Plugins
Browse, filter, and install DeepSeek-Harness plugins.
288 plugins found
dsh-workspace-memory
lovenndme/dsh-workspace-memory
Workspace-scoped persistent memory for DSH, laid out like Claude Code's auto-memory: one English-slug Markdown file per memory beside a MEMORY.md index under ~/.dsh/projects/, with hybrid vector+keyword recall, three automatic triggers (index injected every turn, file-path hints appended to tool results, per-message prefetch), a review queue for low-confidence writes so nothing enters the library silently, and global preferences written as numbered chapters into ~/.dsh/AGENTS.md under a byte budget. Everything is read from and written to local files; the optional leanvec embedder (~85 MB, installed locally by the bundled script) powers semantic recall but runs in-process, so the plugin itself opens no network connections and uploads nothing. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-long-term-memory
wojiao42/dsh-long-term-memory
Long-term memory for DSH: injects your Markdown memory file at each session start, adds read/write/recall/undo tools with backup and audit, and lists your detailed profile files (interests / profile / project notes) with guidance on when to read them. Zero dependencies; never opens a network connection.
feiyu-memgate (dsh-feiyu-memgate)
n0rmal-114/feiyu-memgate
Long-term memory through the bundled feiyu-memgate gateway, which the plugin starts on 127.0.0.1 (needs Python 3.11 or newer, nothing to pip install): recalls related memories at the start of each user turn and appends them after the user message as a marked data block, gives the model memgate_remember and memgate_search tools, and adds a /memgate command and a settings page where each feature can be switched off. By default memories are written only when the model calls the remember tool. Keyword retrieval over SQLite by default, with no model and no download; an OpenAI-compatible embeddings endpoint or the optional dsh-feiyu-memgate-embed add-on (local CPU embedding models, downloaded on request) adds semantic retrieval. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
xuyi-memory-release (dsh-adapter)
joymitu/xuyi-memory-release
Xuyi (续忆), local long-term memory for QQ companion chats: archives QQ private and group messages to a local SQLite file, recalls earlier statements with their original wording through automatic recall and the `xuyi_recall` tool, writes a daily diary, supports backup export/restore, and ships 11 persona presets with a first-run setup guide.
dsh-copyback
redkiller79/dsh-copyback
DeepSeek Harness (DSH) plugin: keeps a recallable history of copied text on this machine. copyback_search finds entries by keyword or date and returns previews, copyback_copy writes a chosen entry back to the system clipboard, and copyback_manage pins, deletes, clears or pauses recording. The daemon listens on 127.0.0.1 only, skips secret clipboard markers from password managers, records only foreground copy actions on Windows by default, and stores data as local JSON. Requires Python 3. MIT licensed (Copyright (c) 2026 FeiGe).
dsh-memory-assistant
psychic-z/dsh-memory-assistant
Long-term memory for an agent. Conversations become memory cards; recall reads a few cards and answers in three explicit states (exact / related / none), so the token cost of remembering stays flat as the library grows, and it asks instead of guessing.
dsh-lcm
zy-xyz/dsh-lcm
Lossless context compaction: an LLM summarizes a leaf of compacted events and replaces it with one checkpoint node, nothing is deleted, so lcm_search still matches text a checkpoint summarized and lcm_expand restores any event by seq. Summaries condense at fanin 4, a threshold crossing sweeps several leaves under two clocks, and an idle pass resumes a sweep that ran out of budget. Optional semantic recall ranks events against any OpenAI-compatible embedding endpoint, with a /lcm-embed backfill command and status. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
-
a2092776074-collab/-
File-based memory for DSH agents: layers, FSRS-5 decay, cold archive, recall, zones, and optional auto-injection.
super-dsh (better-dsh)
pgmi-builds/super-dsh
Make your dsh ready for serious coding. (Tools x Schemas)^REPL. `skill://`, `ctx://`, `agent://`, `dvc://`, `dsh://`, IPython REPL, Context as Variables, cross compactions recallable, full context revive. `hash-edit`, `dvc://browser`, subagent as function, workflow as function.
dsh-benwo
cheeseratrat/dsh-benwo
Local-first persona & memory for DSH: layered persona, eight memory types with decay, keyword recall, and a rolling short-term window. Your data never leaves your disk.
dsh-conversation-log
imcaibaicai/dsh-conversation-log
Mirrors every session to a standalone readable Markdown file plus a JSONL twin whose name carries date, time and topic, keeps a searchable index beside them, and adds a settings-page search and a model recall tool.
dsh-foresight
overfloweee/dsh-foresight
Composer add-on for DSH: next-message prediction shown as ghost text, history prefix completion, a one-line recap after each turn, and ↑/↓ recall of earlier prompts.
dsh-prompt-history
xingxing2013/dsh-prompt-history
Prompt history in the composer: Up and Down recall prompts sent earlier in this browser (newest first), Down walks back and restores the draft you had before the first Up, and the badge in the composer corner opens a numbered list to pick one directly. Only prompts you actually send are recorded — never fragments left by deleting text or cancelling a composition — history is shared across sessions and deduplicated, its badge size is adjustable in Settings → General, and Ctrl/Cmd+Shift+Backspace clears it.
dsh-prompt-suggest
linsongrong/dsh-prompt-suggest
Inline next-message prediction in the DSH composer: a grey ghost line, Tab to accept, ArrowUp to recall sent prompts.
dsh-Engram
yhprime/dsh-engram
Experience and skill engine with a sidebar console and exp_record / exp_recall / exp_feedback / exp_consolidate / exp_type tools, stored in a local JSON file. Optional Git backup (off until you configure a remote) pushes the library to a remote you choose; GitHub sign-in uses a device code or a token kept in local settings.
dsh-session-fold
kennethfan/dsh-session-fold
Folds older oversized tool results into spill files and replaces them with short, deterministic stubs at step boundaries, with no LLM call: the stub keeps the first 200 and last 80 characters plus the sequence number, tool name, line/char/size counts and the original file path, and each fold is a real surface replacement accompanied by compaction/prune shadow pricing so token counts stay honest. Triggers on context pressure at 25% of the model window (falling back to 32768 tokens when the window cannot be resolved) or on five accumulated candidates; the last three turns, error results and rich content are never folded. The original is recovered from the session log rather than the spill file, so /folds, /unfold <seq> and /unfold all keep working after spill cleanup; session_fold_recall lets the model fetch a folded result by sequence number or by keyword, and session_fold_diagnose reports the effective settings. /spill-prune removes orphaned spill directories, preview only unless --apply. A Settings page exposes 12 of the 13 options as draft-then-save fields; they are volatile, so saved changes apply without restarting the plugin.
dsh-memlite
risense-ai/dsh-memlite
DSH plugin: persistent local memory powered by @rsrsai/memlite (respire-aligned prompt/recall/wrap-up logic; JSONL causal tree, git sync, data-compatible with Rust memlite; four-view memory browser with conditional writes, receipts and status).
dsh-cerebrum
liu-wen-wu/dsh-cerebrum
Brain-inspired cognitive architecture for DeepSeek Harness: hippocampal episodic memory, cortical semantic memory, spreading-activation recall, appraisal-based emotion, neuromodulator state, Big Five personality and dual-process judgment.
evolver-agent-plugin
evomap/evolver-agent-plugin
Evolver for DeepSeek Harness, by EvoMap: recalls a proven strategy behind each prompt, reports its reuse at turn end, and distills verified work outside the conversation.
dsh-foxy-memory
kun-fox/dsh-foxy-memory
Connects DSH Foxy to Foxy Memory for cross-platform recall, with local JSONL fallback, platform filters, and a memory browser. Requires dsh-foxy.
whale-mind
fogstop/whale-mind
Memory engine for a long-lived companion agent: a six-module loop (gate, solidify, store, retrieve, inject, decay) that decides what is worth keeping, distils raw turns into long-term entries, fuses short and long term at recall time, and fades entries that stop being used. Runs offline by default; if DEEPSEEK_API_KEY is set it also sends each message to the DeepSeek API to judge and distil it. Zero runtime dependencies and no build step; ships three switchable panels over the same store - neural brain, memory ring and memory galaxy - so you can watch what it remembers. Non-commercial license: commercial use needs the author's permission.
FastCompact (dsh-fast-compact)
victorwwchan/fastcompact
Deterministic, zero-LLM compaction engine for DeepSeek Harness: the checkpoint is compiled locally from the session log with no summarizing round-trip, and dropped tool traffic becomes seq reference lines the model can restore with recall, which helps on small context windows. Ships as two packages: install dsh-fast-compact and dsh-fast-compact-preset, add both to the profile's bundles, pick the Fast Compact (standard) preset and start a new session. Needs dsh >=0.1.5-rc.2 <0.3.0.
dsh-memory-v2
yanlrx/dsh-memory-v2
Rui Xi's Memory (dsh-memory-v2) — a local long-term memory plugin for DeepSeek Harness: four memory collections (semantic / conclusion / profile / temporary), per-day scene archives, two-phase consolidation and literal trace. When structured recall finds nothing, it falls back to searching the daily scene archive: time-window first (yesterday / last week / N days ago / dates), then a 2/7/30/180-day tiered sweep, with line-numbered citations. All data stays in the local DSH directory; semantic recall, diagnostic logs and the sensitive debug route are off by default.
dsh-renor
renorai/dsh-renor
Connects DeepSeek Harness to the hosted Renor memory MCP server over Streamable HTTP, using a Renor API key from RENOR_API_KEY, so the model can call Renor's recall and save tools. It is a configuration bundle with no code of its own.