Plugins

Auto-discovery vision bridge for text-only DeepSeek Harness agents: automatically finds an image-capable model from your configured providers and returns picture descriptions as plain text via a vision tool.

Local-first structured vision for text-only agents: images go to a local OpenAI-compatible VLM and come back as JSON evidence (summary, verbatim OCR, layout regions, entities/relations, colors, explicit uncertainty), with anti-hallucination fallback and an optional paste/upload bridge; zero cloud cost, images never leave the machine.

Synesthesia Encoder for DSH: a vision model translates images into compact structured spatial text (canvas/elements/percentage coordinates), giving text-only LLMs pixel-level image understanding via the `mm_vision` tool.

Registers a `deepseek-vision` provider route: the Web GUI accepts pasted images and transcribes them to text via the free Zhipu GLM vision API before delegating to the DeepSeek adapter.

Routes chat images to a fixed OpenAI-compatible vision model, returns factual observations to the selected main model, and reuses session-scoped observations across replay, compaction, and restarts.

Anti-bot HTTP fetch tools hardened by SXS's production scraping stack (millions of requests/day): UA-pool rotation, retry with exponential backoff, anti-bot wall detection (captcha / verification challenges) and adaptive rate limiting — tools: `sxs_fetch` / `sxs_fetch_json` / `sxs_rate_status`.

Firecrawl-backed web search provider for the built-in web_search tool, with a settings card for the API key and result limits.

Provides the bili_summary tool: Bilibili video metadata, subtitle timeline, and sharp-based frame capture with built-in error handling and graceful degradation.

Trending-topics collector aggregating Baidu / Toutiao / Douyin / Weibo hot lists in one call (Weibo optional cookie), returning titles with heat values for content creators — tool: `sxs_news_hot`.

Safe Kubernetes capability for DeepSeek Harness with workload inspection, bounded logs and events, failure diagnosis, and approval-gated operations.

Jira Cloud issue-tracker integration exposing eight model tools for issue search, project and transition lookup, creation, updates, comments, and transitions; writes are opt-in and support dry-run.

Citation tools for agents: exact DOI lookup, Crossref bibliographic search, GB/T 7714 / APA / MLA / Chicago formatting, BibTeX generation and bounded-concurrency DOI validation.

Unreal Engine .uasset inspection (resolve/registry/load) and restricted Blueprint node editing through built-in UE Python.

Character consistency toolkit: personality profile cards, appearance-weight stats, and behavioral-drift detection for long-form fiction.

A slim port of Headroom: compresses tool output, cuts up to 20% of context, without affecting the model's context cache or agent performance.

Agent config packer for DeepSeek Harness: pack local agent assets (skills/sessions/profiles/settings/memory) into a zip for migration or sharing, with privacy scanning, diff-based restore, pack management, and a settings panel.

Connects DSH to local Beav for Xiaohongshu (RED/RedNote) and social-media AI operations: topic research, knowledge, copywriting, image, audio, and short-video workflows with approval and artifact tracking.

Read-only repo bootstrap scanner (repo_setup_scan tool): detects stack/tests/docs/git/db and recommends plugins, MCP servers and hygiene files.

Data analysis toolkit: CSV/TSV/JSON profiling, IQR and z-score anomaly detection, structured summarization with quality issues, and code-free filter/group/aggregate queries.

Zero-dependency MCP client bridge that connects stdio and HTTP MCP servers and registers their tools as mcp_<server>_<tool> for the agent.

Gives an agent its own email inbox through AgentMail — eleven tools for sending, reading and labelling mail, plus inbound mail delivered into one harness session per email thread, with an approval gate and recipient allowlist on everything outbound.

Long-term memory injected at session start: preferences/facts/summaries/knowledge in global and per-project scopes, budgeted recall via `agent/pre-step`, durable JSON store.

Enhanced auto-compaction defaults for DeepSeek Harness agent presets: apply tuned threshold/retention budgets and per-model policies with one command, idempotent with backups and rollback.

Brings your existing Claude / ChatGPT history into DSH: instant zero-token import of the memories.json inside a Claude export, local Claude Code transcripts with no export needed, and conversations distilled through the model you already configured in DSH. Every memory carries verbatim evidence checked against the source by code — a paraphrase is dropped and counted, and evidence found only in the assistant turns is always routed to review rather than stored.