Plugins

Self-hosted SearXNG search provider: the bundled installer sets up and supervises a local instance on macOS/Linux/WSL (needs git and Python 3.11+), key-less and tracking-free; it probes the engines your network can reach and applies the recommended set in one click.

Mirrors an Android phone screen to a Windows PC over USB or Wi-Fi with scrcpy, and exposes start, stop, status, connect (reconnect after a phone reboot) and screenshot as an agent tool and a /mirror command. Requires scrcpy and adb installed on the host (winget install Genymobile.scrcpy); the plugin does not bundle them.

Per-session fast-delivery mode from the composer. New conversations start enabled; switching is refused while that conversation is running, and a read-only session-header badge shows on/off during a run. One switch drives three subsystems: a circuit breaker that short-circuits test and build commands instead of running them, an apply_patch tool that writes SEARCH/REPLACE hunks atomically (all anchors must match or nothing is written), and a dehydrator that trims terminal output to a pass line or the last 15 error lines.

Connects dsh to the BulkPublish MCP server (32 tools) to draft, schedule, publish and analyse social media posts, manage media, and handle inbox conversations and comments across 15 platforms, authenticated with a BulkPublish API key sent as a bearer token.

Runs a local command, an HTTP request or a log entry on DSH lifecycle events (startup, session start/idle/end, user messages, tool results) or on a daily or interval schedule; a left-rail panel and five agent tools manage the same rule set.

Cross-session memory for DeepSeek Harness: extracts durable facts from sessions in the background, recalls relevant memories on demand, and keeps a layered summary, a persona snapshot and a commitment ledger; data stays local unless you point it at your own private Git repository.

Caps how many DeepSeek Harness conversations run at once, so extra conversations wait in a FIFO queue instead of piling up model requests. On Windows a bottom status strip shows physical memory, commit memory and disk usage; on other platforms only the queue and physical memory are reported. A plugins-page card changes the limit.

Layered context management: at each turn end older tool output becomes a deterministic card, the model can fold older ranges into its own summaries in up to three tiers (compress), and every original is archived locally for decompress and search_context. Works alongside DSH-Mem0: superseded runtime-context snapshots (such as recalled memories) are never archived, carded or folded, and are replaced by a one-line placeholder at turn end when the prompt cache is already broken, when the saving outweighs the cache miss, or above 75% of the window; a strataBudget service (pressure, allowance, countTokens) and a strata/fold-landed event are provided for other context plugins; strata_status warns when DSH's automatic compaction is off or its official summary keeps failing. Its L1 layer, archive rotation, prune guard and preset takeover are forked from dsh-live-compact 1.0.6 (MIT); uninstall dsh-live-compact or billion-context first — they replace the same compaction rows and Strata will not take over while either is installed.

Compare two or three answers in one session and drop chosen turns from every later model request.

Rewrites the message you type into the DSH composer into a precise prompt before the model ever sees it, with one cheap side call on the session's own route. The rewritten text is what gets logged and sent, so the transcript always shows exactly what the model received; hover the whale to compare before and after. Slash commands, very short or very long messages and image-only messages are left alone, and any failure sends your text untouched. The composer whale is the switch: dark silhouette when off, gold when on.

Lists this session's runtime errors — turn errors, tool failures, command failures and subagent failures — as copyable cards in a conversation tab.

Multi-character companions with optional personas, editable per-character memories, persistent chat bindings, and QQ and WeChat bot connections with QR login and refresh. QQ requires a separately installed local NapCat instance; WeChat uses the official ClawBot/iLink channel.

Quota takeover for DeepSeek Harness on top of Our Free Model: compiles your platform order and pinned model tiers into one ordered fallback chain, skipping platforms that lack the model, sit in cooldown or are out of quota, writes the result back as Our Free Model combos, and after a quota or rate-limit failure re-plans and injects a follow-up continue message into the interrupted session so the turn resumes on the next platform; the chain ends with your configured aggregate fallback model or the official DeepSeek quota.

Gives hand-declared models on custom or relay routes a vendor-matched reasoning-effort picker: detects Claude, GPT, DeepSeek, GLM, Kimi, Qwen, Gemini, Grok, Doubao or MiMo from the model id, display name or endpoint host, fills in only the levels that vendor accepts plus the pi-ai compat fields its request format needs, and writes them into the profile config so the Models page reasoning switch turns on. Models you edit or switch off are left alone, and a Models page card hands them back on request.

Writes one model and reasoning effort into every session at once from a control beside the composer model picker, since the shipped picker only changes the session you are in. Sessions that already match are skipped, subagent sessions follow their parent instead of being written, and the same selection can be pinned as the default for new sessions.

Dark CRT pixel skin for the conversation pane: hard borders, block shadows and bitmap headings, scoped to chat and composer.

One click beside the composer turns a half-formed draft into a structured prompt the AI can act on: goal, constraints, output format and acceptance criteria filled in, placeholders only where a real decision is missing. Rewritten in place and never sent — undo with one click or Ctrl+Z. Four editable presets (general / code / writing / translation), optional conversation context to resolve references, and a model that either follows the session or is pinned to a chosen provider and reasoning effort. Requests survive session switches and typing while a rewrite is in flight; a result that no longer matches the draft is kept for retry instead of overwriting it. Pure JS, no build, no bundled dependencies.

One collapsible sidebar widget stacking OpenCode GO, Command Code and GLM Code Plan quota windows, with reset countdowns, top-up balances, a settings page and a /provider-usage command.

Shows OpenCode Go usage (5-hour, weekly, monthly) in the DSH composer dock and a Settings page.

Intercepts DSH tool results before the model reads them: dedupe cache for repeated calls, a declarative decision graph that replaces large outputs with structured digests, an injection gate, and an honest token ledger that includes a negative-return account for over-compression. Measured 1400-1600 tokens saved per hit; the cumulative ledger is currently negative and the README says why, including that it cannot skip model turns.

Sets token, cost and wall-clock caps on a DSH goal and blocks that goal when a cap is reached, instead of only reporting the spend. The figures come from the usage events DSH records for the session, priced per model, with a pill beside the composer that opens a per-model breakdown. The official DeepSeek tariff is built in, with peak/off-peak pricing toggleable because it depends on the route; other models are priced from configured rates, and a model with no rate has its tokens counted and its name listed rather than being guessed at.

A handwritten-journal salary timer on the DSH composer dock: set your monthly salary and work hours, then it shows how much you have earned today and this month in real time, plus daily, hourly and per-second rates, progress toward quitting time, hours worked past quitting time, weekday attendance dots and a status badge (working, lunch, off work, unpaid overtime, day off). Settings are kept in localStorage only; no network requests.

Replaces the sidebar workspace list with a Codex-style browser: sticky Pinned / Projects / Recent sections, status marks for working, awaiting approval, interrupted, and completed sessions, right-click sorting plus workspace rename and delete, and per-session pin and archive menus.

Adds a reasoning-effort rail above the DSH composer: drag or use the keyboard to preview and submit the levels the current model exposes (Off through Max), while a procedurally rendered micro-universe contracts and collapses into a black hole as effort rises. Levels go through the DSH model-selection interface, so the rail shows the level DSH confirms, and the plugin writes only to $DSH_HOME/stellar-effort/.