Plugins
Browse, filter, and install DeepSeek-Harness plugins.
248 plugins found
dsh-cookie-sentinel
zhkkjf/dsh-cookie-sentinel
Raises the local Host's HTTP header budget to 128 KiB and prunes stale dsh-auth cookies only on the launch-token response that mints the replacement, so an already-locked-out desktop profile recovers and later random-port launches stay at one cookie.
dsh-recovery-memory
zilta-amaze/dsh-recovery-memory
Conversation memory behind a 20-letter recovery code: /recovery create packs the current conversation into one local record, and /recovery memory <code> injects it into a new conversation, where the model first summarises the recovered session and ends its reply with 记忆已恢复. Records are plain JSON under $DSH_HOME/recovery (mode 0600) with no network calls; the restored transcript is complete unless it exceeds the configured character budget, and /recovery where plus the dir option or DSH_RECOVERY_DIR move the directory to shared storage or a synced folder.
dsh-quota-meter-plus
lstalu/dsh-quota-meter-plus
Enhanced derivative of ai-shushu/dsh-quota-meter; cannot be installed alongside it (both serve /quota). Per-session spend and quota meter for DSH: bills real token usage against an editable model price table (including peak/off-peak pricing), shows a live progress bar and, in the session header, a balance capsule (the balance needs a DeepSeek API key), and blocks new model calls when a session budget runs out. Subagent and helper-call spending rolls up into the parent session ledger.
dsh-composer-assistant
mr-elk/dsh-composer-assistant
Adds next-message prediction, inline draft completion, and prompt optimization to the DSH composer, with a call budget, request stats, and glossary protection in Settings. A fork of Somnus678/dsh-input-assistant; both put their controls on the same composer, so do not install the two together.
dsh-proactive
mili1360/dsh-proactive
Wakes a session when a long background task finishes after the turn has ended, and lets the model schedule its own wake-ups (once, interval, or cron with jitter) under quiet hours and a daily budget.
dsh-budget-guard-plugin
existence001100/dsh-budget-guard-plugin
DSH plugin that enforces per-task budget caps by CNY amount or token count, with automatic interception to prevent runaway agent costs.
agentloom (dsh-plugin)
nowyousee1/agentloom
Bridges the shared ~/.agentloom store between DeepSeek Harness and Codex: injects the shared memories and the AGENTS.md entries the context budget truncates into the system prompt, and adds six loom_* tools for status, sync, memory search/list/add and skill listing. Requires the agentloom CLI installed and a one-time agentloom init; the seven-tool MCP bridge in the same repo is a separate package for MCP clients.
dsh-wb-memory
nero0427/dsh-wb-memory
Renders WorkBuddy SOUL, USER, MEMORY and topic Markdown files from an existing ~/.workbuddy/user-*-personal directory into the DeepSeek Harness system prompt, with a byte budget and a settings page; the profile's AGENTS.md loader must be disabled first.
dsh-mistral-spend
switcha57/dsh-mistral-spend
Shows real-time Mistral Vibe and API budget usage in the sidebar, with per-model token cost tracking, cached-token spend, and API-key management. Requires a Mistral API key (MISTRAL_API_KEY by default, or a custom apiKeyEnv).
DSH-Mem0
light-cheng/dsh-mem0
Mem0-backed long-term memory for DeepSeek Harness with managed Platform, self-hosted server and local OSS backends; visual settings, automatic recall (from the first turn) and capture, editable memory summary, token budgets and weekly memory hygiene that only deletes memories this plugin wrote. Captured text is redacted; the memory summary is a stable system-prompt section (plugin:dsh-mem0:profile) and recall a separate mem0:recall block appended last, so the cached prompt prefix stays stable; recall and capture have timeouts (recallTimeoutMs, addTimeoutMs). With dsh-strata installed, recall size follows its strataBudget allowance, and the optional captureStrataFolds setting (off by default) also saves its fold summaries as memories.
dsh-auto-compaction (dsh-auto-compaction)
1010231693/dsh-auto-compaction
A session auto-compaction plugin built for local models (compaction should also drop to seconds on cloud models): when idle it replaces the oldest history with a summary so the local engine never re-reads the whole history; the trigger point is adjustable, compaction can be rolled back at any time, and mid-task compaction can compress early when the remaining budget is low (off by default).
dsh-cookie-guard
mxw0808/dsh-cookie-guard
Windows-only guard against the desktop shell locking itself out: it counts the dsh-auth-* launch cookies the shell has accumulated, reports how much of the 16 KiB request-header budget they consume, and once the count passes 40 it backs up the whole Cookies database and lets DSH rebuild it, so every cookie in that profile is cleared. Install is one command: on load the plugin registers its own weekly scheduled task pointing at the scripts inside the package, and uninstalling it removes that task — nothing to copy into your home directory and no schtasks line to run by hand. The check itself runs while the app is closed (it waits up to 3 hours for the shell to exit). It does not raise the header budget or keep a floating panel; scripts/ can also be run standalone without the app installed.
dsh-selfnote
xyzovo/dsh-selfnote
Self-narrative memory in five budgeted segments (800 chars, not a full context): a first-person note the model writes to itself, a profile of you aggregated from approved facts, environment facts kept separate from who you are, heat-ranked conclusions, and habits. Every injected fact is traceable to a fact id and can be retired; the profile can be edited by hand, and self-notes stay plain lines you can clear. Facts fade by use and time without ever changing their credibility. Preference-like lines you say are auto-detected as candidates (never auto-approved), with conflicts kept side by side. Recall over past conversations with citations, an incremental index that only decodes newly appended frames, a pointer-required warm layer, a doctor that says which part is broken, a heartbeat proving injection is alive, and export/import so the whole thing moves to another machine.
tabellio-dsh
yffo/tabellio-dsh
DeepSeek Harness native adapter for tabellio: budgeted auto-recall, native memory tools, and explicit-clue candidates. The memory core stays in tabellio.
dsh-token-dash
spartawhy117/dsh-token-dash
Token and cost dashboard for DeepSeek Harness: 8 providers, with subscription quotas (GLM / Kimi / OpenCode Go / Command Code), balances and budgets; third-party-API-key endpoints (custom, relay, local OpenAI-compatible) are tracked too, and unpriced models never show as zero. Backs up to local JSON.
ai-context-doctor
wjddidi-1/ai-context-doctor
See what a conversation feeds the model, what your rules keep out, and what one click would change.
media-suite (media-runninghub)
do-nothing/media-suite
RunningHub cloud ComfyUI workflows as a background task pool: submit a batch, and a watcher dispatches it within a concurrency budget, polls each job, downloads every output to disk, and wakes the session when the pool drains. A shared ledger records batches, costs, instance tiers, submit and finish times, and per-file save paths, with a live board in the right sidebar.
dsh-whale-panel
bilihave/dsh-whale-panel
Bilibili curation floating panel for DSH: learns your interests on a probability schedule and decays them by half-life, picks videos inside a token budget derived from a daily money cap, and mentions you only when a fit score passes a threshold. Comments are off by default; once enabled they run in draft-and-confirm or self-checked auto mode under a daily quota, with a hard no-comment rule for political, government and frontier-science topics, and comment text is scrubbed for account identifiers before it can be posted. It signs in through your own Bilibili account cookies; a separate posting account is recommended.
dsh-long-memory
dogbotowo-oss/dsh-long-memory
Long-conversation memory for DeepSeek Harness (DSH): keeps settled decisions, user corrections and exact numbers, with their conditions and sources, available across compaction and restarts in 100-1000+ turn sessions; one small budgeted evidence block per model step, with enabled skill rules re-applied in the same block.
dsh-self-trigger
erty3244/dsh-self-trigger
Lets the agent inject one turn into a chosen session on its own when the host has been idle. Daily cap, active hours, weighted action lottery, per-activity budget, and a policy file re-read on every check. Disabled by default; sends no network requests.
dsh-ctx-budget
lugabeeee/dsh-ctx-budget
Static-context audit for a DSH home: a six-layer baseline (rules, memory, skills, tool surface, sessions, KB), broken-path checks for a markdown capability map, memory duplicate/stale/over-limit reports, SKILL.md description compression, and tool-surface plus cold-start static-context estimates recovered from session logs. Four read-only DSH tools; writes require --apply and are backed up first. Requires Python 3.10+ on the host (stdlib only; all four tools shell out to the bundled CLI).
dsh-token-cost
catgrandfa/dsh-token-cost
Token spend panel for DeepSeek Harness: today and 7/30-day totals, natural month/quarter/year sums, cost split by cache-hit input, cache-miss input and output, per-model and per-session detail, daily and monthly budgets with a projected day-end spend, peak/off-peak pricing, CSV and JSON export, and a zero-dependency CLI report. Also prices GLM (Zhipu) and Kimi models shipped through third-party routes. Maintained fork of olimc2016/dsh-token-meter-panel (MIT, 0.6.7) with a rewritten panel; it uses its own row, route and slot ids, so it installs alongside the upstream entry rather than replacing it.
dsh-qqbot-muu
wuwo1979/dsh-qqbot-muu
Standalone QQ-bot extension pack for DeepSeek Harness — fully independent, no other plugin required. Two-layer SQLite memory with hippocampal recall, a persona that keeps learning from daily chats, group tiers, local-model quick replies with a single-brain arbiter, TTS outbox, sticker library, an approval-gated video studio, and a four-form desktop pet (three custom characters plus the stock fish) playable over a public invite link with access-code login, single seat and brute-force protection. Chat bridging is deny-by-default: c2c/group access defaults to a care mode that only responds to the special-cared people and groups of the owner (shared with the persona system, zero extra config); allowlist, open and disabled modes remain available. First-run defaults (persistent inbound dedupe, configurable outbound-hook budget, optional default permission preset, extension seeding) are written only where nothing was configured and never overwrite user changes. Interview and quiz practice run inside chat with local scoring and configurable transcript retention. Requires QQBOT_APPID and QQBOT_SECRET, and Node.js 22.5 or newer.
ai-context-doctor (plugin)
wjddidi-1/ai-context-doctor
Adds an AIignore tab to the right sidebar: scores the open conversation and its folder across five dimensions, blocks reads of build output, lockfiles and logs before they reach the model, and writes the .aiignore rules for them one button at a time.