Plugins

Three-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggable long-term memory, smart routing, supervised agent workflows, WebUI, and headless tools.

Project-scoped cross-session memory: seven-layer SQLite store (soul/user/project/fact/lesson/rules/topic) on node:sqlite, cache-friendly first-message injection plus per-message keyword hits, memory_remember/search/find_similar/read/update/project tools, and idle-window consolidation ("dream") with peak-hour suppression. Prompt texts ship as per-language data files — the framework supports multilingual users.

Roleplay workspace for DeepSeek Harness: import SillyTavern/TauriTavern character cards or author one from scratch through an interactive flow; turn a long TXT novel into a playable card with either an intensive or a coarse reading pass; the main agent consults worldbooks on demand, and prose is read in a dedicated tavern reader tab; explore multiple worldlines inside one conversation (regenerate, edit-and-send, explicit clone); scoped style presets with 16 built-in styles, a character agent cluster, a standalone decision card, and card or novel export; long stories hold together through a frozen settings prefix, a hard-cut context window, traceable director notes and keyword/semantic/hybrid recall, with embeddings either online or fully local. Targets Harness 0.1.2-alpha.3 and applies its documented compatibility patches.

Chat meme stickers: text-only send, mood auto-send, QQ/WeChat-style picker, auto-learn, custom packs.

The memory that dreams — cross-session memory for DeepSeek Harness: recalls you across sessions, auto-consolidates in its sleep (autoDream), freezes conflicting memories for your review, and keeps a replayable audit trail. Offline-first local semantic search over SQLite with human-editable Markdown mirrors, an entity graph, an interactive memory panel, plus an external API and CLI.

Adds a Managed Agents settings tab and MCP tools to dispatch long-running agent tasks to Ark cloud Managed Agents.

Registers Ark Agent Plan, Coding Plan and postpaid model routes in the native DSH model picker.

ChatGPT OAuth provider for Codex models with subscription web search, quota and safe reset, image tools, Fast mode, and model-aware context; no API key or Codex CLI.

Select text → annotate → send with your message; replies map back to each annotation.

Auto-resumes interrupted DSH Web requests: sends a queued 「继续」 after network, timeout or host-crash failures, with error classification, adaptive backoff, templated continue text and browser notifications.

Adds a strip above the composer to recall sent-but-unread (steering) text messages before the model reads them.

Arknights: Endfield industrial-editorial theme for the DSH Web UI: cream paper, ink text, zero border radius, two switchable accent palettes (signal yellow / teal-cyan), plus optional marching-squares contour background, ENDFIELD watermark and boot progress plate.

Cleans AI traces from Russian text: finds chatbot copy-paste artefacts (ChatGPT, Gemini, Grok, Perplexity, DeepSeek), strips hidden text marks (zero-width characters, invisible layout; shadow scan catches markers split by invisibles), and rewrites the text into natural prose on request; 40 regex markers, 38 with full evidence-registry entries; 156 gates, 530 tests; offline, text-only bundle (binary metadata removal lives in scripts/).

Model-driven context compression (Active Context Pruning) for DeepSeek Harness: the model decides when and what to compress.

The memory that dreams — cross-session memory for DeepSeek Harness: recalls you across sessions, auto-consolidates in its sleep (autoDream), freezes conflicting memories for your review, and keeps a replayable audit trail. Offline-first local semantic search over SQLite with human-editable Markdown mirrors, an entity graph, an interactive memory panel, plus an external API and CLI.

The memory that dreams — cross-session memory for DeepSeek Harness: recalls you across sessions, auto-consolidates in its sleep (autoDream), freezes conflicting memories for your review, and keeps a replayable audit trail. Offline-first local semantic search over SQLite with human-editable Markdown mirrors, an entity graph, an interactive memory panel, plus an external API and CLI.

Volcengine Ark provider plugin for DeepSeek Harness (DSH): registers Agent Plan, Coding Plan, and postpaid routes on the native pi-ai adapter so Ark models appear in the model picker.

In-place conversation rewind in the same session window without forking (Claude Code /rewind semantics): a per-message ↶ button cuts the model context back to any user message, with an optional Claude-Code-style file restore from disk-persisted before-backups.

Adds account login, API and custom Provider setup, model switching, image fallback for text-only models, and token/cost attribution to DeepSeek Harness 47f.

AI image generation for the DSH Web GUI: text-to-image and image-to-image through a configurable OpenAI-compatible endpoint (gpt-image-2 / gpt-image-1 / dall-e-3), with an api_url/api_key settings card and a sidebar split-pane generation studio.

Proactive associative memory for DSH: zero-prompt recall injected at a fixed boundary, three-layer auto-consolidation, skill crystallization, and Astra-style context management - handoff ledgers and a PLAN whiteboard that survive context-window switches, water-level sensing with an auto-detected model window. Local Markdown storage, model-agnostic, zero deps; lexical 0GB floor with optional semantic tiers.

Claude Code-style auto-memory, natively: typed memory files (user/feedback/project/reference) with a MEMORY.md index auto-injected into the system prompt (zero footprint when empty); memory_write/read/list/delete follow Claude Code write rules (dedupe-and-update, absolute dates, cross-links); workspace-scoped and user-scoped layers, cross-process file locking with orphan-lock recovery, plain Markdown on disk, no external services, no embeddings.

Prevents request context bloat in DeepSeek Harness: catalogs MCP tools and skills under ctx.capability, exposes them in exposed/progressive/blocked tiers, and invokes low-frequency ones on demand via meta_search/meta_invoke, with a visual settings tab.

Execution maze for DSH sessions: the agent's real path — main advance, failed or dead-end detours, backtracks, request retries and subagent branches — drawn on one wall-clock timeline, with three tracks under each lane sharing that axis (tool-call density, token pulse, context pressure) and a deterministic analysis panel below it (tool result matrix, failure-recovery chains, duration distribution); watch it grow live in a session tab, or upload up to 5 session logs for a same-axis compare.