaging platform](docs/writing-a-channel-provider.md),
[Use AstraBox from a Python application](docs/embedding.md) and
[Extensions](docs/architecture.md#plugin-interfaces).

## Workflow

1. **Deploy AstraBox** — run the service and OpenSandbox on one Docker host,
   Kubernetes, or infrastructure you already operate.
2. **Configure a RuntimeProfile** — choose the Agent program, sandbox image, model
   connection, network access, and lifecycle.
3. **Create an Agent** — select the RuntimeProfile and model in the web console,
   then add a system prompt, MCP servers, Plugins, Skills, or a repository only
   when the Agent needs them.
4. **Start a Session** — open the Agent and start a Session.
5. **Send messages and receive Events** — follow live output, answer questions
   or approvals, and return later without keeping the original browser open.

## Quickstart

### Prerequisites

- A Linux host (or WSL 2) running Docker Engine 26.0 or later with the Compose
  plugin 2.17.0 or later, and a user that can use the Docker socket
- An API key for a model service: Anthropic, DeepSeek, or another Anthropic- or
  OpenAI-compatible service

Install the latest release with one command:

```bash
curl -fsSL https://raw.githubusercontent.com/Colton-z/AstraBox/main/scripts/install.sh | bash
```

The installer asks which model service your Agents use, installs the deployment
into `~/astrabox`, pulls the published images, starts them, and prints the
console address once the console answers. Open <http://127.0.0.1:8088>. Select
a RuntimeProfile, create an Agent, and start your first Session from the console.

![Create an Agent in the AstraBox console](docs/img/agent-create-console-en.png)

The local deployment listens on loopback and requires no login until you turn
on team login, which the installer does with `ASTRABOX_INSTALL_TEAM_LOGIN=casdoor`.
Before exposing it to another network, put it behind an HTTPS proxy as described
in [Team login](https://www.astrabox.ai/docs/team-login#put-the-login-flow-behind-a-proxy).

Read the [release notes](https://github.com/Colton-z/AstraBox/releases) before
upgrading. Run the installer again to install the latest release while retaining
Sessions, credentials and settings. Use matching server and runtime image
versions; existing sandboxes keep their installed CLI until they are replaced.
Choose `ASTRABOX_ENVIRONMENT_NAME` before the first startup and keep it stable;
changing it does not copy data into another Environment.

### Run from a clone

Building the images from a checkout takes longer and is the path for changing
AstraBox itself:

```bash
git clone https://github.com/Colton-z/AstraBox.git
cd AstraBox

make build-agent-image

export ANTHROPIC_API_KEY="your-anthropic-api-key"
export ANTHROPIC_MODEL="your-model-name"
scripts/compose.sh up --build -d
```

For the complete setup and API alternative, see the
[Quickstart](https://www.astrabox.ai/docs/quickstart). For the installer settings,
Kubernetes, or an existing OpenSandbox service, see
[Deploy AstraBox](https://www.astrabox.ai/docs/deploy).

Prewarming prepares the Agent runtime before a Session claims it. New Agents
have it on in the bundled deployments, and each one holds an idle prepared
sandbox; see [capacity planning](docs/deploy.md#plan-capacity-for-prepared-sandboxes).
Native conversation state is stored in the platform database; a persistent workspace
volume is optional and preserves task files separately. For multiple API
replicas or sandbox nodes, see [distributed deployment](docs/deploy-distributed.md)
and [workspace storage](docs/deploy.md#where-conversation-workspaces-live).

## When to use AstraBox

- **Long-running asynchronous tasks** — let work continue after the developer's
  computer or browser disconnects.
- **API integration** — use an Agent from an application without building and
  operating a separate Agent runtime.
- **Batch processing** — run multiple Sessions for independent requests.
- **Scheduled and event-driven work** — start Agents from a schedule, webhook,
  external system, or messaging platform.

Local Agent programs remain the best fit for interactive development on one
computer. AstraBox makes the same kind of Agent available remotely and to other
systems; the two approaches complement each other.

## Documentation

- [Overview](docs/overview.md)
- [Quickstart](docs/quickstart.md)
- [Define an Agent](docs/authoring-agents.md)
- [Run a Session](docs/sessions.md)
- [Connect MCP servers, Plugins, and Skills](docs/adding-tools.md)
- [Automate Agent work](docs/deployments.md)
- [Connect messaging platforms](docs/channels.md)
- [Deploy AstraBox](docs/deploy.md)
- [HTTP API](docs/api.md)
- [Agent-to-Agent communication](docs/a2a.md)
- [Release notes · English and 简体中文](https://github.com/Colton-z/AstraBox/releases)

## Development

```bash
make install
make build-agent-image
make build-assistant-image
make dev
```

Open <http://127.0.0.1:5173>. See [CONTRIBUTING.md](CONTRIBUTING.md) for the
maintained workflow.

## Contributing

Issues and pull requests are welcome. Start with
[CONTRIBUTING.md](CONTRIBUTING.md).

## Acknowledgements

AstraBox stands on the shoulders of these open-source projects:
[OpenSandbox](https://github.com/opensandbox-group/OpenSandbox),
[LiteLLM](https://github.com/BerriAI/litellm),
[Casdoor](https://github.com/casdoor/casdoor),
[Satori](https://github.com/satorijs/satori),
[DBOS Transact](https://github.com/dbos-inc/dbos-transact-py),
[mergerfs](https://github.com/trapexit/mergerfs),
[AIO Sandbox](https://github.com/agent-infra/sandbox),
[shadcn/ui](https://github.com/shadcn-ui/ui),
[Vercel AI SDK and AI Elements](https://github.com/vercel/ai) and
[Docusaurus](https://github.com/facebook/docusaurus) — and it runs the Agent
programs [Codex](https://github.com/openai/codex),
[Hermes Agent](https://github.com/NousResearch/hermes-agent),
[DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness),
[Pi](https://github.com/earendil-works/pi) and
[Claude Code](https://github.com/anthropics/claude-code). [NOTICE](NOTICE) lists
every attribution and license.

## License

Apache License 2.0. See [LICENSE](LICENSE).

Claude and Claude Code are trademarks of Anthropic; OpenAI and Codex are
trademarks of OpenAI. AstraBox is an independent project, not affiliated with
or endorsed by them. Claude Code is proprietary software used under Anthropic's
terms; see [NOTICE](NOTICE).