DeepSeek Harness Plugins · Memory
Plugins that extend DeepSeek Harness (DSH) with vision, workflows, memory, web tools and more.
AgentSoul provides local personality, identity, state, and long-term memory management for DeepSeek Harness, featuring four-layer personality files, memory distillation, and automated injection.
dsh-memory-gate is a long-term memory plugin that uses CBDC authority gating to ensure memories are only injected after adjudication, with post-use feedback learning, local storage, and safe control.
An asynchronous context relay plugin for DeepSeek Harness that transfers bounded context capsules between sessions without interrupting ongoing conversations.
A cross-session plaintext memory plugin for DeepSeek Harness, ensuring controllable memories via a human confirmation gate, with dual-layer storage and BM25 retrieval.
This plugin enables searching, recovering, and securely deleting archived sessions in DeepSeek Harness's native sidebar.
A conversation history recall plugin using three-layer hybrid retrieval (literal, fuzzy, semantic) to enable DeepSeek Harness agents to accurately recall past dialogues, fully local and offline.
A DeepSeek Harness plugin for managing conversations with archive, delete, move to workspace, and per-conversation Agent preset migration features.
DSH Git Memory is a Git-backed memory plugin for DeepSeek Harness that provides reviewable, revertible long-term context, currently in pre-alpha status.
A plugin for DeepSeek Harness that provides a Markdown-based persistent memory system for human-readable and cross-session memory management.
dsh-layered-memory is a cross-session long-term memory plugin for DeepSeek Harness, featuring namespace isolation, multi-layer memory storage, and BM25 full-text search.
DSH ExpMem is a community plugin for DeepSeek Harness that provides long-term personal memory storage for user habits, reusable task experiences, and engineering insights.
codegraph is a code knowledge graph plugin that parses codebases into a queryable index, enabling agents to answer structural questions like call graphs and dependencies.