Plugins

Shared real browser for DSH: a native Electron window the human can watch and take over, driven by the agent over CDP with 20 browser_* tools (open/snapshot/execute/fill/screenshot/download/auth), per-task session isolation, cookie persistence, CAPTCHA detection; self-hosts on plain dsh web without a desktop shell.

Connect ChatGPT OAuth and OpenAI Codex models to DeepSeek Harness, with opt-in search and image tools.

Bridges a DSH session and QQ over NapCat HTTP, forwarding agent replies to QQ and feeding messages you send in QQ back into the session.

Other memory plugins help your agent remember more. This one decides what is allowed to count: agents propose, a human approves (three-store gate + immutable audit log), and recall runs on SQLite FTS5/BM25 with zero model calls (measured p50 2.3ms). A token ledger shows what recall actually cost. One vault for DSH, Claude Code, Codex, Cursor, OpenClaw, Hermes, MengBot and any MCP client. v0.31 adds five one-click skins (Default, Pop, Light, Resident Evil, Spider-Man) with full-bleed theme banners and per-skin hover contrast.

Lowtide (as in low tide) runs task batches automatically in off-peak hours — a highly customizable task framework with four execution strategies, L1–L3 semi/full-auto adjudication, in-place task editing and preflight checks, built on the Cordis microkernel, one build for both desktop and web.

Google Antigravity (agy CLI) models for DSH — streaming chat with Gemini/Claude/GPT-OSS subscriptions, native tool cards, thinking turns, and in-GUI Google OAuth login.

OpenPencil design preview and editing plugin.

MCP Apps Host plugin for DeepSeek Harness: renders interactive HTML cards from MCP _meta.ui in sandboxed iframes, bridges postMessage to MCP tools/call and resources/read

Browser agent.

Arknights: Endfield industrial-editorial theme for the DSH Web UI: cream paper, ink text, zero border radius, two switchable accent palettes (signal yellow / teal-cyan), plus optional marching-squares contour background, ENDFIELD watermark and boot progress plate.

Local Git-backed long-term memory for DeepSeek Harness with hybrid CJK/English retrieval, cited context, transactional sync, previews, and rollback.

Model-driven context compression (Active Context Pruning) for DeepSeek Harness: the model decides when and what to compress.

Select text → annotate → send with your message; replies map back to each annotation.

Generates game art from reference images via Seedream image generation and MiniMax image-to-video, assembling eight-direction sprites, sequence frames, and skeleton animations with local green-screen keying.

Moves an existing DSH session to another agent preset through a previewable five-section handoff, preserving the source session and either pausing the target for confirmation or continuing immediately.

Diagnoses and repairs DeepSeek Harness on native Windows around the official persistent PowerShell and Workspace Write stack, creates the desktop shortcut, and keeps earlier Git Bash and BusyBox presets behind an explicit legacy setup. No WSL.

Three-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggable long-term memory, smart routing, supervised agent workflows, WebUI, and headless tools.

Superpowers for DeepSeek Harness: TDD, debugging, planning, and collaboration skills adapted from obra/superpowers, installed as a Cordis plugin registering 14 skills with zero runtime dependencies.

The DeepSeek Harness plugin shop: browse, install, enable, and update dsh plugins from a git-auditable catalog.

Evidence-first attention supervision for DeepSeek Harness with C0–C3 policy, deduplicated Inbox alerts, quiet hours, and redacted outcome records.

Authenticated mobile gateway for DeepSeek Harness: connects the companion native iOS client over WebSocket for sessions, live events, tasks, goals, approvals, commands, and file transfers, with QR pairing and device revocation.

UltraCode-style multi-agent orchestration: a generatable, savable, governable, observable, resumable workflow layer.

Red-team engagement mode: send one target organization name; a planner session runs five execution roles (recon, asset triage, vulnerability discovery, exploitation, internal pivot) with configurable concurrency; preflight checks skills/resources; scoring uses four stages (recon, internet, boundary, internal) with server-side caps and privilege-wins dedup; findings stay in a local SQLite fact base. The persistent right-side console has nine pages and includes asset mapping, agents, sessions/tunnels, findings, score targets, reports, POC knowledge base and skill library. v0.15.2 adds automatic HTTP evidence/action records, batch ingest, scope check, tunnel pivot probe, data proof, cleanup ledger and T0-T3 asset admission to prevent scope drift. 59 redteam_* tools; 38 bundled skills.