Plugins

One read-only index of every local AI-agent session (Codex, Claude Code, DSH, Trae, or any JSONL source) grouped by project, plus an append-only shared board for decisions and handoffs so switching agents leaves no context gap.

Actually delete DSH sessions instead of archiving them (Windows only). Clears all six on-disk locations (transcript, title cache, billion-context SQLite index with VACUUM, workspace registry, cost-meter ledger, bridge logs) with a dry run, a backup, byte-for-byte rollback, and an automatic quit-delete-relaunch flow.

Live step pill in the DSH session header: folds the durable session event stream into the agent's current action (tool name plus its argument summary), the step index inside the running turn, the elapsed turn time and the todo progress, polls it every 1.2 seconds, and renders blue pulse while working, green for a finished turn and red for a failed tool call; hides itself 9 seconds after a turn ends. On Windows it also opens an always-on-top desktop HUD (set DSH_AGENT_STATUS_HUD=0 to disable).

Select text in the chat transcript, right-click, and quote it into the composer. The quote travels as an atomic chip and renders as a collapsible card, while the model receives the full block with message role, turn, block index and character range.

Layered local memory for DeepSeek Harness: a Markdown index auto-injected into the system prompt, a route layer read on demand, and evidence files for detail. Pure files, zero runtime dependencies.

Cross-workspace long-term memory for DeepSeek Harness: one machine-local store shared by every workspace, a compact index injected at session start, and a searchable tool for the details.

A plugin center for DeepSeek Harness: install, update and enable DSH plugins, aggregate plugin index sources, and install from a git branch. Also publishes a subscribable format-1 plugin index.

Unreal Engine 4/5 (UE4, UE5) asset browser and exporter for Windows x64: browse, preview and export cooked assets from local PAK archives via CUE4Parse, with 3D mesh preview, animation playback and a searchable asset index. Oodle-compressed archives need Epic's oo2core DLL, which is not bundled but can be downloaded from the settings page.

Bundles a deep-read paper library and the paper-deepread-html skill: a sidebar panel to browse interactive reading reports, upload PDFs into a managed library, deep-read them with an agent (or through an optional site auto-read worker), and manage or rebuild the library; ships the paper_deepread, paper_deepread_uploads and paper_deepread_reports model tools. Deep-read/ingest and report builds require Python 3 (the bundled skill prepares a PyMuPDF venv on first use; index rebuild falls back to plain python3).

Governed literature library: import papers, extract text, keep one index row per entry, and verify quotes verbatim.

Reads the local NTQQ (QQ 9.9.x) message database on Windows and Linux and exports group and private chat history to txt, csv, json, md, html or sqlite. Ships sixteen model tools: qqnt_status and qqnt_doctor for environment and blocker checks, qqnt_extract_key, qqnt_index to build or inspect the sidecar index, qqnt_list_groups, qqnt_list_chats, qqnt_search, qqnt_stats for totals and monthly counts, qqnt_export_group, qqnt_export_chat and qqnt_export_batch (a chat can be named the way the user says it, and ambiguity refuses instead of guessing), qqnt_jobs for OCR, speech-to-text, chunking and model downloads, qqnt_media for a chat's downloaded images, qqnt_storage for disk usage and allow-listed cleanup, and qqnt_ask plus qqnt_recall for retrieval with citations. The local web UI on 127.0.0.1:46728 adds an incremental SQLite index, six views (chats, export, statistics, ask, settings, models), a task panel, a single-pane layout on narrow screens, sender redaction, media bundling, per-day splitting, export presets and AES-256 password ZIPs; OCR, speech and embedding components install into the plugin's own virtualenv on demand. Needs python3 with sqlcipher3 (the settings page can create a private virtualenv), and the database key is read from the running, logged-in QQ client.

Long-term notes and daily journals kept per workspace in a hot/cold archive, each tier with its own index and rebalanced once a day; read and written through seven memory_* tools, with a settings page for per-workspace options.

Long-term memory kept as blocks: one event per block, written to a local append-only event log with a block view and derived indexes, so a full history stays recoverable while only the matching blocks reach the context. The model saves entries with memory_remember and pulls the relevant few with memory_recall, plus one automatic recall pass before each step. Data stays in ~/.beme; no external service and no API key.

Layered long-term memory for DeepSeek Harness: append-only event log, rebuildable tag index, day diaries, semantic layer, trend quarantine, and an offline knowledge-graph panel.

Prompt-box screenshot shortcut button. Drag a box, shot taken immediately. DSH hides automatically; multi-monitor supported. Ctrl+Alt+1--hides the window then shoots; shift+click--does not hide. Hold Ctrl+Alt and click 1 to shoot repeatedly. ! One copy is saved by default, named by content hash, in the DSH attachment library; each session writes an index recording which shots belong to it (can be changed to keep an extra copy in the session folder). Images are part of the context, so deleting them breaks the session — use the "Delete Conversation" plugin to remove images together with the conversation. Windows only.

Web of Science 文献流水线插件：检索式迭代历史与数量闸门（未过闸门强制用户确认检索词）、PDF 收编与 %PDF- 审计、解析编排（复用 dsh-pdf-mineru）、知识库骨架与五层 lint/index、浏览器作业守卫（强制关 tab / 强制把验证交给人）。全流程不依赖任何 skill。

Archives DSH conversation output into SiYuan notes: a single siyuan_archive call files content under `<archive path>/<year-month>/<type>/<date>_<time>_<topic>_<content>` with a metadata table and auto-maintains an index document at the notebook root; 6 siyuan_* host tools (list notebooks, full-text search, read document, archive, delete block, remove document) and a Web settings page for base URL with connection test, API token in the host credential store, archive target and title template, plus notebook/document-level read/write/delete permissions with default deny and child levels able to only tighten.

Delivery panel in the DSH sidebar: indexes every image and file sent to the harness (content-addressed attachments plus @-mentioned local paths), rebuilds Taildrop send history per target device from tailscale file cp calls in the session logs, lists incoming files (the Tailscale inbox plus unmarked files in ~/Downloads), and sends new files to a device from the panel with online status and upload progress.

Memory that outlives the session, kept as plain daily log files: one markdown file per day plus a generated index the agent greps instead of re-reading. Registers the annals skill, injects the write-it-down rules into the system prompt, and exposes three tools — annals_init builds the log directory, the index generator and a separate Git repository in one call; annals_query full-text searches past entries and returns them with file and line anchors; annals_links resolves which entry cites which. Reminds the agent once per turn when it changed files but wrote no log that day, and once more when the log was updated but the index was not. Adds a settings page for the six switches.

A local-first sidebar knowledge base for a DSH workspace: indexes projects, documents and plugins, classifies entries automatically, and provides search, file previews and editable notes. Data stays in the workspace.

Read-only preview of SQLite files and MySQL / MariaDB / PostgreSQL / SQL Server connections in the right sidebar, with tables, paged rows, columns, indexes and draggable column widths, never writing to the database.

DeepSeek Harness plugin: delete a session from the sidebar and cascade the delete through its subagent lineage — durable log, cached projections, search-index rows and workspace accounting.

Registers one agent tool, plugin_guard, that statically scans a DSH plugin package before it is installed and reports a verdict with the reasons: a missing or broken dsh.bundle.patch, a missing dsh.permissions block, install scripts, dangerous APIs and obfuscation, dependency risk, and source that is not indexed and therefore cannot be verified. Read-only: the scanned code is never imported, installed, evaluated or run.

Outbound route pool for DeepSeek Harness. Ships 15 seed routes plus a 20-entry candidate pool covering 7 target kinds (GitHub raw/codeload/main, npm registry, PyPI index, HuggingFace, general). Routes are verified before use: upstream IP lists go through a TLS handshake with full certificate-chain validation (a bare TCP check can be answered locally and report dead IPs as healthy), and failures advance a cooldown ladder of 2/5/15 minutes with the fastest healthy route picked per target kind. Routes are applied by rewriting the URL with one of four rules (prefix, registry, index, host-replace), reaching git, pip, npm, pnpm, gh, curl and wget through three paths: the shell seam (download commands the model runs through the bash tool are intercepted and rewritten automatically; commands wrapped by the pwsh tool, and fetches made by the host itself or the renderer, are not covered), two registered tools the model can call directly (line_pool_status, line_pool_run), and child-process spawn. Multi-line commands keep their line breaks and only the download segment is touched. URLs carrying credentials (user:token@host) are never rewritten, so tokens are not forwarded to third-party mirrors. No global config is modified. A sidebar panel lists every route with latency, failure reason and cooldown countdown, supports per-route retest and enable/disable, and shows live TUN/proxy status from network-adapter and loopback port checks. The candidate pool is re-verified every 24 hours so newly usable routes are added and dead ones dropped. 570 tests, 87% line coverage.