Plugins

Open-source CMA-compatible agent runtime for any model, with MCP tools, sandboxed sessions, audit, replay, and a local console. Includes a native DeepSeek Harness bundle over stdio MCP.

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

Support dsh runtime on Multica.

Run the dsh runtime on Multica.

Branch-based message editing, reroll, retry, and a version timeline.

Deep Mnemon integration: local three-tier memory (Runtime Memory, retrievable Documents, supervised Memory Spaces).

Zero-dependency toolkit: time / encoding / json / calculator / csv / regex / markdown / diff / stat / schema — ten deterministic tools in one install.

Right-side dot-timeline rail: jump between user messages.

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.

可配置子代理 profile 系统，单一 subagent 工具 + profile 参数，含 Web UI 设置/实时进度/子代理树 | Configurable subagent profile system: single subagent tool + profile param, with Web UI settings/real-time progress/subagent tree

Blender 3D production plugin with 30 modeling/reconstruction skills, 13 runtime tools, and 26 deterministic helpers for reference fitting, rendering, validation, animation, and portable export; installable as `dsh-blender`.

DeepSeek API balance and 24-hour usage dashboard in Settings, with estimated spend, token counts, request counts, and an hourly timeline.

A DeepSeek Harness plugin for real-time token tracking and highly accurate session cost estimation, featuring dynamic peak/off-peak pricing support.

DSH-TUI: a lightweight and fast terminal plugin connected directly to the DSH runtime.

One memory layer for every AI tool and agent: Context Bundle injection, prompt-time recall, MCP tools, and turn-end DSH thread capture.

Real-time outline panel for the DSH Web session page: user questions plus a Markdown heading tree (H1–H6) that updates live during streaming, with click-to-locate highlighting, expand-depth control, search, and per-session favorites.

DeepSeek balance and token usage in the web sidebar, with a today/all-time toggle and provider filtering.

Animated blue-whale desktop pet with per-session response progress, model activity and tool-call traces, token counts, output speed, elapsed time, and collapsible multi-session status cards.

Read-only runtime management panel for the official DSH MCP client: connection status, registered tools, errors, and reconnect counts through the /mcp command and a Settings tab, with sanitized display and enable/disable patch suggestions.

Fail-closed Feishu (Lark) channel bridge: chat with a bot, get dsh agent turns back. Official-Python-SDK-only integration (exact-pinned); deny-by-default allowlist, webhook signature/timestamp/replay verification, per-chat sticky sessions; bilingual docs.

Strict ISO 8601 parsing, IANA timezone conversion, and UTC calendar arithmetic.

DSH↔Godot engine runtime bridge: launch and drive a running Godot 4.x game through its in-game TCP interaction server — 8 tools (scene/UI inspection, GDScript eval, input simulation, screenshots, headless static ops, script validation), replaces godot-mcp.

DSH book-to-skill plugin: a 5-stage long task (fetch → parse → understand → generate → install) with 3 human gates, host tools for the agent and a browser timeline panel

Per-model capability declaration for DeepSeek Harness: reasoning-effort levels (wire spellings) + request modalities (vision) for OpenAI-compatible providers. Settings section, zero runtime harness deps, no YAML.