Plugins

GPT plans dependency DAGs, DeepSeek workers execute tasks with adaptive parallelism, and an optional GPT reviewer audits incremental Git diffs and drives repair rounds.

Agent teams: spawn named long-lived teammates, coordinate them with a shared task list, member mailbox, and virtual workspaces, and watch the team live in a team-room tab.

Cron scheduler with a sidebar UI: run shell, Python or Node scripts, skills, or agent tasks on a schedule, with push notifications and session archiving.

Adds persistent execution contracts, recursive work graphs, critical clarification, and evidence gates for long or underspecified Harness tasks.

Run Stata through DeepSeek Harness: the native Stata AI Skill service auto-starts with DSH (macOS/Windows binaries bundled), so you can run regressions, do-files and econometrics workflows with no manual setup.

12 tested engineering skills (git commit, code review, test-first, plugin dev, debugging, changelog, PR review, task breakdown, and more): every SKILL.md passes a format validator aligned with the official skill rules plus an isolated load smoke test.

Matt Pocock full promoted skill set (25 SKILL.md: grilling, writing-for-agents, wait-what, TDD, code review, wayfinder, ask-matt router) ported to DSH.

Ponytail lazy senior dev mode: 6 skills adapted from DietrichGebert/ponytail.

273 ECC skills (95.8% of the 227k-star operator system) ported to DSH in four batches.

In-chat preview for produced files: click a produced-file chip to render Markdown (server-side markdown-it + highlight.js), images, or plain text right in the conversation; system-app open and reveal-in-folder stay one click away.

Turn raw data (CSV / pasted table / SQL results / DuckDB) into a structured Markdown report with business conclusions, metrics and charts.

Preview Mermaid diagrams as images via local rendering in DSH Web when the chat message contains a Mermaid fenced code block, and also allow integration with external rendering servers.

Voice pair: free edge-tts neural speech synthesis + OpenAI-compatible ASR transcription.

Voice input for the Web UI: a mic button that drives local VocoType offline speech recognition and auto-inserts recognized text into the composer (auto-deploy, dedupe, continuous dictation).

Mic button in the composer tool row: Web Speech API speech-to-text (Chrome/Edge), language switching, and optional auto-send, zero dependencies.

Universal image generation for DeepSeek Harness: auto-discovers image models from any OpenAI-compatible endpoint (SenseNova, StepFun, Agnes, Qwen, Flux, SD, Imagen and more), with agent tools and REST API.

Renders pasted/uploaded images inline in the DSH Web chat and gives text-only models vision: the model-invokable visual_review tool calls any OpenAI-compatible multimodal API first, falling back to a local Qwen3-VL worker.

Vision-augmented DeepSeek adapter: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description.

Full vision-capability bundle for DeepSeek Harness: a vision_understand tool (OpenAI-compatible vision APIs, free Zhipu GLM-4V-Flash by default) plus paste/drag-and-drop/button entry points for image recognition.

Local OCR for attached images via Tesseract: only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.

GPT Image 2 `image_gen` with Codex subscription OAuth by default or explicit API-key mode: developing card, up to three live API partials, durable attachment replay/lightbox/download, text-only model output, and bounded credential-safe requests.

Vision bridge for text-only DeepSeek routes that analyzes attached and local images through configurable OpenAI Responses, Chat Completions, or Anthropic Messages endpoints while leaving image-capable routes native.

Combine text, vision, and image-generation APIs into one Mix model with automatic routing: text-only requests go to the chat model, user images and agent screenshots go to the vision model, follow-ups keep using the same session image, and agents can generate or edit images with session-scoped call history.

Drive the user's real browser through the local Kimi WebBridge daemon: navigate, find-tab, snapshot, click, fill, evaluate, CDP, screenshot, network, upload, PDF export and tab-management tools that reuse existing login sessions.