Плагины

Runs Hindsight long-term memory on your own machine: after a one-time uvx --from hindsight-embed@latest hindsight-embed profile create server setup (~450 MB of Python dependencies) and with your own LLM key, the plugin manages the local memory server itself (health probe, start, stop, logs), registers ten hindsight_local_* tools for status, page search, page read, recall, remember and reflect, injects a knowledge-page index once per session, writes each finished turn back into the bank, and extracts facts with your own LLM key. Do not enable it alongside the official @vectorize-io/hindsight-coding-agents plugin: both read the same bank and would inject duplicate context. At session end it writes a handoff snapshot that the next session injects as previous progress. The data directory is configurable (dataDir) and scripts/relocate.mjs moves an existing install to another drive, creating directory junctions where the server hard-codes its paths.

PTC agent preset whose tools.guard refuses tool calls until the session holds an active goal and an in-progress todo.

One main session coordinates several root sessions: a /relay command and 14 peer_* tools for batched status reports, a version-line notice, task-board claims, handoff and wake, read-only session inspection, and a web panel. Phone notifications need the DSHA device bridge.

Gives an agent tools to open foreground sessions, prompt them in queue or steer mode, read the transcript back, cancel a turn, and get the authenticated URL of the local web app.

Adds two entries to the DSH web sidebar above the settings row: a batch picker that groups sessions by workspace, filters them by a search box and moves the selected ones into a recycle bin, and a recycle bin that restores sessions one by one or all at once, or permanently deletes them. The recycle bin keeps its own list in browser storage and hides its sessions by wrapping the host session-visibility check, so it does not use the host archive; a moved session keeps its log on disk until it is permanently deleted. Sessions that are currently running are refused and reported instead of being moved.

Give your agent an external emotion state machine: several axes (0-100) that drift over time and move when you speak to it. Each turn the plugin injects which band you are in plus which tags you may use. The numbers belong to the plugin: the model reads them from the injected prompt and can change them only through the plugin's own emotion tools, never by asserting a mood.

Connect DeepSeek Harness to the local Codex CLI with dynamic model discovery, image input, Harness-owned tools, and read-only ChatGPT plan and quota display.

TeleAgent (China Telecom TeleAI "Stellar" agent) model provider for DeepSeek Harness with the working v1 gateway signing: two-round HMAC-SHA256 keyed by the login JWT signature segment, which fixes the 40104 rejections the older local-v1 signing produced. Signs in through a dedicated browser window over the DevTools protocol — the plugin intercepts the login callback the same way the official desktop app does, so nothing has to be copied by hand — and also accepts a pasted token. Ships points balance, daily check-in, an in-composer account chip, and a configurable context window (100K by default, 16K–2M, since the gateway declares no catalogue and the official client ships one shared 100K preset for all three tiers). Cannot be installed alongside anye-99/dsh-codearts-auth: both register the same teleagent provider, and this plugin reuses its credentials and derives its SSE/tool-call parsing from it.

One Settings page for OpenCode Go: an account pool that rotates A-to-B when a key runs out or stops authenticating, per-account 5-hour/weekly/monthly allowance, per-model spend with remaining quota, capability tags (image, video, text-only, tools, reasoning), a live OpenCode-vs-official-API cost comparison, and 10 UI languages.

MCP server panel for the DeepSeek Harness Web GUI: the sidebar lists every @deepseek-ai/dsh-mcp-client row — including rows inserted by other plugins — and derives its connection state from the loader fiber, the mcp__<server>__* tools still registered, a TCP probe of HTTP endpoints and the last connection test; it shows the row's configuration, enables or disables it by editing only that row of the patch file, reconnects once after a failed attempt, and reports unavailable servers to the agent through a system-prompt note plus a call gate that refuses their tools instead of letting each call fail at the transport.

A collapsible column beside the conversation that organises conversations into a workspace/topic tree, opens the real sessions in place, and exposes the tree to the assistant through 9 model tools.

A tiled sticky-notes board for the DSH sidebar (a notes plugin): per-row density, colours, pins, search and colour filters, a trash with restore, Markdown export, and note_* tools that read and write the same notes.

Counts the assistant rounds that call tools without writing anything to the user, then inserts a short progress reminder as a visible user message at the next model-request boundary, so a long silent tool loop reports what it has done before continuing. A Settings page adjusts the silence threshold (default 10), the reminder wording, the language (en / zh-CN / zh-TW), whether the reminder repeats every further threshold of silent rounds, whether subagent sessions are counted, and whether Agent Teams nudges the lead only or every member.

Unofficial DeepSeek Harness port of the Academic Research Skills plugin (CC-BY-NC-4.0, non-commercial): 5 skills, 16 /ars-* commands, 4 agent roles, write-scope guard, and deterministic Python gates.

Tool-execution efficiency suite for DeepSeek Harness: read-only result cache, speculative prefetch, and concurrent readonly shell commands. Honest scope: helps when tools are slow and calls repeat; model latency dominates otherwise.

Loopback-only ACP door for DeepSeek Harness: connect VS Code and other local clients to a running kernel over the local loopback address, sharing its models, tools, memory and sessions. Browse history, change permission modes and call capabilities registered by DSH plugins.

Feishu/Lark integration for DeepSeek Harness through the official lark-cli: a sidebar panel for app setup and QR sign-in, a command console, and agent tools that run any lark-cli command across 18 business domains, 200+ high-level commands and the full OpenAPI; the official CLI is downloaded on first use on Windows, macOS or Linux.

Two small macOS features in one plugin. keepAwake stops the display and system from sleeping while dsh runs (caffeinate tied to the host process). taskNotify posts a system notification when a top-level conversation finishes its turn, with the outcome (completed, error, blocked, output cap) and the duration; clicking the notification brings DeepSeek Harness forward. Click-to-focus needs Xcode Command Line Tools to build the notifier; without the toolchain the notification still appears but clicking it opens Script Editor. Subagents and Agent Teams members never notify, and a stop you pressed is silent by default. Both features can be switched off separately.

Makes identifiers inside inline code in chat clickable; resolves a definition, then a wrapper, then the next occurrence, and opens the file at that line in the sidebar preview.

BreezeBlue text-to-speech for DSH: three agent tools, a header toggle that reads assistant replies aloud (markdown and code blocks stripped), and local HTTP endpoints for audio playback, synthesis and long-poll delivery. Requires a BreezeBlue API key (BREEZE_API_KEY); synthesis is billed per character.

Bundles the PrismSearch MCP server and its agent skill. Web search over Bing and Baidu with no account or API key, plus Google and Brave when API keys are set and DuckDuckGo, Sogou, 360 and Yandex when enabled in config; automatic engine fallback and an aggregate mode. Also image search, WeChat Official Account article search, and fetch_page, which returns web pages and PDFs as Markdown in segments.

Registers the hosted SpecStream MCP server with the harness MCP manager and keeps the API key in the credential store. The server returns live web data as structured rows, each value with its source URL, and a run starts only after the quote's maximum is approved.

Connects DeepSeek Harness to AIyting's image generation MCP endpoint and registers four tools: aiyting_image_catalog (models, routes and specs), aiyting_image_settings (read, quote and save parameters), aiyting_image_generate (return a quote first, and submit only with an explicit credit ceiling) and aiyting_image_task (task lookup, waiting, and a local per-account ledger for unfinished jobs). A sidebar page signs in with an AIyting access key, shows points, today's usage and daily quota, logs out, and keeps per-conversation defaults for model, route, aspect ratio, resolution and count.

LibTV canvas and media tools for DeepSeek Harness, with three director skills bundled and one-time WeChat QR authorization.