CATEGORY
Models & Usage DSH plugins
Verified manifests and exact versions in this category.
All plugins
874 plugins
dsh-model-tierModel Tier
Tiered model router for DeepSeek Harness: routes auxiliary calls (session title, compaction) and subtasks to light models, escalates hard tasks to strong ones — automatically, per request, across providers.
@rayadesu/dsh-billingBilling
DeepSeek Harness billing plugin: account balance and this session's billed spend with a session-header badge.
triss-dsh-provider-bundleTriss Dsh Provider Bundle
Configuration-only DeepSeek Harness (dsh) provider bundle activating the pi-ai opencode, opencode-go, and zai catalogue routes.
dsh-peak-indicatorPeak Indicator
DeepSeek API peak/off-peak (peak-valley) pricing indicator for DSH Web: Displays in the session header whether the current period is peak or off-peak (half-price).
dsh-all-usageAll Usage
DeepSeek Harness usage dashboard with model, provider, workspace, cache, balance, and CSV insights
dsh-plugin-balancePlugin Balance
DeepSeek / OpenCode Go / OpenAI quota overlay: displayed above the input box, with DSH model list synchronization, custom quota API, drag support, and theme adaptation; includes DSH session token usage statistics (by day/month/model) and cost estimates based on official peak and off-peak rates.
dsh-acp-enhancedAcp Enhanced
Enhanced ACP server for DeepSeek Harness: block-level streaming, usage/stat telemetry (cache hit rate, token speed, input/output tokens, context length, turns, tool timing), model & reasoning-effort switching, and permission-preset control over the ACP wi
dsh-usage-statistics-panelUsage Statistics Panel
DSH web plugin: a usage statistics panel with per-day token trend, GitHub-style activity heatmap, cache hit-rate curve and per-model breakdown, replicating the reasonix usage stats feature.
dsh-clawrouterClawrouter
A second brain for your DeepSeek Harness agent — strong-model review before risky tool calls, plus 73 models from one wallet. No accounts, no API keys.
dsh-local-aiLocal Ai
Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.
@wingsky-1/dsh-provider-usageProvider Usage
Usage statistics floating widget (v2 contract): capsule + detail panel, with HTML rendered and injected by the host; user mjs adapters connect to any data source through three functions (fetchData/formatCapsule/formatPanel); host-injected shared chart utilities (utils); API key configuration chain i
dsh-model-proModel Pro
Model Pro — DSH plugin for llm-pi-ai provider lifecycle: create/edit, custom headers, enable/disable with uninstall-restore safety, model discovery, and per-model connectivity tests
dsh-plugin-langfusePlugin Langfuse
Langfuse observability for DeepSeek Harness: OpenTelemetry traces, compaction, feedback Scores, and fork lineage
dsh-llm-workbuddyLlm Workbuddy
WorkBuddy (via the local workbuddy2api proxy) LLM provider adapter for DeepSeek Harness, with a Web login-status widget
dsh-miopiik-run-statsMiopiik Run Stats
Programmatic token usage egress reading session cumulative usage buckets (uncached/cacheRead/cacheWrite/output). 会话累计 token 四桶可编程出口
dsh-miopiik-model-authMiopiik Model Auth
Model authorization gate: subagent model/provider pulls must be in the user-controlled allowlist. 模型授权闸：子代理拉模型必须 ∈ 用户 allowlist
aqua-deepseekAqua Deepseek
DeepSeek API real-time pricing fish tank floating window — one-click installation into DeepSeek Harness, pixel-art companion animation, automatically follows peak and off-peak periods
dsh-budgetBudget
Cost governance for DeepSeek Harness: aggregated token/cost metering per model, session and day, session/daily/monthly budget caps with threshold alerts (desktop notification + webhook) and alert/block/degrade over-limit policies, built-in carbon footprin
dsh-engramEngram
Minimalist long-term memory for DeepSeek Harness, distilling symbolic-index + pi-esr ideas: zero-LLM auto-capture, a symbolic [ENGRAM] index with progressive disclosure, and an ESR-lite evidence-closure protocol (esr_task / esr_node / esr_close / esr_link). Real agent-behaviour telemetry (usage roll
dsh-deepseek-usageDeepseek Usage
DeepSeek API usage monitoring: a sidebar floating button and expandable panel showing the actual balance, today’s Tokens, usage by model, and estimated spending.
dsh-multi-model-providerMulti Model Provider
Register models, assist with portraits, and select the Agent model from a secret-free catalog for DeepSeek Harness.
dsh-freerouteFreeroute
Free-tier model aggregation for the DeepSeek Harness (dsh): registers the freeroute provider over a pool of free-quota upstreams (OpenCode Zen / B.AI / OpenRouter / SenseNova built in, plus remote catalogs and custom gateways), transparent failover before
dsh-observeObserve
OpenTelemetry and Langfuse observability exporter for DeepSeek Harness: turn/step/tool/LLM spans, token and cost metrics, and sanitized LLM prompt/completion capture from the session/event stream, with async batching, bounded offline buffering, and retry with backoff.
@mofeng2223/dsh-claude-providerClaude Provider
Custom Claude provider support for DeepSeek Harness
@goodandready/dsh-model-syncModel Sync
Automatic model catalog synchronization for API-key DeepSeek Harness providers.
@feiyang666/deepseekharnessdesktopDeepseekharnessdesktop
DeepSeek Harness usage & cost tracker plugin: per-call token/cache-hit stats, peak/off-peak billing, DeepSeek balance query, CSV/JSON/PNG export with custom destination, and persistent local storage. Ships a host half plus a web client half in one npm pac
dsh-subagent-default-modelSubagent Default Model
Configure default model routes for DeepSeek Harness subagents, with single-model, round-robin, random, and per-route reasoning-effort options.
dsh-usageUsage
Token usage, estimated cost, and a 52-week activity dashboard for DeepSeek Harness Web
@welsione/dsh-model-routerModel Router
Unified ModelID routing for DeepSeek Harness: one logical model id over multiple providers, first-token failover with cooldown, health-aware ranking, fallback reasoning efforts, purpose-based simple/complex task split, per-tier reasoning effort, and a set
dsh-experience-pluginExperience Plugin
DSH plugin: model reasoning levels plus CLI request mimic, with a unified Daily Optimization settings section.