Plugins
Browse, filter, and install DeepSeek-Harness plugins.
18 plugins found
dsh-model-context-catalog
howillmakeit/dsh-model-context-catalog
Match context windows for configured DSH models in one click, show capacity sources, and support selective bulk configuration, manual editing, and continuous synchronization.
dsh-plugin (dsh-auto-trust-all)
mzzsfy/dsh-plugin
Makes every Host header that actually reaches the server a trusted entry: all webServer routes are wrapped and the parsed host is registered in connection.trustedHosts (mirrored into webRuntime.trustedHosts on host generations that still have that service), so wildcard or otherwise unenumerable entry domains work without editing the start command; entries beyond a configurable capacity are evicted LRU-first. It does not change the listen binding — that stays with the deployment layer — and the authentication layer is untouched. Because any Host header is accepted, the host allowlist no longer protects against DNS rebinding; use it only on a network you trust.
dsh-session-pruner
mrzhangkris/dsh-session-pruner
Full-type session lifecycle management: one-shot subagents archived on completion, idle continuable subagents / main sessions archived (recoverable), a capacity cap, projection-cache cleanup, and a hot-reload settings panel.
dsh-ark-coding-provider
akiyuki1130/dsh-ark-coding-provider
Unofficial Volcengine Ark Coding Plan LLM provider: registers an `ark-coding` route with 12 models (capacity facts measured per model), multi-account with automatic rotation, a bundled pinned arkcli for the official model catalog and live plan quota, plus a settings wizard and a sidebar usage card.
dsh-tokenlens
senyingxidi/dsh-tokenlens
dsh-TokenLens (词元透镜) — provider-aware plan capacity plus local token statistics (today/7d/30d/all-time, by harness/provider/model/workspace) for DSH.
dsh-clinepass
hateyoulittle/dsh-clinepass
ClinePass provider for DeepSeek Harness: 15 bundled subscription and free models, a settings page with per-model capacity overrides, subscription usage for the 5-hour, weekly and monthly windows, and multi-account failover to a backup account.
dsh-aidrama
limomss-dunang/dsh-aidrama
Pre-production studio for AI short dramas: imports a TXT/Markdown/DOCX script or pasted text, splits it into episodes, structures the bible, characters, scenes, props, episodes, shots and prompts, compiles prompts for the selected video-model dialect (Seedance 2.0/2.5, MiniMax H3, Kling, Wan), and hard-validates IDs, beat durations, dialogue capacity and look/identity locks before generation, and warns when a shot looks like it has more than one action.
dsh-routing-forensics
bushizhanghan/dsh-routing-forensics
Forensic analysis of past model-routing decisions. Replays each session, classifies every turn's task complexity from its request shape (deterministic, no LLM), and reports two kinds of waste: an expensive model on cheap work (the difference is measurable), and a cheap model on expensive work that failed on its own merits — where every retry re-sends the whole context, so the downgrade cost more than the upgrade. Distinguishes provider-capacity retries (RATE_LIMIT/TIMEOUT/TRANSPORT) from model failures so it does not cry wolf. Derives routing rules from the evidence, priced against a built-in per-million table.
dsh-memory-vault
xying-lm/dsh-memory-vault
Disk-backed long-term memory for DSH: a SQLite FTS5 vault that captures every conversation turn, injects relevant past turns into new sessions within a per-turn character budget, groups sessions into resumable conversation files, and ships a web panel for search, paging and capacity.
dsh-model-palette
jensen-yao/dsh-model-palette
Global Alt+M model command palette for DeepSeek Harness Web: fuzzy search over models and providers, favorites and recents, per-model reasoning effort, provider and model configuration, request retries, capacity presets, and optional OpenRouter image/video generation tools.
dsh-radeon-capacity
lcy362/dsh-radeon-capacity
Shows AMD Radeon Cloud AI Capacity for every Radeon model — a per-model badge in the model picker, and the selected model's capacity on the same row as its name. The badges register only once a Radeon provider is configured, so they never displace the host's own model annotations. Quota is display-only, since AMD is currently free and unmetered. Its settings page can also write the provider into the DSH user layer, so the provider keeps working after the plugin is uninstalled. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-ark-agent-plan
fushena/dsh-ark-agent-plan
Unofficial Volcengine Ark Agent Plan provider: registers an `ark-agent-plan` route with a model catalog fetched from the gateway, per-model thinking-effort control, server-side harness tools, and a quota badge with a panel showing remaining plan capacity.
dsh-session-trash
zhaoqianguo/dsh-session-trash
Adds a recoverable trash bin for DeepSeek Harness sessions: right-click delete, restore, permanent purge, configurable retention with automatic expiry, batch restore and purge, capacity stats for bin / archived / active sessions, archive takeover that can unarchive or move archived sessions into the bin, and 10 agent tools. Entries are deleted permanently after 30 days by default, and the agent tools can purge entries or empty the bin.
dsh-tokenlens
daigahou/dsh-tokenlens
dsh-TokenLens (词元透镜) — provider-aware plan capacity plus local token statistics (today/7d/30d/all-time, by harness/provider/model/workspace) for DSH.
dsh-windows-monitor
joyboy-yy/dsh-windows-monitor
System monitor overlay for DeepSeek Harness: a compact corner pill showing CPU and memory, expandable into a detail card with disk activity and throughput, per-volume capacity, network, uptime and battery. Windows only.
dsh-rf-toolkit
bestgi/dsh-rf-toolkit
Six RF calculators as agent tools: level conversion, link budget and maximum range, cascade noise figure, Shannon capacity, and impedance match.
dsh-morning-paper
damlys99/dsh-morning-paper
A newspaper-style front page for a session you left running, as a Conversation View tab beside Chat and Trajectory: a per-turn timeline (duration, steps, tools, tokens, outcome), file churn counted per file, where the wall clock went and how much of it was the model rather than tools, which single turn ate the spend, failures nobody retried quoted with their failing command, and a context-pressure gauge measured against the routed model's own declared capacity. The briefing is folded from the durable session log and never generated by a model, so it costs no tokens, cannot hallucinate, and is byte-identical for the same log and clock; it appends nothing to the session and reaches no model, and it reports a pending approval without ever answering it. Pages are offered only when they have content, and the tab refreshes itself on turn settle and on a two-speed poll backed by a metadata-only tail probe.
dsh-mirror
webkubor/dsh-mirror
Make the AI remember how you think, not what you said: actively captures your principles, redlines, and working habits across sessions — with memory capacity, graceful decay, and human-readable reasoning for every entry. 0.7.0 brings an intuitive persona portrait with evidence tracing.