Plugins

Use a Kimi Code membership in DeepSeek Harness through a dedicated Kimi subscription model route

Dynamic LLM provider gateway latency and health pulse probe for DeepSeek Harness

Cline free models provider for dsh: scan the Cline model catalog dynamically and serve the :free models through the harness LLM seam

DSH provider preset for the Memorax DeepSeek V4 Flash gateway

Harness AI brand occupants for the dsh web client's brand slots plus the Harness theme

Native SuperGrok / X Premium OAuth provider for DeepSeek Harness. Reuses local grok-bridge tokens; no xAI API key.

DeepSeek Harness provider plugin that delegates ChatGPT subscription access and agent execution to the locally authenticated Codex app server.

A cron-based scheduled task plugin for DeepSeek Harness (dsh) desktop: create / edit / delete / fire-now tasks from the settings panel, with cross-session agent follow-up and multi-level notifications. Zero LLM tools — purely human-driven scheduling.

DeepSeek Harness mobile: CSS-only UI plugin, password-protected Cloudflare tunnel and a tiny Android WebView app - use DSH on your phone.

Paired experiments and promotion gates for DSH plugins.

dsh plugin: bounded retry for gateway network_error failures the stock retry policy cannot classify (e.g. OpenCode Zen finish_reason: network_error)

Forgetting-curve in-place dialogue compression for DeepSeek Harness: recent turns stay verbatim, middle turns are structurally dehydrated (zero-LLM), ancient turns fold into a bounded summary pair — unbounded conversations on a bounded memory budget.

Run the main session model on a local Claude Code subscription through the official Claude Agent SDK, taking over the llm/stream route for the claude-code provider, with token-level streaming, session resume, and DSH tools bridged in over MCP so they keep DSH sandbox and approval.

Local LLM integration plugin for DeepSeek Harness

Explicit, evidence-first multi-model consultation for DeepSeek Harness

Nous Portal free-tier provider for dsh: Portal OAuth (device-code) agent-key lifecycle behind an OpenAI-compatible harness route

Ghost-text completion for the composer: FIM suggestions stream in inline after a typing pause (SSE, first token rendered immediately), Tab accepts one word at a time and Shift+Tab takes all, in-flight requests are truly cancelled on retyping or Esc. Plus two-layer typo checking: a browser-local dictionary scan (Chinese wrong phrases, English misspellings and proper-noun capitalization, user-defined per-browser entries) with a debounced LLM context pass, underlined in red in the text with per-item navigation and click-to-fix.

Memory triage for DeepSeek Harness: at the end of each turn it decides which entries to keep and which to archive, routes project-specific ones into a project bucket while global ones stay in the main store, merges near-duplicate entries, and falls back to an LLM when the rules are unsure — automatic actions are recoverable archives only, never deletions.

ego lite for DeepSeek Harness, with a memory it keeps: the agent recalls what it learned about a site before it acts, promotes a script that worked into a reusable site tool, and hands you the keyboard through a real dsh prompt when a page needs a human.

An Obsidian-style knowledge base: ingest sources, let the LLM build and maintain an interlinked wiki, and ask questions grounded in it.

Real Red Alert 2 AI battlefield for DeepSeek Harness with fog-safe control and post-match learning

Pools several OpenCode Go API keys and hot-switches each request to the least-used one, with official usage and balance lookup plus a graphical settings page.

High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness — a drop-in upgrade over dsh-compaction-basic.

Reads the session files thirty-three other coding agents on this machine already wrote — Claude Code, Codex, Cursor, VS Code Copilot Chat, opencode, OpenClaw, Hermes, Kimi, Cline, Zed and more — including sessions from before it was installed: six tools (deja_recall, deja_session, deja_blame, deja_fix, deja_how, deja_remember), a /deja command, and optional automatic recall added to the runtime context. Local BM25 index, no LLM, no embeddings, no network (dsh plugin --profile web add dsh-deja).