liangmianya/dsh-synapse

A visual, non-linear conversation workspace plugin for DeepSeek Harness ; A canvas-based session explorer and branching workspace for DeepSeek Harness.

What it solves

It transforms linear chat histories into a visual, interactive map. This solves the problem of managing complex conversations that involve multiple follow-up questions and branching paths, making it easier to navigate and organize sessions within the DeepSeek Harness (DSH) environment.

How it works

Synapse acts as a visual projection of existing DSH sessions. It organizes conversations, follow-ups, and branches into a draggable and zoomable canvas. It integrates directly into the DSH web profile, reusing the existing DSH Web Server without launching a separate proxy or application. While the visual layout data is stored separately, the actual session logs remain the single source of truth in DSH.

Who it’s for

Users of DeepSeek Harness who want a non-linear way to explore their AI interactions and better manage branching conversation threads.

Highlights

  • Conversation Mapping: Visualizes continuous follow-ups and branches on a single operational canvas.
  • Real Branch Preservation: Connects cards based on native DSH fork relationships to avoid duplicating session history.
  • Enhanced Follow-ups: Allows users to select text from an answer to start a new follow-up question immediately.
  • Bi-directional Sync: Maintains consistent context when switching between the visual map and the native DSH chat interface.

Related

  • Project
    YangDai2003/Kori

    A cross-platform note-taking app with support for Markdown, LaTeX, and Mermaid diagrams, featuring an optional AI co-writer that connects to various LLM providers.

  • Project
    VectifyAI/pageindex-mcp

    A Model Context Protocol (MCP) server that enables LLMs to perform reasoning-based, vectorless RAG over long PDFs using hierarchical tree structures.

  • Project
    DY-2026/GameDesignOS

    A local-first operating layer for AI-assisted game design that transforms fragmented AI output into structured, evidence-linked design decisions and project memory.

  • Project
    callie0313/dylan-heartbeat

    An AI residency runtime for Kelivo companions that enables proactive wake-ups and mobile notifications, giving AI characters a continuous sense of time and time-aware autonomy.