Plugins

Remote DeepSeek Harness with full server-side API access (`settings.*` / `credentials.*` / `host.listDirectory`). Token-gated reverse proxy, per-device sessions, phone invite QR, fence self-check, optional approval / CIDR / idle timeout / local TLS, WebSocket/SSE.

Reflective self-evolution plugin for local Qwen3.8 27B/3.8 Flash and online APIs: a coding-loop convergence steerer curbs Qwen3.8 27B/Flash repeated-verification deep-thinking to converge faster and cut thinking time; a five-state delivery guard detects and corrects stuck turns and infinite loops; model-agnostic host logic, mostly compatible with online APIs; per-use continual self-improvement with counter-reason self-checks, critic escalation, inverted-index memory retrieval, coding-loop convergence steering, and a five-state delivery guard.

Smart Charts skill: turns CSV/TSV/TXT/XLSX/XLS/JSON data files into standalone interactive ECharts HTML - 32 chart types including offline maps, 3 themes, no CDN. A --profile data profile (per-column dtype, cardinality, missingness, samples, statistics, entity grain, insight signals) lets the agent read the data and pick the chart itself; each chart embeds a fact sheet (plot_stats + data_preview) whose numbers are the only quotable values. LLM transform code runs in a restricted sandbox (blacklist + AST whitelist + safe builtins); --doctor self-checks the Python environment. Fully offline, ECharts bundled.

Plugin manager with a rescue center: grouped enable/disable by necessity, multi update sources (npm / dshfind market / GitHub), browser-first downloads with an auto-install folder, P2P fallback, pre-boot self-check and broken-bundle quarantine.

Law paper writing corpus for DeepSeek Harness: 850 bibliographic records from four CLSCI journals (2024-2026) with title, authors, abstract, keywords and outline, supporting BM25 search, framework cards, journal profiling, submission self-check and export.

Detects which conversation model an account is being served: launches concurrent throwaway probe conversations, scores each streaming chain-of-thought by how its paragraphs open, and cancels probes that read as the older model within seconds. Includes an offline self-check that replays 13 hand-labelled chains-of-thought through the same classifier.

Voice tools: free edge-tts neural speech synthesis, OpenAI-compatible ASR transcription, voice list, batch voice preview and health self-check.

Citation tools for agents: exact DOI lookup, Crossref bibliographic search, GB/T 7714 / APA / MLA / Chicago formatting, BibTeX generation, bounded-concurrency DOI validation and health self-check. A step-by-step first-run guide (3 steps) now opens inside its settings panel.

Browses Bilibili on your behalf and actually takes part: search videos, like, coin, send danmaku, post comments, reply to other people, and keep replying when someone answers back. Reads the video's Bilibili AI subtitle (or transcribes the audio locally when there is none) so its comments talk about what the video really says, and it reads that same content before choosing whom to reply to. Instead of copying other people's sentences, it distills rules about how to sound like a person and gets less AI-ish the more it runs. Skips videos it already browsed, de-duplicates replies per thread, and after too many rounds with the same person in one comment section it reviews whether the exchange has any substance -- if it looks like two bots complimenting each other, it says one last line and stops replying to that person there. Checks whether each comment is genuinely public or only visible to your own account, can scan any time window (last hour / day / 3 days / all) and lists the ones others cannot see, warning you on the overview when replies got folded. Six-tab settings panel where every change takes effect immediately with no restart, a manual run that queues behind the background listener instead of being refused, and an environment self-check that tells you exactly what to install. Requires Python 3 for the Bilibili actions; the built-in check lists any missing packages.

Auto maintenance and resilience for DeepSeek Harness: startup self-diagnosis, automatic repair of missing directories, scheduled configuration backups with rotation, one-click restore, smart-start port detection, plugin-change self-check with automatic rollback, startup failure rescue, and a health watchdog that restarts a stuck-but-alive instance. Ships as a Cordis plugin plus a standalone CLI.

Knowledge-planet (zsxq) knowledge base toolkit: sync posts and attachments, extract docx/PDF text and images, rebuild an index, search, and self-check — pure JS, no Python. Requires a Knowledge-planet subscription and its Cookie, pasted into config.json.

Deterministic code security review: 40+ rules, secret entropy detection, staged-diff review, SARIF export, baseline acceptance, SBOM-lite dependency inventory and health self-check. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

Bilibili curation floating panel for DSH: learns your interests on a probability schedule and decays them by half-life, picks videos inside a token budget derived from a daily money cap, and mentions you only when a fit score passes a threshold. Comments are off by default; once enabled they run in draft-and-confirm or self-checked auto mode under a daily quota, with a hard no-comment rule for political, government and frontier-science topics, and comment text is scrubbed for account identifiers before it can be posted. It signs in through your own Bilibili account cookies; a separate posting account is recommended.

Cross-session memory for DeepSeek Harness: a three-tier store (behavior notes, deep details, session archive) plus a 600-character core card injected every step, work/companion/learning state lines, multi-person and multi-group records with visibility partitions, session-scoped suppression or deletion of memory fragments, summaries and fact candidates that can route to a separate model, and backup plus self-check tools. Data is plain text under the home directory, and entries can carry images and audio stored by content hash.

A gold switch beside the composer that raises every model request to the strongest reasoning effort the current model declares and to its default max output tokens, and adds a system-prompt section asking for exhaustive, self-checked work.

Per-step context ledger for dsh: measures what every step actually re-sends, then offers three opt-in gates — a schema-budgeted tool table, long-tail result externalization, and duplicate-read pointers. In the author's A/B test the tool-table gate cut 16,110 first-step prompt tokens (-49.7%), about -23% of per-step context on long sessions. v0.3.1 adds a read-only /budget-doctor self-check, spill index maintenance and a growth forecast.

Select text in a conversation to attach a numbered highlight with a colour stored per note, keep every mark in an outline panel that jumps back to its quote, and let a corner self-check badge report style, selector and saved-key problems without opening dev tools.

TRAE-style conversation rollback rebuilt for DSH 0.1.7-rc.2: per-turn file checkpoints restore touched files and truncate the model context in place under the same session id. Adds a /rollback doctor framework-contract self-check, an affected-file diff preview computed against the current on-disk state so it stays correct after a restart, a one-click undo-last action with a Ctrl+Shift+Z shortcut, a setting for whether rolled-back messages stay hidden, and English UI text.

White-box causal guardrail for dsh: every tool call is adjudicated before execution along a deterministic causal logic chain — blocks destructive and credential-file operations, escalates repeated boundary violations, cuts faulting links until verified-fixed, and gives risk verdicts on un-auditable execution; runs fully local with zero API cost, plus 6 white-box self-check tools.

Test-stability tools: repeatedly run vitest/jest/pytest/node:test suites, classify flaky cases, keep history, maintain a quarantine manifest and health self-check.

DeepSee: DeepSeek Harness vision, multi-model routing, and Gemini visual self-checks before delivery

Drive an Edifier Halo PixelBar — a 256x32 1-bit dot-matrix screen in a desktop speaker — from DSH over raw USB HID: push custom bitmaps, play GIF animations, render pixel-art walk scenes from sprite sheets and push self-rendered text, with a color-calibration table, a hardware self-check and EQ / volume / lighting / face-scene control. A push can return the screen to the clock afterwards.

Freezes a six-step repair chain into callable tools — freeze the facts, measure the real shape, minimal repro, single-variable A/B, a judge that must say OK, delivery gate — plus a zero-dependency boot self-check (path drift, missing files, version sync, crash-log freshness), per-item tunables and a rollback ledger that backs up every action.

Registers a frontend-design skill that asks for a design plan and token system before writing code, and ships Chinese typography rules plus a measured no-screenshot self-check. It provides one skill and no tools, makes no network requests and writes no files.