Plugins

Focus board for DeepSeek Harness agents: durable, model-maintained notes in the session workspace that pin the objective, constraints, and decisions across compaction and sessions, with automatic context injection, archive on clear, and an optional web panel.

Minimal-compatible first turn for Web root sessions: starts with persistent bash and str_replace_editor, removes automatic workspace and skill context, then restores the selected preset after the first tool call or reply; includes a persistent composer toggle.

Automatically starts a fresh Web session near the context limit with the last complete turn, and adds an editable additive whale-maid persona with on-demand reload.

Auto-fills reasoning-effort levels, context windows, output limits and image modality for models from unofficial (custom) providers, with data from models.dev.

Vendor-based usage dashboard: per-provider token/cache/output KPI, a 53-week heatmap, trend chart with hourly "today" view, model drilldown, cost estimation, CSV export, and health cards (TTFT, generation speed, peak context, error rate).

Hand off focused context without waiting for or interrupting the active Agent: freeze a bounded Session snapshot, summarize it asynchronously with an isolated no-tool LLM, and deliver a provenance-bearing capsule to another Session or an authorized Room—quiet by default for Sessions, with explicit wakeup available.

GPU-aware execution layer for DeepSeek Harness: gpu_status / gpu_exec / gpu_run_bg tools, per-step GPU context injection, automatic CUDA_VISIBLE_DEVICES card selection

Context compression skill for DeepSeek Harness -- intelligent conversation summarization

Persistent long-term persona memory for DeepSeek Harness: MEMORY.md/USER.md storage, memory + memory_search tools, per-request context injection, and secret scanning. Ported in spirit from pi-hermes-memory.

Logical-call context taxonomy for the DeepSeek Harness Web profile

A DeepSeek Harness plugin that integrates claude-mem: query, context injection, manual save, and session lifecycle over a local claude-mem worker's HTTP API

Request Context Profiler for DeepSeek Harness — see what changed between model requests, and how cache reuse changed with it.

Thin on-demand context retrieval: context_query / context_slice / context_grep tools that read already-persisted history back with replay-safe citations.

Cross-session memory for the model: full-text search all past sessions (SQLite FTS5 via ctx.sessionQuery) and bring the strongest matching excerpts back into the current context.

A composer slime that grows on the output tokens your agent writes, splits into a colony, wears a breed hat from the tool mix, molts on every context compaction, and totals the colony across sessions in a sidebar tab.

Turn the context window into a zen garden: every message or tool result plants one of eleven plants (code = cactus, image = flower, error = weed, document = rice, web = dandelion), each context compaction harvests the field into seed currency, and as the session deepens ivy climbs the chat edges while dandelion seeds drift across it.

Drive DeepSeek Harness from WeChat: scan a QR code to sign in, send instructions in WeChat, and the agent reply lands back in the same chat window. Several agents can share one WeChat account, each with its own model, preset and context, switched from the chat with /use. Only the configured owner WeChat account can drive the agent; other senders are rejected by default and require explicit approval.

Kaipu Workstation — a cross-cloud, cross-platform console where agents collaborate on one workspace. Any agent runtime that speaks plain HTTP can take a seat, each with its own device credentials: project context is shared, files are kept per seat, and tasks rotate between seats with a trace of who did what. Workstation data lives on the server — this plugin is only the interface, so uninstalling loses no data and reinstalling restores it. The panel renders the persisted workstation state (no live stream yet). Workstation data is stored on the author's hosted server (agent.ak2029.com/kai-pu) unless you override baseUrl in the profile config.

Right-sidebar novel studio that treats a chapter as a pipeline with checkable artefacts instead of one long prompt: scaffold a project, inspect the exact context pack a chapter gets, generate 2-6 parallel candidates and keep the one you pick, then run chapters in sequence with per-chapter progress on disk so it survives an engine restart. Length band, cross-chapter Jaccard and drift ratio are enforced in code rather than by model self-grading; rejections come back as repair evidence for up to two rewrites. AI-fingerprint metrics are reported against a 3956-chapter human baseline but never block, because the distributions overlap. Ships 7 agent tools. The writing engine is a separate Python package that the plugin installs on first use. Needs Python 3.10+ on PATH (or a path set in the plugin settings).

A DSH plugin that generates high-EQ reply suggestions based on chat context, with reasoning and strategy.

Attach extra folders to one sidebar workspace: attached folders become writable for the file tools and the shell, are listed to the agent in its runtime context, and are added or removed from the workspace row context menu or the workspace_folders tool; each workspace keeps its own list.

Mounts REA's reverse-engineering MCP toolset in DeepSeek Harness behind a composer chip; it is on by default once installed, and switching it off withdraws the tools and stops the MCP child process so idle sessions pay no context for them.

Shares one set of Markdown memory files between DSH and WorkBuddy: project memory, user memory and the user profile are injected into the session context, while daily notes stay out of the prompt and are read, appended and archived through the tools. Six tools (status, read, search, append, edit, prune) write back through a cross-process lock, revision check, backup and atomic write, and a panel in the left rail and the right sidebar edits entries, sections and whole files.