dsh-narra-channel
Run the following command in DeepSeek Harness:
dsh plugin install NetMind-AI/dsh-narra-channel
Paste the following prompt into your AI chat to install this plugin:
Install by running dsh plugin install NetMind-AI/dsh-narra-channel in the DeepSeek Harness terminal; source code is available at https://github.com/NetMind-AI/dsh-narra-channel .
About this plugin
dsh-narra-channel is a standalone third-party channel plugin that bridges a DeepSeek Harness Agent Preset with Narra Messenger, letting you expose your agent as an independent identity in Narra's multi-room chat—without modifying Harness or Narra source code.
Once bound, each Narra room maps to a deterministic Harness session. Different bindings run concurrently while messages within a single binding are serialized, preventing duplicate invocations. The plugin streams text replies through the Narra Gateway and automatically switches to short, speech-friendly responses when it detects voice_instructions. Sensitive Gateway tokens are stored exclusively in Harness Credentials, keeping them out of ordinary settings, logs, and model context.
It is designed for developers who have already configured a model provider in Harness and want to extend their agent into Narra Messenger, particularly teams or individuals who need multi-agent parallelism, room-level isolation, and transcribed-voice interaction.
Use Cases
- Bind a Harness Agent Preset to Narra Messenger multi-room chat in minutes
- Receive streamed text replies in Narra with automatic short-response mode for voice instructions
- Run multiple agents concurrently in Narra with independent, non-interfering bindings
Best For
- Developers with a configured model provider in Harness looking to connect to Narra
- Teams needing room-level isolation and concurrent multi-agent chat management
- Integration engineers who want to extend messaging channels without modifying Harness or Narra source
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.