dsh-session-fork
Run the following command in DeepSeek Harness:
dsh plugin install Jason-skd/dsh-session-fork
Paste the following prompt into your AI chat to install this plugin:
In DeepSeek Harness, install this plugin by running 'dsh plugin install Jason-skd/dsh-session-fork', with the source code available at https://github.com/Jason-skd/dsh-session-fork.
About this plugin
Traditional session-based AI conversation management often leads to fragmented memory and polluted context: starting a new session erases project context, while continuing a chat introduces irrelevant information over time. The dsh-session-fork plugin addresses these pain points by introducing branches as the building blocks for AI conversation management. This approach enables parallel workflows, where each branch holds its own memory, preventing context pollution and allowing for continuous, mergeable memory across sessions.
The plugin's core capabilities include an upgraded native fork function that turns every fork into a managed branch, along with inter-branch operations like squashing unique turns and conclusions back into the main or other branches. It also offers branch visualization through a vendored VS Code Source Control Graph, providing an authentic and intuitive interface for managing branches. This foundation supports future expansions into sub-agent collaboration and branch-scoped long-term memory, making it a robust tool for advanced AI teamwork and secretary applications.
This plugin is ideal for AI developers, team collaborators, and anyone building AI systems with DeepSeek Harness that require organized conversation management. If you need to handle complex dialog flows, avoid information clutter, or explore multi-agent coordination, dsh-session-fork offers an efficient branch-based solution to streamline your AI workflows.
Use Cases
- Handle multiple AI tasks in parallel, avoiding context pollution.
- Maintain continuous conversation memory in complex projects.
- Enable branching communication and collaboration between AI teams.
Best For
- AI application developers managing complex dialog flows.
- Team collaborators seeking efficient AI workflows.
- Users building AI secretary or collaboration systems.
Related Plugins
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.
An opinionated, zero-infrastructure file-based memory protocol: human-readable markdown files plus a bounded always-loaded index, curation discipline, and no database or embeddings.