Plugins
Browse, filter, and install DeepSeek-Harness plugins.
78 plugins found
dsh-context-steward
whatsmore-nf/dsh-context-steward
DSH 智能上下文压缩插件 —— 在有限窗口内管理认知资源,让 Agent 记住真正重要的信息。 Smart context compression for DSH — managing cognitive resources within limited windows, so your Agent remembers what truly matters.
bites-the-dsh
ch4acko3/bites-the-dsh
Adds read-only, scriptable playback to native DSH conversations, with simulated user typing, forward and reverse playback, event stepping, speed control, idle-gap compression, and direct seeking by event, turn, or recorded time.
dsh-arc-context
plxloyzb/dsh-arc-context
Adaptive Reversible Context (ARC) for DeepSeek Harness — provider-aware, cache-conscious context governance with reversible recovery.
dsh-compressor
lifeodyssey/dsh-compressor
A slim port of Headroom: compresses tool output, cuts up to 20% of context, without affecting the model's context cache or agent performance.
dsh-plugin-context-compressor
yytbit/dsh-plugin-context-compressor
Context compression skill for DeepSeek Harness -- intelligent conversation summarization
dsh-session-slim
turingcorp-net/dsh-session-slim
On open, rewrites a session stored log down to the visible conversation and archives the original, so a 68.6 MB session resumes from 90 KB instead of loading about 1.2 GB into memory (one migration of roughly 10 s, then instant). The last permission preset and model choice of the session are carried over, the original stays under archive/ for a one-command rollback, and a session another process owns is left untouched.
dsh-tokeneconomizer (prune)
sonettogu14/dsh-tokeneconomizer
Hides the tools that stayed idle across previous sessions, decided once when a session starts from recorded evidence; it ships disabled, and the compression, skill and image tools are never hidden.
dsh-money-board
github798383392/dsh-money-board
Session cost board for DeepSeek Harness: reads save-token's token counters and prices them with the official DeepSeek table, showing session spend, compression savings and the peak/off-peak delta above the composer.
dsh-caveman
lornatang/dsh-caveman
Caveman skills and tools for DeepSeek Harness: response styles, recoverable tool-result compression, model routing, browser tools, and delegation.
dsh-compaction-vcc
tingfeng-droid/dsh-compaction-vcc
Replaces LLM summarization with deterministic text compilation, so compaction makes no model calls and keeps original tokens; elided content stays retrievable through seq pointers. Based on TsFreddie/dsh-compaction-instant.
billion-context-patched
no-ni/billion-context-patched
A patched build of ranxianglei/billion-context (MIT) with the author's model-request accelerator folded in: verified snapshot reuse, parent-session inheritance for forks, outbound request-body compression, and image folding after the first send.
dsh-compress-bench
dingchenhui0618-arch/dsh-compress-bench
A local mirrored A/B benchmark for context compression, not another compressor. It runs one fixed read-only scenario twice with the same model and temperature — compression off, then on — and reports input tokens, turns, tool-call success, fact coverage, answer similarity and a per-line diff, with JSON, a self-contained SVG and raw warnings. 18 node --test tests, zero dependencies. The first measured run: 63,029 → 6,927 locally estimated input tokens (−89.0%), 3 → 3 turns, facts 3/3 → 3/3, answer similarity 1.00 on one sample.
dsh-memory-router
dcd887/dsh-memory-router
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.
dsh-plugins (dsh-notes-context)
sqzw-x/dsh-plugins
Notes-backed context compression for DeepSeek Harness: replaces LLM-summarized compaction with a model-written persistent notebook plus recoverable raw history, so the rollover boundary itself costs zero model calls.
dsh-websift
knlcxy/dsh-websift
Token-efficient web reading for DeepSeek Harness: one call fetches several pages through a real Chrome/Edge over CDP, gates them by relevance and returns a single digest, cutting context tokens by 80-98%. Real search URLs, login flow, screenshots, three proxy modes.
dsh-notes-context
sqzw-x/dsh-notes-context
Notes-backed context compression for DeepSeek Harness: replaces LLM-summarized compaction with a model-written persistent notebook plus recoverable raw history, so the rollover boundary itself costs zero model calls.
DSH-Headroom-Plugin (plugin)
kipozannaki/dsh-headroom-plugin
Runs the upstream Headroom compression toolkit (headroom-ai, Apache-2.0) inside DeepSeek Harness over MCP: headroom_compress, headroom_retrieve and headroom_stats are exposed as mcp__headroom__* tools backed by the upstream server, installed on demand by uvx. Compression is lossy but reversible — originals are fetched back by hash from a local CCR store. Also ships a registrar that adds DeepSeek Harness to Headroom's own MCP registry, and a model-header sanitizer for the upstream proxy.
dsh-curate
111222cjyq/dsh-curate
A human-in-the-loop curation workbench inside a DSH session: mark whole turns or single messages to keep verbatim or to summarize, rewrite user, assistant, tool-result and injected-context messages in place without a model call, then compress the marked ranges with model-written summaries or the official /compact. A local JSON backup is written before every write to the session.
dsh-memory-vault
xs1023/dsh-memory-vault
SQLite-backed long-term memory for DeepSeek Harness: add, search, update and archive entries with categories and tags, automatic conversation logging, tiered compression, and a project dimension that scopes retrieval to the current workspace plus global facts.
dsh-context-zip
brunhildzhou/dsh-context-zip
Context compaction that keeps its receipts: a five-section handoff summary, a durable segment index, review tools that read compacted text back, optional working notes, and a read-only extraction exit. Mounts as the compaction-basic row's replacement; cha
dsh-asc
janeickholt/dsh-asc
Model-driven context compaction for DeepSeek Harness. The agent decides when and what to compress, commits durable session-log replacements, and ships reversible tool-result compression with byte-exact hash retrieval.
dsh-context-compressor
rootkiller6788/dsh-context-compressor
An Agent-safe context compressor for DeepSeek Harness. It semantically preserves critical tool outputs such as errors, file paths, JSON payloads and command results, instead of mechanically truncating the context.
dsh-xingtu-skills
xingtu1996/dsh-xingtu-skills
XingTu 26 production-grade AI agent skills, packaged as a DeepSeek Harness (DSH) skills plugin — token compression, code review, safe refactor, migration, evidence review & more. 26 个生产级 SKILL.md 技能,DSH 一键安装即用。
dsh-memory-nexus
frank-nf/dsh-memory-nexus
Integrated memory and context management plugin: four-layer memory system (L2-L4), context compression/trimming/freezing, prompt orchestration, input box UI buttons, and enterprise security with role-based access control.