create-dsh-app
Run the following command in DeepSeek Harness:
dsh plugin install menotbobbybrown/create-dsh-app
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install menotbobbybrown/create-dsh-app in your DeepSeek Harness terminal to install this plugin; source code is at https://github.com/menotbobbybrown/create-dsh-app.
About this plugin
Getting an autonomous AI agent up and running is rarely the hard part—it is the gluing. Wiring up MCP tool integrations, persistent memory, headless browsing, and a hot-reload dev loop by hand eats hours that could go into actual product logic. create-dsh-app collapses all of that into a single scaffold command so you can start iterating on behavior immediately.
Every generated project ships with dsh-plugin-mcp pre-connected to a catalog of common services (GitHub, Postgres, SQLite, Brave Search, and more), dsh-plugin-memory for a durable knowledge graph and user-preference recall, and dsh-plugin-browser for headless navigation with clean Markdown extraction. The runtime is TypeScript on the Cordis lifecycle, with tsx-powered hot reload that keeps the feedback loop tight.
It is built for solo developers who want to prototype agent ideas without babysitting boilerplate, and for engineering leads who need a consistent, reviewable project skeleton across a team of contributors. Licensed under MIT, so it is safe to fork, extend, and ship to production.
Use Cases
- Scaffold a full agent project with MCP, memory, and browser in one command
- Keep a team on a consistent agent project structure and dev loop
- Rapidly prototype an autonomous agent on DeepSeek Harness
- Skip environment setup and go straight into business logic
Best For
- Solo developers who want to prototype agent ideas fast
- Engineering leads standardizing agent project structure across a team
- Tech teams building AI applications on the DeepSeek Harness ecosystem
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.