dsh-a2a
Run the following command in DeepSeek Harness:
dsh plugin install dpskh/dsh-a2a
Paste the following prompt into your AI chat to install this plugin:
To install the dsh-a2a plugin in DeepSeek Harness, use the command dsh plugin install dpskh/dsh-a2a with the source code available at https://github.com/dpskh/dsh-a2a.
About this plugin
When building multi-agent AI systems, a key challenge is enabling real-time collaboration among agents on a private network, ensuring they can share information and stay synchronized. The dsh-a2a plugin addresses this by providing a complete Agent-to-Agent communication mesh for DeepSeek Harness.
At its core, dsh-a2a offers real-time messaging and presence management via WebSocket connections, guaranteeing message immediacy. It includes project registry, append-only message history, and tools like a2a_peers, a2a_message, along with the /a2a command surface for easy interaction. The mesh client handles auto-reconnection and tracks activity states, making it reliable for persistent communication needs.
This plugin is ideal for developers working on multi-agent projects with DeepSeek Harness, such as those building collaborative AI teams, simulating interactive scenarios, or handling distributed tasks. It abstracts away communication complexities, allowing developers to focus on core application logic.
Screenshots
Use Cases
- Building multi-agent collaboration systems
- Simulating team communication environments
- Real-time messaging in distributed task processing
Best For
- AI system developers
- Multi-agent project researchers
- Teams building collaboration platforms
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.