Plugin

Keep conclusions alive across context compaction: the model writes a task checkpoint and the plugin re-injects it into the system prompt's first node — the span compaction never touches, so it survives any number of compactions. Four-tier injection (0/95/175/≤12000 chars) scales with session relatedness; checkpoints live in the plugin's own folder, never in your workspace.

Four-layer memory for DeepSeek Harness, ported from the memory design of NoMindSama/qq-dsh-bridge (MIT) with the QQ channel removed: an append-only dialogue log, a weighted long-term fact store with decay and one-way archiving, self-notes the agent writes about itself, Chinese bigram recall over the raw log, and incremental AES-256-GCM sync to a private git repo where only ciphertext is stored. Archived sessions drop out of recall without losing their history.

Cross-session long-term memory backed by Supermemory: pre-step semantic and chunk recall with per-session deduplication, debounced transcript upload, background LLM fact extraction (add/update/delete) with bigram and semantic deduplication, memory_search / memory_save / memory_forget tools, global or per-workspace container scoping, and a Plugins page UI for API key storage, memory CRUD, recall preview and activity log. Requires a Supermemory API key (a free monthly quota is available), and conversation excerpts are uploaded to Supermemory's cloud.

Local-first, file-backed memory plugin for DeepSeek Harness: Markdown memories, verified trust, per-turn recall, and optional SQLite FTS5.

Keeps a turn from closing on an unfinished reply: a stream guard turns silent truncation into an in-step retry, and a completion protocol asks the model to declare how each turn ended.

Adds custom task groups and an activity bell to the sidebar: drag sessions into or out of a group, reorder them by hand, collapse groups, and see running, waiting and unread sessions in one place.

Permanently deletes a conversation, optionally together with the documents and attachments it created.

Copy a user message together with its images and files, then paste it into any session: the text lands in the composer and each attachment is rebuilt through the official createDrafts/addAttachments path, so it uploads and sends like a normal draft.

Delete a conversation record from the DeepSeek Harness Web UI, with a trash bin to restore or purge it. Both this and zhezhi33/dsh-session-recycler install under the package name dsh-session-recycler, so install only one of them.

Lists every session stored in the local DSH profile with its title, workspace, last-modified time and size, then moves the selected ones to a 90-day trash you can restore or purge; deletion detaches the live session first, so the sidebar updates without restarting the app.

Soft-branches a self-contained sub-question into a child session and returns only a bounded digest, so the main context grows by a short summary instead of the whole investigation.

Lists resumable Codex chats under the DSH composer, grouped by the concrete project each one belongs to, and inserts a mechanically extracted recovery context into the draft without sending it. Project ownership is resolved from the Codex project registry with path-boundary matching and labelled by how reliable it is: recorded session ownership, registered directory, unreadable metadata, or a directory registered under several projects (left unknown rather than guessed). Also reports when the stored autosave is behind the log tail, which usually means the turn ended without a stop. The chat list requires python3 >=3.8 on PATH; Windows is not supported yet, and without python3 the list stays silently empty.

A self-hosted digital-life companion for DSH. Three slow-moving hormones (dopamine, cortisol, serotonin) set its mood and tone, a memory layer turns chats into events and facts with version chains and a forgetting curve, and it writes, hot-loads and unloads its own organs (tools) when a capability is missing. It handles text, images, stickers, voice notes with text to speech and speech recognition, and file uploads; the web space holds diary posts and guestbook comments, and it starts conversations on its own schedule. The built-in web server listens on 0.0.0.0:2332 by default, so create the owner account before exposing the port.

Persona, mood, long-term memory and per-person ledgers for a DSH agent, with a portable soul pack for moving between machines.

Adds a relay_check tool that runs relaycheck against an LLM API relay to detect model swaps, misreported usage, truncated context and injected prompts; keys are read from environment variables.

An Auto toggle next to the model selector that schedules reasoning_effort per request: complexity is scored by a MiniMax/OpenAI-compatible model with a zero-dependency heuristic fallback (fallbacks not cached), effort ladders adapt to each model real effort list (low/high/max, low/high/highx/max/ultra, ...), heavy tool calls upgrade the tier within the same session, the lit button and reply badges show the effort actually used, and every decision plus observed token usage lands in a JSONL ledger. A standalone-button fork of imkingjh999/dsh-adaptive-effort; do not install it and the original in the same profile.

Switch OpenAI models between Codex-style Responses WebSocket transport and SSE from the composer, inheriting DSH provider settings with an optional priority-tier toggle.

Use Claude models in DeepSeek Harness through Claude subscription accounts.

Google Antigravity model provider based on LiZhenNet/dsh-antigravity, with a multi-account pool added. Do not install it in the same profile as LiZhenNet/dsh-antigravity: both register the same bundle id (dsh-antigravity) and the same npm package name.

Registers two LLM account pools as model providers: TeleAgent (China Telecom TeleAI; paste a token once) with a daily 09:00 UTC+8 full-pool check-in — currently check-in, balances and model listing only, since its chat is blocked by the client signing key — and AutoClaw (Zhipu desktop, Windows), whose tokens are decrypted from the local DPAPI-protected credential store and whose chat streams through the desktop bridge. Both pools report credit balances and model catalogs; quota-triggered failover across local desktop instances is automatic, while switching the AutoClaw account is an opt-in setting (off by default). Panels ship in settings and the left sidebar.

Reskins the whole app from a sidebar panel with five skins — pixel arcade, midnight terminal, neon cyber, paper study and aurora glass — changing the palette, type and texture, with one click to restore the default look.

Meteor-night wallpaper skin for DeepSeek Harness: a sharp full-window meteor picture, transparent sidebar and night-only ink.

Adds Amadeus-inspired light and dark colors and interface decorations.

Six switchable background palettes, a custom image, or any solid color for DeepSeek Harness, with adjustable opacity and a dedicated Background settings page.