Plugin

A no-limit Texas holdem table where you are the only human. Eight seats: you plus seven LLM agents written on AI-founder personas (Altman, Dario Amodei, Musk, Liang Wenfeng, Jensen Huang, Lei Jun, Zhang Yiming). Each agent bets through the currently selected host model and falls back to its own heuristic style when no model is available; every agent only ever sees its own hole cards, because the prompt is built from that seat alone. A hand ends by revealing the winner hole cards, with a flip animation replayed on every community card, and a rail keeps a live action-and-table-talk timeline. LAN mode (off by default, single-machine play is unaffected) lets another install on the same network join this very table: the host shows a six-digit room code, UDP broadcast discovers nearby tables, and a joiner randomly takes over one bot seat, with the seat handed back to its character on leave or after twenty seconds of silence. The room code is never put on the wire and every snapshot is generated for one viewer seat, so nobody, not even the host, can read another player hole cards. Fork of BubblePtr/dsh-holdem (MIT), credited in the README and in the UI.

Plugin index inside DSH that lists over 10,000 third-party plugins checked against the dsh.bundle manifest in their package.json rather than by star count, with one-click install and a companion website.

Turn-handoff reminders in the DSH Web UI with a modal or top banner, six browser-synthesized chimes, configurable auto-dismiss, and a sidebar speaker toggle with an unread session list.

Desktop notification and sound when a turn completes, the agent asks a question, or an approval is requested, each independently toggleable, plus an activity ball that lists live sessions and jumps back to one.

Prior-art search for an idea: three tools find similar open-source projects on GitHub, rank them by a score computed in code from a relevance judgement and the star count, then read the chosen repositories (README, dependency manifest, directory tree, key files) and report the class and function declarations found in each file header; files_read lists what was actually fetched.

Mounts the tsm-core-dlr semantic service (LanceDB vectors + graph) as MCP tools and ships the scenario-independent DLR/TSM modeling skill, a service-status overlay and the agent rules; the service is a hard dependency and must be running before the bundle activates.

Add MiniMax image understanding, image generation, speech synthesis, and transcription tools to DeepSeek Harness.

A memory subsystem for DeepSeek Harness: full ontological memory (event/fact/rule three-ontology) plus a goal system (goal.js) — belief values written via Bridge trigger words, goal activation scored at read time (0.25 domain + 0.35 bridge + 0.40 sim) to recover goal/value long-range associations, journal ledger, episodic archive, low-confidence decay, memory_append/read/consolidate plus linghun_goal_update/get/state closed loop. Independent of the original dsh-linghun line. 16/16 on LoCoMo-Plus.

Long-term memory scoped to the DSH workspace. A session opens with a one-line-per-memory index - bodies are fetched on demand by the `memory` tool, so the same character budget holds about three times as many entries - and when a turn ends a purely local search over the last user message pulls the matching memories into the next briefing at no model cost. Optional auto-capture distils a stretch of conversation into structured memories; in draft mode they wait in an approval queue instead of landing directly. A portrait layer keeps a workspace and a global picture, rewritten from the journal and the records, with the same draft-or-direct choice. Settings → Memory holds the archive, list and timeline views, a health check (duplicate clusters, stale entries, broken links), the supersede version chain with rollback, and a read-only scan that imports existing WorkBuddy / Qoder memory files.

Read-only attachment library: lists every image and file attachment stored on this machine, its size, and which conversations (including those in the session trash) still use it, with Show in Finder and Open in Preview.

Cross-workspace DSH messaging and sender navigation, with bounded same-workspace context and opt-in local Claude Code messaging.

Pins a selected passage of a finished user or assistant message as source text and keeps it in the model input across context compaction: each pin is recall-on-demand by default, or can be moved to a neutral resident system-prompt section or an emphasised highlighted one. Selections are aligned back to the source text with source-exact, source-normalized or rendered fidelity, and each of the three levels has its own character budget.

Rewinds a session to before a chosen user turn, from a button beside Copy under your own message — the model-visible surface is replaced in place and the interface hides the rewound turns, without patching DSH source or deleting the original session log.

Time-based model routing: a settings panel defines weekday peak and off-peak windows and the provider/model each one uses, the choices are read from the harness registry (API keys and subscription logins alike), and a global switch decides whether that policy sets the model and reasoning effort of every request. The switch is independent per session, each session row carries a light showing its own state, and the settings panel names the model in force right now and why. A day no window matches — every weekend and holiday — uses the primary model of the first plan; the advanced thinking model is a separate axis, used only when a session itself asks for max reasoning.

iOS 26 liquid-glass skin: a frosted glass sheet over a neutral mesh wallpaper, system blue as the only accent, with separate light and dark palettes. Installs as a DSH client plugin (165 KB, no dependencies) that injects its own CSS, wallpaper and token overrides.

Cuts session input tokens three ways, each with its own switch in a panel under the composer: lossless structure-aware compression of tool results on `tools/post-execute`, then a per-tool head/tail elision that always names a recovery path through the shared spill store; tool-catalogue visibility per agent on `agent/created`; and a per-workspace memory document that recall matches against each new message and injects through `agent.inject`, so the transcript is not re-read. Measured 41.76% fewer prompt tokens over 149 recorded requests, with a bundled script that re-measures any profile.

Read-only clinic for DSH session logs: 22 named diagnostics (token waste, retry and failure loops, context bloat, cross-session amnesia, idle MCP servers and skills), each reported with a replayable evidence locator such as session.v4.jsonl.zstd#L101-L110, and each finding turned into an executable prescription — a profile-patch YAML snippet or a command with current to suggested values, risk, verification and source — plus a feedback command that retires a prescription you reject, after which the report states it was removed by your feedback. Zero dependencies, default zero egress, session files are never written.

Pasted screenshots become numbered references: each Ctrl+V image is stored in the attachment library under a stable number, listed in a composer-dock thumbnail panel with an image source in the @ menu, and inserted as a reference chip at the caret — automatically after paste when the auto-insert switch is on.

Keeps the images you pasted or attached in the composer, per session: they are mirrored locally in the browser and handed back through the official draft channel when you return to the conversation or the composer remounts, and dropped as soon as the message is sent or you remove them.

Hierarchical workspace tree and multi-view manager for DSH: workspace and session naming creates virtual folders (/), multi-view support (workspace tree, flat workspaces, single list, time timeline), session pinning, and independent sections for workspaces and sessions.

Your real Obsidian vault in the DSH right Sidebar: the vault tree, full-vault search, notes rendered with read-view typography, wikilink navigation, in-place editing, and a clickable outline.

Select text in a DSH conversation, a file preview or the terminal to quote it: the floating bar offers Comment, Add to chat and Side chat, and Alt+Q / Alt+C / Alt+B do the same three things. The quote - and its comment, kept in the same chip - is inserted as a native reference chip, and a sent quote stays one rounded capsule in the message that expands on click and can be copied. A hover card can jump back to the message a quote came from, and the right sidebar carries a quote list page that searches every quote of the session, jumps back to any of them and exports them as Markdown. Side chat writes the quote into the composer of one dsh-better-sidebar side thread per conversation without sending it, and that page can bring the thread conclusion back into the main composer or export it as a file. A sent quote can also be revised: the card puts its old comment back in the comment box, the corrected quote is sent as a new message, and the old capsule is marked as superseded (the transcript itself is append-only).

Let Agents directly control independent local DSH instances with zero intrusion—no plugins or components required on the target. Isolated environments enable autonomous configuration and testing, while Agents with different models and personalities can chat, role-play, or form nested control chains. Supports conversational setup, user-like operations, incremental reading, saved references, and remote session/workspace search.

Snapshots plugin versions and profile configuration, with an independent recovery page to restore a known-good configuration when DSH cannot start.