convez.ai
MCP ServerDevOps & InfraestruturaAvançado
jbeshir

Demesne

jbeshir/demesne

Orquestração de agentes IA em containers isolados com controle de segurança

Ver no GitHub
InicialPluginScore · de 0 a 100

MCP server que orquestra agentes de IA e comandos shell em contêineres OpenSandbox descartáveis e isolados. Permite executar scripts não confiáveis, renderizar React, converter mídia e orquestrar múltiplos agentes com segurança via montagens somente leitura e allowlists de egresso.

Instalação

$npx convez-ai jbeshir/demesne

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
71%
Último commit
há 3 semanas
Versão
v0.2.0
Issues abertas
4
Contribuidores
1

Casos de uso

  • Executar scripts e comandos em sandboxes descartáveis sem risco ao host
  • Renderizar widgets React e fazer screenshots via headless browser
  • Orquestrar múltiplos agentes IA com tarefas delegadas e verificação
  • Transcodificar mídia e processar imagens em ambiente isolado
  • Pesquisa autônoma com acesso à internet controlado

Veredito

Ferramenta poderosa para execução segura de código e orquestração de agentes, mas ainda em fase alpha com quebras esperadas. Ideal para quem precisa executar tarefas autônomas complexas mantendo o host isolado por camadas de segurança — contêiner, mount read-only e egress allowlist.

README

A tradução para o português deste README ainda está na fila.

Demesne

An agent-agnostic, local, containerised agent-orchestration MCP server you drive from your agent of choice. It runs untrusted shell, scripts, and AI coding agents in disposable containers, decoupling agent reasoning from execution effects. Host mounts are read-only; outbound network access is governed by egress allowlists.

License Latest Release CI

[!WARNING] Alpha — best-effort. demesne is early software, and is largely built using itself (its own containerised agents do much of the work). Expect rough edges, gaps, and breaking changes between versions. Treat it as alpha and best-effort, and review what it does before relying on it.

What you can do

Ask your agent to run through demesne:

  • One-off scripts — execute a shell command in a fresh sandbox and collect output. Example
  • Headless React-widget rendering — render and screenshot a React widget inside a sandbox via the demesne-built browser image (Playwright + Chromium + Node 22, works at egress=none). How-to
  • Video / audio / image conversion — transcode, convert, and manipulate media inside a sandbox via the demesne-built media image (ffmpeg + ImageMagick + libvips + audio tooling, works at egress=none). How-to
  • Long-running research with open internet — spawn a research agent with unrestricted outbound access. Reference
  • Delegated coding-agent tasks — hand off a prompt to a sub-agent running inside a sandbox. Example
  • Persistent sessions — create a sandbox, run multiple commands, upload/download files, then destroy it. Example
  • Multi-agent orchestration — the orchestrator agent is itself a containerised run that spawns child sandboxes for its workers and verifier, dispatching tasks and judging results across the tree. Example
  • Ready-made orchestration skills — a library of SKILL.md pipeline definitions (migration sweeps, corpus map-reduce, document ETL, and more) to drop into your agent and adapt. Pre-alpha: in principle ready to use but largely untested — regard them as examples of what could be tried. Example skills

Together these let your agent take on larger tasks more autonomously: you can push security-review-awkward script execution, autonomous research, and entire multi-agent pipelines into containers that run with no permission prompts — much of the autonomy you'd otherwise reach for --dangerously-skip-permissions to get, but with the host kept at arm's length by a container boundary, read-only mounts, and egress allowlists. (That boundary is container-level isolation, not a hard security guarantee — see SECURITY.md.) And you don't pre-declare the pipeline: your agent composes the orchestration prompt itself for the task at hand, and the containerised orchestrator adapts the layout and subagents as it runs.

How it works

Containerised agents can themselves spawn sandboxes, and — with appropriate configuration — get a read-only subset of your host's MCP server tools proxied in through a per-sandbox tunnel. See docs/reference/nested-sandboxes.md.

Get started

a. Install the binary

Download a release binary from the GitHub releases page. Builds are available for linux/amd64, darwin/amd64, darwin/arm64, and windows/amd64.

To build from source instead, see CONTRIBUTING.md.

b. Run a local OpenSandbox

demesne needs a running OpenSandbox instance. See docs/reference/requirements.md for prerequisites; Step 2 of the Quickstart walks through launching one locally.

c. Wire into Claude Code or Codex

See docs/how-to/wire-into-mcp-client.md for the per-client config snippets and full env var reference.

For the full walkthrough, see Quickstart.

Tools

ToolDescriptionReference
sandbox_scriptRun a shell command in a fresh sandbox and tear it down. Returns exit code, stdout, stderr, and the /out host path.ref
sandbox_createCreate a persistent sandbox. Returns a sandbox_id handle and the /out host path. TTL is 24h, refreshed by each sandbox_exec.ref
sandbox_execRun a shell command in an existing sandbox. Refreshes TTL. Returns exit code, stdout, and stderr.ref
sandbox_uploadCopy a host file into an existing sandbox.ref
sandbox_downloadCopy a file out of an existing sandbox; written under <output_dir>/downloads/<basename>. Returns the host path.ref
sandbox_destroyKill an existing sandbox. Host output dir is preserved.ref
sandbox_agentRun an AI coding agent (codex or claude-code — defaults to codex when Codex credentials are configured, otherwise claude-code) in a fresh sandbox against a caller-supplied prompt. Outbound HTTPS is restricted to the vendor proxy. Returns exit code, stdout, stderr, the /out host path, and the (indicative) cost summary.ref
sandbox_researchRun a long-running research agent with no input mounts and unrestricted outbound internet access. Returns exit code, stdout, stderr, the /out host path, and the (indicative) cost summary.ref

For a step-by-step walkthrough of the persistent-sandbox lifecycle, see the Quickstart and the sandbox_create / sandbox_exec reference pages.

Docs

QuickstartFive steps to your first sandbox_script call
DocsTutorials, how-to recipes, reference, explanation
ExamplesRunnable example calls
Example skillsReady-to-use orchestration pipelines you can adapt (pre-alpha)

Contributing

See CONTRIBUTING.md for building from source, linting, and tests.

Status

See CHANGELOG.md for milestone history.

Ver o original no GitHub

Bom para

Relacionados