Plugins

Layered memory for DSH whose agent-facing surface is 10 tools: high-privilege writes (memory_add, memory_delete, memory_import), rumination controls (memory_ruminate, _cancel, _status), and a memory graph (memory_search_graph, memory_expand_graph_node), built over an L0-L3 distillation pipeline that recalls and injects relevant memories before each model step.

Role-based multi-agent team for DeepSeek Harness — your digital workforce. One goal assembles a team of product, architect, frontend, backend, reviewer and QA roles that deliver through a nine-phase gated pipeline, plus a persistent team you can keep directing across sessions. Zero runtime dependencies, no build step.

Signs in to Huawei Cloud CodeArts and registers CodeBuddy, WorkBuddy, LobsterAI, Qoder (global and China), TRAE, Cline, Loomy, Raccoon Work, MiniMax Code, TeleAgent, ZCode, Step Code and Antigravity as LLM providers, with per-provider account pools; several of them also show quota balance and daily check-in in the same panel.

DeepSeek Harness plugin that turns Jev judgments into three automatic actions — pruning oversized tool output to the segments relevant to the request, screening fetched pages for instructions aimed at the model, and picking which skill fits the next step — plus the jev_ask and jev_gate tools, a judgment ledger that survives restarts, and a /jev-status report. Needs a TypeSafe API key; without one it is inert and sends nothing.

A better fold bar: automatically folds tool calls and Think segments into step fold bars, and collapses each finished turn into a single turn header with live metrics (duration, TTFT, token, tok/s, cache hit) — only the final summary stays visible; customizable leading icons with animated poker cards built in (suit-cycling card animation while running, a deck when collapsed, a fan when expanded), a settings row for the official fold mode, compatible with both new and old DSH versions. Zero intrusion into DSH source.

Replay sessions on a playable timeline with per-step token usage, audit sensitive operations, estimate cost, view fork lineage, compare sessions, and export standalone HTML replays.

Project documents and long-term memory as plain Markdown in a dedicated Obsidian vault: six mem_* tools (search, read, write, log, brief, admin), one budgeted recall injection at the first step of a session, and automatic distillation of completed turns. Obsidian does not need to be running, and the vault stays readable with the plugin uninstalled.

Authentication gateway for the DeepSeek Harness Web UI: the login gate covers pages, /api, /plugins and WebSocket upgrades; PBKDF2 password hashing with per-user salts, HttpOnly SameSite session cookies named per DSH_HOME and IP-based login lockout; invite-code registration; two-factor login with TOTP or passkeys (WebAuthn: several keys per account, phone enrolment by QR, username-less sign-in, and a step-up before any login factor is added or removed); a user-management settings panel (users edit their own profile and manage their own TOTP and passkeys, admins add or remove users, reset passwords, manage invites and clear the passkeys of a lost device); per-user model and API-key configuration whose private entries are encrypted with a key derived from the login password and stay unreadable by any admin, with admin sharing to selected users (usable, balance visible, key never shown, revocation immediate) and unconfigured users blocked rather than falling back to the deployment configuration; per-user isolation on the REST and list APIs and per-frame ownership filtering on the WebSocket mux; session persistence across restarts; a JSONL audit log; and a fail-closed gateway. Requires the DSH 0.2.0 line (the 0.1.1-rc.2 transport line was removed in 0.7.0); passkey login needs a localhost or HTTPS origin because browsers require a secure context.

Template-driven code review skill: five-step review flow, critical/medium/minor severity grading, four-dimension scoring (quality, security, performance, maintainability), dual text and HTML report output, and an on-demand reference knowledge base.

Learning mode that explains each agent step (WIP).

Wraps work in named tasks and, once a task closes, folds its whole span of messages into one summary at the next step boundary; the original content can be restored on demand.

Multi-machine sync: keeps multiple dsh replicas consistent through one private GitCode repository — skills, sessions, settings and plugin manifests each with an independent switch; changes go through branch, PR and merge, remote-only additions are pulled back before every push so nothing is deleted, and an AI smart-align step semantically merges files both sides changed (plus one-click conflict resolution); private repos enforced, pull never overwrites local edits.

Move sessions across workspaces by drag-and-drop with true in-place migration; recover orphaned or unregistered sessions; re-point stale workspaces after folder renames. IDs and history stay intact, with per-step backup and rollback.

Persona engine for DeepSeek Harness: one config.json drives the AI's self-name (per model, per tier), how it addresses you, relationship stance, character text, per-item work contracts with individual toggles, thinking-chain language, appearance and reply tone (both opt-in and per-model overridable), and long-term memory gated by human confirmation - the AI can only append proposed candidates, a human confirm line flips them into effect, and the log is physically append-only and replayable. Confirmed entries are injected as a quoted data-not-instructions block; entries tagged with a kind can instead be routed to arbitrary files on confirmation and never reach the prompt. Three prompt sections re-evaluate from disk on every assembly, so edits apply on the next step with no restart. Persona presets are shareable JSON snapshots (imports and exports SillyTavern character cards, v2/v3 read, v2 written) and deliberately never carry memory. Zero runtime dependencies, no network, no shell; any error degrades to an empty section rather than a broken session. Ships blank - installing changes nothing until you write something.

Trellis-style workflow for DeepSeek Harness: per-turn phase breadcrumbs via agent/pre-step, bundled skill provider, and DSH-native task/phase state with git-cleanliness guardrails.

Live token stats under the DSH Web composer: streamed tokens/s, output token and first-byte latency, plus per-step estimate-vs-actual reconciliation using the official BPE tokenizer, to tell a slow stream from a stalled one.

Cross-session persona and diary for DeepSeek Harness: a local gate decides whether a turn is worth remembering, then one extra model call turns it into a first-person diary entry plus an impression of the user, where every impression carries the specific moment that produced it. Later conversations inject about 2000 tokens of that as a self-memory block in three registers: a persona core, a section for judgements the model wrote itself, and the diary. There is a tool for the model to record a judgement in its own words, and a plain markdown hand-note file the human can write into which the plugin only ever reads. A sidebar panel lets you read, forget or export the archive, and forgetting demotes an entry rather than deleting it, so an old one still surfaces on a strong topical match. Local-only, secrets are stripped before anything is sent, and the archive is a plain folder you can read, edit or carry to another account. Zero runtime dependencies, no build step.

css-in-js styling kit (styled / Token / Styling) for the forked conversation UI: consumes the official --dsw-* design tokens, so no CSS Modules precompile step is needed.

Team knowledge base for offline knowledge sharing (FDE box scenario): browse, full-text search and refinement entry points; raw material is queued automatically and distilled into wiki pages by a serial bot session (Karpathy LLM Wiki pattern: immutable raw, two-step refinement, log stream, monthly lint).

Experience memory and reflection for DSH agents: automatically extracts candidate lessons after tasks and recalls user-reviewed lessons in relevant later tasks. Supports source provenance, project-scoped retrieval, conflict handling, usage feedback and expiry review; capture and recall have separate controls, and writing lessons to AGENTS.md requires preview and explicit application. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

All-in-one local memory: JSONL files per scope (session, project, global, or a custom name) with per-scope dedup, five model tools (memory_save, memory_search, memory_list, memory_get, memory_forget), automatic recall and hard rules injected into the agent pre-step, and a settings panel. Retrieval combines lexical IDF with a local embedding backend, which the panel can install and manage itself.

kimi-tide（月汐）— preset-and-rule model router for DeepSeek Harness（预设+规则驱动的逐步模型路由）：named presets with ordered image/keyword-group rules route each agent step across ANY mounted provider/model (candidate pool = full host catalog enumeration, no whitelist), w

Model-autonomous context compaction for DeepSeek Harness: a mind_map tool surveys the agent context surface (stable seq ids, roles, token weights, clear-boundary markers, the clear-mind playbook), a clear_mind tool replaces a chosen conversation-history span with a model-written checkpoint through the native compaction transaction, call and result pairs self-collapse into one-line tombstones, and a proactive reminder nudges the model when the context grows long or a turn runs too many steps.

Per-step model router: named presets with ordered image/keyword-group rules route each agent step across every mounted provider and model, adding collaboration flows for image transcription, an image guard, a multi-plan quota panel, and per-step decision observability.