dsh-llm-opencode
Run the following command in DeepSeek Harness:
dsh plugin install bobowsh/dsh-llm-opencode
Paste the following prompt into your AI chat to install this plugin:
To install this plugin in DeepSeek Harness, run the command: dsh plugin install bobowsh/dsh-llm-opencode, and refer to the full source address: https://github.com/bobowsh/dsh-llm-opencode.
About this plugin
In the era of AI-assisted coding, developers often seek to leverage large language models for efficiency, but many solutions require paid APIs or complex configurations, creating high barriers. The dsh-llm-opencode plugin addresses this by acting as a bridge between DeepSeek Harness and OpenCode Zen, allowing users to access multiple free models—such as DeepSeek V4 Flash and Nemotron series—without any API keys or credit card information.
Its core capability lies in seamless integration: once installed, users can select OpenCode Zen as the provider in DSH settings, with free models ready to use out of the box. The plugin automatically syncs the latest model directory from the gateway and handles streaming responses and authentication, ensuring stable access. For coding tasks, it supports context windows up to 200K, making it suitable for large codebases.
Who is it for? Whether you're an independent developer, student, or open-source contributor looking to explore LLM applications in coding at zero cost, dsh-llm-opencode is an ideal choice. It streamlines the path from zero to one, allowing the focus to return to the code itself.
Use Cases
- Provide free model access for coding agents without an API key.
- Seamlessly integrate OpenCode Zen models into DeepSeek Harness.
- Automatically sync the free model directory to ensure latest availability.
Best For
- Independent developers seeking zero-cost AI coding assistance.
- Students and educators for learning and experimenting with LLMs.
- Open-source project maintainers needing free models for testing and development.
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.