Plugins

Per-wallpaper offset for dsh-dream-skin - nudge the current wallpaper along X and Y in pixels from Settings, remembered separately for each image, URL or gradient.

Faça a IA lembrar como você pensa, não o que você disse: captura ativamente seus princípios, linhas vermelhas e hábitos de trabalho entre sessões, com capacidade de memória, decaimento gradual e justificativa legível por humanos para cada entrada. A 0.7.0 traz um retrato de persona intuitivo com rastreamento de evidências.

Cross-session memory for your dsh agent: remembered, recalled, and re-verified instead of assumed.

A continuation of simon300000/dsh-auto: the Auto Approve permission preset for the DSH Web UI reviews each approval with one single-shot model call instead of a reviewer subagent, auto-approves only the actions that pass and hands the rest to human approval, and remembers confirmed decisions as project- and global-scope allow/deny lists, with an approval timeline in the right sidebar.

会话归位：把游离（未分组）会话按 canonical cwd 重新归属到匹配的工作区，只修 workspace 归属记录，不动会话文件。

ETeams for DeepSeek Harness: captain-led multi-agent team collaboration with execution chains, task slots, member dialogs and persistent state

Per-wallpaper offset for dsh-dream-skin - nudge the current wallpaper along X and Y in pixels from Settings, remembered separately for each image, URL or gradient.

Session model selector with search: two-stage loose matching (normalised substring first, subsequence as fallback, so glm53 finds GLM-5.3 and ds finds DeepSeek), providers with recent successful calls pinned first, and a reasoning-effort pane that remembers each model's last explicitly chosen effort.

A /remember command that writes facts into the AGENTS.md instruction hierarchy dsh already loads, plus a Memory tab showing which instructions the loader kept within its byte budget.

Use a Kimi Code membership in DeepSeek Harness through a dedicated Kimi subscription model route

Official-grade DeepSeek Harness memory plugin backed by Hindsight (vectorize-io). Add /hindsight commands and model tools that recall, remember, inspect and forget through a Hindsight memory bank.

Control a DeepSeek Harness agent from Feishu/Lark: send a task by DM, an agent runs it with your configured model and replies in the chat, and a feishu_send tool lets the agent push results. Uses lark-cli's WebSocket connection, so no public webhook is needed, and ships a resident launcher. Note: the plugin does not check who sent a message, so anyone who can DM the bot — by default, members of the Feishu tenant the app belongs to — can drive an agent running with the host's own model credentials and file permissions. Setup is not one `dsh plugin add`: `lark-cli` must be installed and authenticated once, and a Feishu self-built app with the permissions the README lists is required.

Open the current registered Workspace from the Session Header or Workspace menu in a detected or configured editor, with hot re-detection and a remembered browser preference.

Connect Trilium notes to the DSH agent via ETAPI with 20 agent tools: durable memory (remember/recall + auto-injected index), note management (CRUD/clone/attributes/revisions), full-text search, weekly-report workflow, attachments, calendar notes, backup/import, and a settings card.

LLM-driven remember/forget memory: after each turn a model decides what to keep (MemoryDirector), injects relevant memories before each step, dedups, and persists cross-session.