Plugins

Stops session lockups from OpenAI-compatible gateways that stream empty tool-call ids: intercepts llm/stream chunks in memory to synthesize consistent call_<sha256> ids across tool-call-delta and block-end, plus offline session repair/verify scripts under tools/.

Lets the agent read the app, title, URL and text of the window in front through the macOS Accessibility API, with opt-in on-device screen memory it can search.

Experience and skill engine with a sidebar console and exp_record / exp_recall / exp_feedback / exp_consolidate / exp_type tools, stored in a local JSON file. Optional Git backup (off until you configure a remote) pushes the library to a remote you choose; GitHub sign-in uses a device code or a token kept in local settings.

Local-first memory nebula for DeepSeek Harness with graph views, evidence chains, hygiene checks, and offline snapshots. Reads the memory stores of every workspace and of other memory plugins (read-only, for example meow-memory's SQLite) and writes only under $DSH_HOME/memory-nebula. Registers 9 agent tools and a system-prompt section (usage rules every turn, plus not-yet-read neighbouring memories after a few reads); its /export and /share endpoints return the full memory text without authentication on the local server, and an optional standalone engine listens on 127.0.0.1:7890.

Local long-term memory core for DeepSeek Harness with plain-text notes, a bounded index, five tools, optional host-model consolidation and auditable evidence. It appends every user and assistant message under 32,000 characters to ~/.companion/cold/<date>.jsonl in plain text, with no built-in cleanup, and adds a short index of its notes to every system prompt; the optional model-based consolidation is off by default and, once on, sends those messages to the session's model.

Adds a live system dashboard with per-core CPU, memory, GPU, processes, disk usage and a STOP action for ending processes, plus per-process energy on macOS, exposed as a browser page, a GUI panel and a `systemInfo` service other plugins can inject. macOS is the main platform and Linux is best-effort. The dashboard page and its read-only JSON (process list with users, disks, logged-in users) are served with no login check; publicDashboard: false only refuses non-loopback peers. STOP accepts loopback requests only and sends SIGTERM, then SIGKILL after a grace period, to any process your account may signal except pid 1, the DSH host and its parent.

Floating, draggable sensor dashboard for the Harness Web UI on Windows: GPU-Z GPU temperature, clock and dedicated VRAM on the left, CPU temperature/clock and system memory on the right.

DSH plugin: persistent local memory powered by @rsrsai/memlite (respire-aligned prompt/recall/wrap-up logic; JSONL causal tree, git sync, data-compatible with Rust memlite; four-view memory browser with conditional writes, receipts and status).

Brain-inspired cognitive architecture for DeepSeek Harness: hippocampal episodic memory, cortical semantic memory, spreading-activation recall, appraisal-based emotion, neuromodulator state, Big Five personality and dual-process judgment.

Context-budgeted local memory for DeepSeek Harness: fixed ~600-token cache-friendly injection (session/daily snapshots), three-stage sleep consolidation, spaced repetition, temporal validity, subagent-driven L0 mental-model rewrite, typed memories (fact/s

Back up and restore dsh-mnemon memory and skill components (memory spaces, project documents, runtime memory, skill files, skill data) to S3-compatible storage or WebDAV.

A pet ledger whose achievements come only from real DeepSeek Harness session events: tool-failure streaks, long completed turns, red-to-green test runs, and commit+push success. Every achievement expands into the session id and the actual tool-call evidence (command, result, duration); demo cards are a separate in-memory list with a visible 演示 watermark and never count or persist. Daily quests are generated from the day’s real active time and command types, then frozen. Host + client halves, zero runtime dependencies, 70 tests, local JSON only.

Bridges the official IAR C-SPY MCP server into DeepSeek Harness: build .ewp projects, start simulator or hardware debug sessions, and read variables, registers, memory, the call stack and target output from the conversation. Windows only, and it needs an IAR Embedded Workbench installation. Setup needs Python 3.10+, Git and network access to GitHub and PyPI.

Auto-detects whichever memory tool local Hermes uses, then reuses its skills and memory in DeepSeek Harness, with always-available recall. Needs python3 and a local Hermes installation; it only reads from Hermes.

AI-assisted reading workspace for DSH with a local TXT/Markdown/EPUB/PDF library, annotations, prompt presets, long notes, memory, export and companion tools.

Zero-config per-Session freshness for codebase-memory: on Session start and on every working-directory change it refreshes the index of the Session's own repository, so each project in each Session answers from its current graph while indexing stays in the shared daemon.

Backup and restore for dsh-mnemon: pick any of its three memory components (memory spaces, project documents, runtime memory) and archive them to S3-compatible storage or WebDAV, then browse the archives and restore a chosen subset. Live SQLite databases are copied through node:sqlite backup() so a concurrent writer cannot tear the copy; every file carries a SHA-256 checked before upload and again before restore; a restore previews by default and deletes the stale -wal/-shm sidecars before writing a database back. Archives are named mnemon-sync-<device>-<timestamp>.zip so backups from several machines stay tellable apart. Runs a single timer with intervals from hourly to weekly, stores credentials in a 0600 file outside the DSH profile, and depends on nothing outside Node.

Structural scaffolding for DSH agent continuity: layered memory (hot/index/judgments), judgment cards, handoff packs (compact mode), compaction review. Zero-dependency, pure files, portable — rebuild the 'self' across model changes. Not a memory engine; the skeleton of continuity.

Connects DSH Foxy to Foxy Memory for cross-platform recall, with local JSONL fallback, platform filters, and a memory browser. Requires dsh-foxy.

Approval-free memory archiving for DeepSeek Harness: writes Markdown memory files without approval prompts, backs the old file up before any overwrite, marks a revised conclusion as status: superseded in one call, and prunes old backups after 30 days by default (optional size cap). The writable scope is hard-limited to configured memory roots (default ~/.dsh/memory). Companion to dsh-kb-lite, which indexes these files and down-weights superseded ones. Host-only, no npm dependencies; requires Node.js 18+.

Memory engine for a long-lived companion agent: a six-module loop (gate, solidify, store, retrieve, inject, decay) that decides what is worth keeping, distils raw turns into long-term entries, fuses short and long term at recall time, and fades entries that stop being used. Runs offline by default; if DEEPSEEK_API_KEY is set it also sends each message to the DeepSeek API to judge and distil it. Zero runtime dependencies and no build step; ships three switchable panels over the same store - neural brain, memory ring and memory galaxy - so you can watch what it remembers. Non-commercial license: commercial use needs the author's permission.

Visualizes all DSH session memories as an interactive 3D nebula, with a neuron-signal skin, memory-scaled clusters, zoom-driven detail levels and a live write/read activity stream over SSE.

Three-tier memory (personal, project, session) built on the Hy-Memory engine, with relevant memories injected before each step. Ships seven memory tools (search, add, list, get, update, delete, forget), a settings panel with per-tier lists, editing, change history and duplicate cleanup, real token accounting per write, session summaries written by the engine at session end, and a user profile refreshed from recent memories. Memories can be exported to and imported from MemHub. Needs Python 3.11+ once to install the engine, or uv, which fetches 3.12 itself; uninstalling keeps the stored memories.

macOS (Apple silicon) fork of aureth-labs/dsh-aurabot-qq: the same QQ persona bot (chat, voice notes, stickers, memory, song covers, modules) with the Windows-only code removed. It connects to a OneBot v11 gateway such as SnowLuma running in OrbStack or Docker, falls back to the macOS `say` voice, sends files over 30 MB to a containerised gateway through a loopback-only temporary download link, and installs the song-cover environment (Applio, audio-separator, uv, Rubber Band, separation models) at pinned versions. It keeps the upstream package name and plugin id (dsh-aurabot-qq), so it replaces upstream and cannot be installed alongside it; use upstream on Windows.