dsh-plugin-vm-sandbox
A DeepSeek Harness web plugin that provides per-session OrbStack VM sandboxes with native conversation UI and model tools.
Install
No clear install command was found in the current repository evidence.
Plugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Adds a VM tab with VM, snapshots, jobs, audit, and network/sharing subviews.
- Provides model tools for VM creation, execution, lifecycle management, deletion, uploads/downloads, and status.
- Supports snapshots, restoration, scheduled VM tasks, and automatic snapshot retention policies.
- Supports port forwarding, network allowlists, sharing policies, and VM-to-VM service discovery.
- Supports templates, initialization scripts, cloud-init, hot CPU/memory/disk resizing, and image import/export.
- Records metrics history and supports multi-machine execution groups with fail-fast or continue strategies.
Useful For
- Give each DeepSeek Harness conversation an isolated Debian or Alpine VM environment.
- Let models execute tasks and manage sandbox VM lifecycles through exposed tools.
- Run scheduled workloads, inspect background-job output, and review VM operation audits.
- Create reusable development environments from templates or initialization configuration.
- Coordinate workloads across multiple VMs while applying network and sharing policies.
Who It Fits
- DeepSeek Harness web-profile users
- Teams using OrbStack-hosted development or execution sandboxes
- Developers building agent workflows that need session-scoped VM environments
Documented Limitations
- Supports the DeepSeek Harness web profile.
- Requires @deepseek-ai/dsh-client-runtime and @deepseek-ai/dsh-client-ui-conversation.
- Requires OrbStack installed and running on the host, with orb available at /usr/local/bin/orb.
- State is persisted locally at ~/.dsh/vm-sandbox/state.json.
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as Apache-2.0.
A root package.json was captured and can be inspected by the registry.
package.json declares a prepare lifecycle script that may run during relevant package installation workflows.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- GHJIVHIDD/dsh-plugin-vm-sandbox
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 9926752 · 2026-08-26
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 3GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-08-26
- Last release
- 2026-08-20
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Sandbox-first automatic permission policy and intelligent risk classification for DeepSeek Harness.
View plugin →Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Local-first AI agent runtime and DSH plugin bundle providing sandboxed sessions, MCP tools, audit logs, and session replay.
View plugin →Second-model AI auto-review for DeepSeek Harness approval requests with fail-closed safety and session audit.
View plugin →