Plugins

Session-aware local notes for DeepSeek Harness: capture notes and page selections in a floating Apple Notes style panel, let the LLM classify topics, auto-inject convention notes into the system prompt, and dispatch todos with recall context to active sessions.

Compaction fallback for compaction-basic: when its LLM summary throws, comes back empty or cannot fit the window, the span is compiled deterministically with a seq pointer on every line (vendored dsh-compaction-instant compiler). Adds recall and search tools, /recall and /context commands, an idle trigger at 45% of the window and an on-disk span archive. The engine mounts as one row in the agent preset (docs/dsh-integration.md).

Publishes a lesson into the DSH conversation: the dependency spine, the question and the vault's drawings, drawn in the vault's own palette.

Layered memory for DSH whose agent-facing surface is 10 tools: high-privilege writes (memory_add, memory_delete, memory_import), rumination controls (memory_ruminate, _cancel, _status), and a memory graph (memory_search_graph, memory_expand_graph_node), built over an L0-L3 distillation pipeline that recalls and injects relevant memories before each model step.

Conversation enhancements: a history-input overlay (Alt+Up with workspace/session/global/prompt scopes), recall of unapplied interjected messages, conversation forking with fork-family version switching, and optional auto-resend after forking (off by default).

Cross-session long-term memory for the DeepSeek Harness: a two-phase extraction/consolidation pipeline over a file-based memory workspace, recall injection, a citation feedback loop, lease-based job semantics, plus a settings page, a sidebar status panel

Knowledge base with a corrective acquisition loop for DeepSeek Harness: when the agent keeps hitting the same failure, a background worker fetches the web under a rate limit, distills the result into a staging area, and only a two-stage commit makes it recallable — pages without sources are refused.

Self-tending living memory in one local SQLite file — a nightly patrol dedupes, merges, decays and cross-links entries on its own, with seven-signal RRF hybrid recall (FTS5 + jieba Chinese-first tokenization, optional vector KNN, graph PPR), a typed knowledge graph, conflict detection instead of silent overwrites, and web telemetry panels.

Coding retrospect distilled memory for DSH: distills rejected solutions, pitfalls and constraints from each turn via a local LLM, tags them into MemOS (type:rejected_solution), and boosts weighted recall on coding tasks via agent/pre-step.

Arrow-key input history for DSH 0.1.2-alpha.1: press ↑ in an empty composer to recall this session's prompts, ↓ to go forward, Esc to restore the draft.

Persistent memory for DeepSeek Harness with curated facts, automatic turn retention, and graph- and vector-ranked recall.

Cipher memory platform as a DSH bundle: four memory types (attention, experience, preference, cognitive) sedimented per turn by four memory agents, cross-session deterministic recall injected via systemPrompt.context, insight review kept out of user-facing output, per-session UNNI/LOOP modes with memory-driven auto-continuation, memory search/ingest tools, plus a settings page (SOUL editor) and an AgentPool panel.

Recall previously sent messages in the input box with Up/Down, and archive a workspace session from its right-click menu.

A living memory workbench for DeepSeek Harness: watch the Hindsight bank grow (7-day curve, recall heat, timeline) and manage knowledge pages and background tasks, with the local daemon auto-started by the plugin.

Forces periodic Engram memory recall and save reminders for DeepSeek Harness agents: injects a dynamic system-prompt context that reminds the model to load prior session memory at the start of a session, and to save new decisions/bugfixes/learnings every

Mnemosyne memory for DeepSeek Harness: remember / recall / forget / stats / sleep tools, embedded skill, auto-setup, optional auto-sync/prefetch, and a Settings panel. Data lives under ~/.dsh/mnemosyne.

Recall (撤回), edit-and-resend (编辑重发) and regenerate (重新生成) for DeepSeek Harness conversation messages — Web and Desktop

Mémoire persistante pour DeepSeek Harness : outils de lecture/écriture/récupération de mémoire, enregistrement automatique par tour, injection de rappel à portée de projet et UI de gestion, avec importation non destructive de la mémoire Claude Code.

Amélioration de la zone de saisie Web : rappelle les invites envoyées entre les sessions avec Flèche haut/Flèche bas, les recherche avec Ctrl+R, restaure les brouillons riches, et ouvre une conversation ancrée /btw ou /side.

Ajoute une mémoire chronologique à DeepSeek Harness : un journal de faits à largeur fixe et en ajout seul + une pyramide de résumés entretenue par l'agent lui-même, avec un budget de lecture fixe et un coût de rappel (recall) qui n'augmente pas avec le volume de mémoire.

Rappel et écriture GoodMemory automatiques inter-sessions pour DeepSeek Harness

Plugin DSH : mémoire Honcho v3 double pair automatique, rappel contextuel, recherche, raisonnement, conclusions, et diagnostics de santé

Mémoire long terme injectée au démarrage de la session : préférences/faits/résumés/connaissances en portées globale et par projet, rappel budgétisé via `agent/pre-step`, stockage JSON durable.

Mémoire bi-temporelle adossée à un démon SodaMem : le rappel est versé au prompt pendant l'assemblage de chaque tour et chaque tour clos est ingéré, sans appel d'outil ni appel de modèle sur le chemin de lecture ; chaque fait rappelé cite le tour dont il provient et porte des dates de validité, de sorte que les faits remplacés cessent d'être récupérés.