dsh-worlds

DeepSeek Harness Development & Runtime High risk

Runs the agent's filesystem, bash and PTY terminals inside a Docker container by providing the `ctx.fs` and `ctx.subprocess` seams, so cwd, environment and background processes survive a harness restart.

通过提供 `ctx.fs` 与 `ctx.subprocess` 接缝，把 agent 的文件系统、bash 与 PTY 终端跑在 Docker 容器里；工作目录、环境变量与后台进程可在 harness 重启后存活。

How to install

DeepSeek Harness dsh plugin add github:frozo-ai/dsh-worlds

About

dsh-worlds **Run the agent's execution world inside a container — so it survives the harness that started it.** DeepSeek Harness records this limitation in packages/terminal/terminal/README.md: "Sessions are process-local and are **not restored after a harness restart**." The session log is durable. The *computer* the agent was working on is not — the shell dies with the harness, taking your cwd, exported variables, and background processes with it. dsh-worlds fixes that by moving the execution world into a Docker container. No CRIU, no microVMs: a container simply outlives its client. harness…

GitHub ↗

Recommendation signals

46 Tool quality · Based on stars, downloads, maintenance, security and docs

– User interest · Adjusted by in-site views, install copies and download clicks

46 Overall

0views

0unique visitors

0install copies

0download clicks

0outbound clicks

Links

GitHub ↗ Report issue ↗

Basic safety check

Findings: curated 收录但无 npm 包/安装命令；无 license
Sources: curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Topics: deepseek-harness, docker, dsh, dsh-plugin, execution-world, sandbox

Related plugins

MCP Server New

Score100

langfuse

langfuse/langfuse

🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

☆ 33.5K ↓ 7.9M Development & Runtime ↗

Claude Code New

Score92

claude-code-templates

davila7/claude-code-templates

CLI tool for configuring and monitoring Claude Code

☆ 30.3K ↓ 17.1K Development & Runtime ↗

Claude CodeCodex New

Score83

loki-mode

asklokesh/claudeskill-loki-mode

Multi-agent autonomous SDLC framework. Spec to deployed app. PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers, 8 quality gates.

☆ 1.0K ↓ 38.1K Development & Runtime ↗