Plugins

Opt-in DeepSeek Harness Skill-only bundle for the Archify architecture-diagram skill.

Swaps the filesystem and bash providers for a mirage virtual workspace: file tools and shell commands run over mounted resources (RAM, S3, Redis, Slack, Gmail, Notion, Postgres) instead of the host disk, with per-mount read/write/exec modes, per-command sandbox routing (monty, pyodide, quickjs in process; docker, e2b, daytona remote), and installed CLIs (git, gh, slack, linear, ntn, gws, or one you register) as head words in the virtual terminal.

Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).

DeepSeek Harness tool plugin that exposes BrowserSkill (bsk) browser automation to the model

Runs local security audits of AI API relays and LLM proxies from DeepSeek Harness, producing Markdown reports for prompt injection, model substitution signals, tool-call rewriting, error leakage, stream integrity, and profile-gated Web3 risks.

Vision tasks for text-only models: intent-aware image Q&A, long-screenshot OCR, UI reproduction, grounding, and pixel diff.

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.

Interactive UI components rendered inline in replies: layout, charts, forms, quizzes, mermaid, 3D scenes, and an action event loop back to the model.

In-conversation generative UI: the model renders interactive HTML cards into the chat stream, with streaming preview and sandboxed rendering.

Sidebar usage panel that attributes tokens to the relay site that served each request, read from your existing provider config: today/month/all-time totals, per-site and per-model breakdowns, a year activity heatmap, and New API / Sub2API / DeepSeek balances.

Adaptive reasoning slider skin that maps each model's available reasoning efforts onto a 0–30 visual intensity scale, with synchronized portraits, background, and interface colors.

DSH适用的Codex风格的思考强度滑块，以及大肥鱼跑步滑块。Codex-style model and reasoning-effort slider for DeepSeek Harness

Multi-provider usage dashboard with provider/model token breakdowns, calendar drill-downs, account balances, and OpenCode Go / Z.ai subscription quota tracking.

Unofficial Command Code LLM provider: registers a `commandcode` route with a live model catalog and reasoning-effort support.

Persistent multi-model squads configured in Settings and selected in the Composer, with per-member model/tool policies; the main Agent dynamically plans each send as a bounded DAG with bounded reviewer/repair loops, while Run Center tracks retries and per-member tokens from official Harness usage events.

DeepSeek Harness (dsh) bundle wiring SkillRoute's skill router into your agents.

Let Your Ideas Flow — Tydora is a modern desktop Markdown editor combining WYSIWYG editing, bidirectional links, mind maps, and an infinite canvas — empowering deep thinking and effortless expression.

Expose MineRU document parsing tools to the model.

Second-model auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.

Word alternatives and underscore-gated fill-ins in the composer. End a line with _ and it is filled; misspellings are flagged as you type. Routes through the model dsh is already configured with, so it needs no API key.

Lark/Feishu bot channel for DeepSeek Harness: each chat drives its own agent, and tool approvals, model questions, and plan reviews return as cards answered by a button or a reply. Switch workspace and model from the chat (`/cd`, `/model`, `/new`), and run several bots that keep separate sessions and can hand turns to each other in one group.

Silky streaming reveal for the Web UI: text appears at the model's arrival rate, new lines glide in, no flicker; follow stays with the user and prefers-reduced-motion is respected.

Auto mode for DeepSeek Harness (dsh): an Auto entry in the Permissions selector whose approval prompts are answered by OpenGuardrails policy instead of a human — plus the full OGR guard engine underneath. No core changes.