Plugins

Use a local TraeX coding agent as a DeepSeek Harness model provider over ACP.

DSH plugin: project/task dual-mode workspaces. Tasks skip the workspace picker — every task conversation gets a fresh scratch directory under D:\dsh_working\<name>-<timestamp> (Codex-style), while projects keep the existing workspace flow. Ships an idempo

A minimal Codex harness for GPT models that do not fit DSH's native interface, while remaining compatible with the DSH plugin ecosystem.

Play your own local music in the DSH web UI: the host scans a local folder (default ~/Music) and streams it over HTTP, with a now-playing bar (prev/play/stop, loop modes, volume, live spectrum) and a draggable playlist panel, plus a model-invokable `music_play` tool.

PII masking middleware for DeepSeek Harness: anonymize names, phones, emails, ID cards, bank cards, keys, and addresses to placeholders before they reach the model, restore them at the display layer, keep the restore table only in memory and a controlled

昔涟 (Cyrene) 主题 + 桌宠 for the dsh web GUI — pearl-white pink theme, Live2D desktop pet, particle background, gradient, and a collapsible config card. Ported from Cyrene-Agent (MIT) with the Live2D model creator's permission.

Save messy notes (text + images) to a Yuque knowledge base, classified by the model.

dsh plugin that turns the iterate skill into an autonomous closed-loop harness: plan -> parallel review xN -> atomic fixes -> validate -> loop -> auto-stop, plus a dry-run pure-review mode with multi-round convergence and a meta-review that audits the rep

DSH plugin: loopback WebSocket bridge that mirrors application frontend tools onto the agent's tool registry and forwards model calls back to the application — one bridge, many apps, key-based namespace isolation

Generic LLM gateway model provider plugin for DeepSeek Harness: mounts newapi / LiteLLM / Higress / any OpenAI-compatible gateway as provider routes, auto-discovers the model list, enriches every model with models.dev parameters, and dispatches each model

Terminal-style AI-lab idle game where you hoard compute, train and upgrade models, publish papers, and prestige from neural nets to ASI.

Cross-ecosystem aggregation data layer: syncs the GitHub dsh-plugin topic and the npm registry into one open JSON index, queried by model tools, a CLI, and a minimal stdio MCP server.

Container-isolated backend for the `ctx.codeRuntime` seam: each Code Mode program runs in a fresh container with no network, a read-only rootfs, dropped capabilities, and kernel-enforced memory, CPU and pid ceilings.

Plugin value auditor: pre-install review (source scan + LLM judge) and post-install audit of installed bundles, with model-switch re-audit reminders.

Automatic secret redaction in tool results: masks API keys, tokens, JWTs, private keys and configured secrets before the model sees them.

Codex-style auto-review permission mode: adds an auto-review preset that auto-approves safe sandbox escalations, asks on risky or ambiguous ones, and rejects critical unconfirmed operations.

RLM mode for dsh: recursive sub-agents via a unified rlm() function — spawn, await, and chain child agents as first-class Python calls. Adds a persistent IPython kernel with tools.* bindings and context-as-variable.

DingTalk IM channel via Stream-mode WebSocket: each chat drives its own tooled agent; replies stream back as messages, no public callback URL needed.

Event-sourced cross-session work ledger: register, track and settle tasks with full audit history, kanban export, and a board digest injected into every model turn.

DSH bundle porting Matt Pocock's 25 promoted engineering and productivity agent skills (grilling, TDD, code review, domain modeling, etc.).

Reads assistant replies aloud via Fish Audio API only (bring your own key): per-message read-aloud, auto-read toggle, and a settings page for model, voice reference_id, encrypted API key, and proxy.

Full-duplex voice mode for the Web UI: a composer mic (RMS endpoint detection) transcribes speech with whisper running locally in the browser, assistant replies stream back as spoken audio sentence-by-sentence, and speaking interrupts playback and the running turn (true barge-in). No API key.

Give text-only models vision: a describe_image tool that delegates images to a vision model from your dsh model list over the harness's own LLM runtime.

Give your text-only model eyes - chat image attachments are auto-described via a vision model (default prompt), with iterative re-parsing through model-generated prompts when details are missing; system/custom model modes + GUI config panel, key-safe secret handling, and a small host patch for DSH 0.1.0-rc.6 (see repo README).