Plugins

Local-first learning mode: cross-session learning threads with per-source explanations.

Projection-driven live DAG for a Session's subagents and durable workflows: status and navigation, deterministic deep-chain layout, fit/pan canvas controls, and current-session node rearrangement.

A chibi blue-haired maid desktop pet for the DSH Web UI with 106 hand-drawn transparent animations, desktop wandering, chat through local Ollama or the DSH online models, and optional screen watching.

Turn a one-line requirement into verified delivery. TeamFlow runs a multi-stage pipeline — triage, PRD, design, technical plan, parallel development, QA with defect rework, acceptance — and gives the model 12 `teamflow_*` tools plus a workbench with a live pipeline graph and a backlog kanban. Each requirement gets its own folder holding the PRD, design, technical plan, QA report and acceptance record.

Preset workbench for editing per-agent personas, system prompt sections and tool descriptions, selecting tools and skills, previewing request context, and importing or exporting JSON/YAML configurations.

Aggregated multi-upstream web search for DeepSeek Harness: replaces native web_search with model-native grounding and agent search APIs, source attribution, and rich citation cards.

Let your coding agent dream: strategies must survive counterfactual replay before they earn trust. An offline self-improvement loop over an evolving world model — no fine-tuning, the LLM stays frozen. Speaks MCP. Ships its Python server inside the package

DSH plugin bundling the kimi-ppt skill: create, edit and export PPT slides and presentations as a locally generated .pptx with Pillow-rendered previews, no browser needed.

Plugin coordination layer: plugins declare their capabilities, commands route to the owning plugin without a model call, tool schemas load on demand to cut prompt tokens, run history consolidates into long-term memory while idle, and failures are classified before any retry.

Zhihu search, agent tools, knowledge bases, and usage tracking for DeepSeek Harness.

Font switcher for the DSH Web GUI: 99 UI fonts and 31 code fonts with CJK-Latin pairing stacks, instant apply and localStorage persistence.

Custom modes / assistant manager: give each mode its own system prompt in the settings page — a custom prompt that is a plain file the agent loop re-reads before every model step, so an edit applies to the running session on its next step — and start it from the official standard / PTC / minimal / Cordis composition, toggling the plugin rows it mounts one by one (a custom plugin composition per mode), renaming it as you like. Several assistants coexist with their own prompts, so one machine can keep a coding assistant, a chat companion and a roleplay (RP) persona side by side — a multi-agent setup you pick from per new session. Rows left untouched stay byte-identical to the shipped ones, platform conditions included.

Agent2Agent mesh.

Learning mode that explains each agent step (WIP).

DeepSeek Harness (DSH) 跨会话记忆插件：对话模型边干边记的 Markdown 项目记忆，支持专题文件渐进式披露、可选后台静默蒸馏、按项目隔离与热更新设置面板。机制对齐 Claude Code auto memory。 | Agent-maintained cross-session Markdown memory: progressive-disclosure topic files, opt-in silent distillation, per-project isolation. Claude Code-aligned.

Compliantly use your own Antigravity quota in dsh: bridges your local logged-in official Antigravity CLI (agy) session as the chat and subagent model provider.

Qingxiao (Wuthering Waves) themed skin for the DSH web GUI, with ice-blue/jade/moon-white palette, sword-light motes and user-swappable backgrounds.

DSH-native integration layer for the Minta memory engine: composes the official dsh-mcp-client row, registers the minta-memory-governance skill plus a session-start memory prewarm, and ships a Minta agent preset; requires the separately deployed Minta engine (Python/Docker) to provide the 19 MCP tools - not usable without it.

Per-conversation persona / master prompt plugin: create, edit, switch and delete persona templates from the composer toolbar, with highest-priority system-prompt injection, fixed interaction guardrails, subagent inheritance, new-conversation default, and local JSON persistence.

"Single-Core Writing" plugin for DeepSeek Harness: Thoroughly tool-streamlined and output-hardened for quantized small models, suitable for running long-novel pipelines locally with on-device models.

Recycle bin for DSH sessions: sidebar delete icons, multi-select restore and permanent delete, live-session protection.

One-level session folders for the web sidebar - group sessions per workspace, move them by drag-and-drop or context menu, archive and restore, server-side persistence.

Cross-session memory with zero-token deterministic recall (bigram-Jaccard fused with FTS5 BM25 via RRF, Chinese-aware tokenization), reinforcement that strengthens repeated observations, and procedures crystallized into SKILL.md files refined in place through an active-stale-archived lifecycle with reversible archive and rollback. Ingest and disposal each expose a user-chosen autonomy tier; conflicts and high-importance writes always go to human review, and nothing is ever auto-deleted. Requires Node 22.5+.

DSH Web GUI right sidebar: VS Code-style file explorer plus source control (git status, stage/unstage/discard, commit, diff, commit graph, fetch/pull/push sync, branch and remote management, git init, multi-repo switch, color-coded file status, file-type icons), an editor view that opens every file reached from the chat, the file tree or source control (Markdown/HTML/PDF/image previews, 15-language syntax highlighting, hunk-level diff editing, Ctrl+S save), file operations (new/move/copy/delete, reveal in file explorer), a collapsible icon rail, a multi-tab bottom terminal (ConPTY), and commit messages generated from the staged diff by a host-configured model.