sandbase-harness
Local-first AI agent runtime and DSH plugin bundle providing sandboxed sessions, MCP tools, audit logs, and session replay.
Install
$ dsh plugin --profile web add -w ../sandbase-harnessPlugin 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
- Integrates with DeepSeek Harness via stdio MCP bridge and Cordis configuration patch
- Provides sandboxed execution across local processes, Docker containers, Kubernetes, and worker queues
- Persistent SQLite session tracking with resumable Server-Sent Events (SSE)
- Audit logs, session replay, and permission policy enforcement for MCP tools
- Built-in web console for agent and session inspection and management
Useful For
- Running auditable coding agents with strict tool permission policies and Docker/Kubernetes isolation
- Extending DeepSeek Harness with native session replay, credential management, and remote execution
- Orchestrating multi-turn agent tasks with local or hosted LLM endpoints
Who It Fits
- DeepSeek Harness developers needing sandboxed agent execution
- Engineers running auditable local or self-hosted AI agent infrastructure
- AI automation builders managing multi-tool MCP environments
Documented Limitations
- Requires Node.js >= 22
- Local source checkout or HTTPS git installation required; unscoped npm package is unrelated
- Docker or Kubernetes infrastructure needed for containerized sandbox backends
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 14 runtime, 15 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
- sandbaseai/sandbase-harness
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- 42b5a73 · 2026-09-30
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
- 678GitHub stars
- Forks
- 75
- Open issues
- 18
- Last commit
- 2026-09-30
- Last release
- 2026-08-30
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Compatibility bridge and host ABI enabling unmodified Pi plugins to run natively on DeepSeek Harness.
View plugin →Preview, create, and edit spreadsheets, docs, slides, and canvases in DeepSeek Harness powered by Univer.
View plugin →Persistent multi-model Agent teams and bounded DAG workflows with GUI controls for DeepSeek Harness.
View plugin →Bundle of 88 open-source Agent Skills for research, business intelligence, marketing, and SEO in DeepSeek Harness.
View plugin →