dsh-of-your-own
Run the following command in DeepSeek Harness:
dsh plugin install LaplaceYoung/dsh-of-your-own
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install LaplaceYoung/dsh-of-your-own in your DeepSeek Harness terminal to install; the full source is available at https://github.com/LaplaceYoung/dsh-of-your-own
About this plugin
You spent six months teaching Claude Code to reply in Chinese, prefer rg over grep, and skip package-lock.json unprompted. You wrote Codex its own AGENTS.md, gave Cursor a .mdc rules file. Then you open DeepSeek Harness and it greets you like a stranger at a bus stop. dsh-of-your-own exists for that exact moment: one command scans every harness's transcripts and rule files in parallel, extracts your language preference, tool habits, and slash-command muscle memory, and writes it natively into ~/.dsh/AGENTS.md—the file DSH loads on every boot. Uninstall the plugin tomorrow; the memory stays.
Beyond preference migration, it catalogs every unfinished session across all your harnesses and can hand one over with a full context brief—original task, working directory, where it stopped, tools in play—so the current agent picks up right where the other one left off. Everything is idempotent, fully offline, and local-only; a single command wipes every trace when you want out.
Built for power users who run multiple AI agents in parallel and are done re-teaching the same preferences to the fourth, fifth, and sixth harness.
Screenshots
Use Cases
- Switch to a new agent harness and instantly inherit every preference, tool habit, and slash command you ever taught
- Catalog unfinished sessions across all harnesses, pick one, and hand it over with a full context brief for immediate continuation
- Uninstall the plugin and your preferences remain in the global AGENTS.md—memory outlives the tool
Best For
- Power users running multiple AI agents in parallel who are done re-teaching the same preferences
- Developers who have invested hours in prompt tuning and want that investment to follow them across tools
- Privacy-focused developers who demand fully local, offline, zero-upload workflows
Related Plugins
Memory layer for coding agents that indexes local session history and auto-recalls relevant context before edits, commands, and failures, with no manual search needed.
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.