Plugins
Explora, filtra e instala plugins de DeepSeek-Harness.
297 plugins encontrados
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.
dsh-team-workbench
narkco-kang/dsh-team-workbench
A named-agent-team chat workbench for DSH: per-member model routes with fallback and 3D mascot avatars; private and group chats with mention relay and bounded parallel lanes; a whole department as one agent whose lead dispatches sub-agents that run in parallel on their own models before the lead synthesizes; record search with hit highlighting and today/yesterday/earlier buckets; a four-layer memory system (raw chats → atomic facts → scene summary → user persona) recalled by hybrid BM25 + embedding RRF; plus an avatar library and local/cloud speech input. Hybrid recall needs an embedding endpoint (default: local Ollama qwen3-embedding:0.6b; otherwise BM25 only); speech input needs a local jianchang512/stt service or a cloud ASR key, otherwise it falls back to the browser speech API.
dsh-plugin-playbook
yangyiqun747/dsh-plugin-playbook
Reusable experience for DeepSeek Harness: save a successful task as a structured playbook, recall it later as a native skill, and gate deliveries behind user-confirmed checks that require objective evidence before write actions are allowed.
javmem-dsh-plugin
xuxiaoxiang0721-tech/javmem-dsh-plugin
Per-Bot memory for Tobs Bots (requires DeepSeek Harness with @botharness/core; it ships off with no Bots listed, and after you list a Bot and set mode to on it works with no other service): a read-only local full-text index of that Bot's own past conversations (Chinese words found inside sentences), memory imported from other AI tools, a status tool, optional auto recall before a step in which a Human speaks, and a service for other plugins. Richer backends can be chosen at install, with a quote first and a daily token cap: a public fact store (memv2-lite), the official Graphiti graph, or both, fed from the Bot's own conversations.
dsh-neocortex
kelunisi/dsh-neocortex
Markdown-authoritative second brain: layered memory, local recall, and a daily Bilibili feed that writes source pages and recent notes back to Obsidian.
dsh-strata
light-cheng/dsh-strata
Layered context management: at each turn end older tool output becomes a deterministic card, the model can fold older ranges into its own summaries in up to three tiers (compress), and every original is archived locally for decompress and search_context. Works alongside DSH-Mem0: superseded runtime-context snapshots (such as recalled memories) are never archived, carded or folded, and are replaced by a one-line placeholder at turn end when the prompt cache is already broken, when the saving outweighs the cache miss, or above 75% of the window; a strataBudget service (pressure, allowance, countTokens) and a strata/fold-landed event are provided for other context plugins; strata_status warns when DSH's automatic compaction is off or its official summary keeps failing. Its L1 layer, archive rotation, prune guard and preset takeover are forked from dsh-live-compact 1.0.6 (MIT); uninstall dsh-live-compact or billion-context first — they replace the same compaction rows and Strata will not take over while either is installed.
hy-memory4dsh
echo-smith/hy-memory4dsh
Hy-Memory 2.0 as a native DeepSeek Harness memory component: three-tier memory (personal / project / session), three scenes (chat / working / coding), automatic recall and capture with tool traces, a Settings > Memory panel, and MemHub interoperability.
dsh-hindsight-local
dyrcjqlgcj/dsh-hindsight-local
Runs Hindsight long-term memory on your own machine: after a one-time uvx --from hindsight-embed@latest hindsight-embed profile create server setup (~450 MB of Python dependencies) and with your own LLM key, the plugin manages the local memory server itself (health probe, start, stop, logs), registers ten hindsight_local_* tools for status, page search, page read, recall, remember and reflect, injects a knowledge-page index once per session, writes each finished turn back into the bank, and extracts facts with your own LLM key. Do not enable it alongside the official @vectorize-io/hindsight-coding-agents plugin: both read the same bank and would inject duplicate context. At session end it writes a handoff snapshot that the next session injects as previous progress. The data directory is configurable (dataDir) and scripts/relocate.mjs moves an existing install to another drive, creating directory junctions where the server hard-codes its paths.
dsh-self-memory
lzk112233/dsh-self-memory
Four-layer memory for DeepSeek Harness, ported from the memory design of NoMindSama/qq-dsh-bridge (MIT) with the QQ channel removed: an append-only dialogue log, a weighted long-term fact store with decay and one-way archiving, self-notes the agent writes about itself, Chinese bigram recall over the raw log, and incremental AES-256-GCM sync to a private git repo where only ciphertext is stored. Archived sessions drop out of recall without losing their history.
dsh-memory
ascrm/dsh-memory
Local-first, file-backed memory plugin for DeepSeek Harness: Markdown memories, verified trust, per-turn recall, and optional SQLite FTS5.
dsh-agentic-pet
beyondgjc/dsh-agentic-pet
A model-driven desktop pet for dsh, derived from PC2005-cloud/dsh-pet (MIT): a transparent always-on-top companion that follows your agent sessions, races the Web UI to answer approvals and questions, and runs an autonomous inner voice — world-clock and self-scheduled wakes, dreams, and bond-anniversary milestones, speaking through pet_say/pet_do, with lines read aloud through BreezeBlue TTS using your own API key. Memory is a per-pet continuity journal — an append-only hash chain, rotation into an archive, self-written stage summaries, and keyword recall with tag clues — alongside letters, a shared living-room board, pet-to-pet messages, an affection ledger, and an interactions audit that records how every approval and question actually ended. Memory and ledgers live in ~/.dsh/whale598/<petId>/; the settings page adds per-pet switches and a tool-call audit dashboard (all-time / last 30 days). It uses its own /whale598 route and data directory, so it is a separate pet from dsh-pet rather than a replacement for it. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
lingshu-skill
q2667671398/lingshu-skill
Lingshu (灵枢) es un sistema de memoria persistente, persona y crecimiento inspirado en el cerebro para agentes de programación con IA. Solo usa la biblioteca estándar de Python, sin dependencias y con prioridad local; requiere Python 3.9+. Incluye memoria por capas hipocampo/corteza, curvas de olvido, consolidación de sueños, recuerdo asociativo difuso, sistema emocional, protección contra la deriva de persona, base de conocimiento, skills autoescritos y panel web local. Se distribuye como skill incluido en DSH. El plugin cordis instalable por separado inyecta sesiones automáticamente solo si (Lingshu está en ~/.dsh/skills/lingshu o se configura brainPy) y hay Python 3. La comprobación opcional de actualizaciones contacta con GitHub/Gitee.
dsh-obsidian-memory
aoyamabf-max/dsh-obsidian-memory
Stores the agent's long-term memory as plain Markdown in an Obsidian vault — every memory is a .md file with YAML frontmatter that Obsidian indexes natively, so you can read, edit, link and back up it with tools you already use. Nothing is locked in a database. Ships a sidebar panel (tag filter, sort by recency or importance, edit in place), 7 agent tools, three-tier token-budgeted recall, BM25 ranking (no embeddings, no API key, works offline, CJK bigram tokenization), importance decay with archiving (moved to .archive/, never deleted), and optional GitHub Contents API sync. A note containing a secret is refused rather than redacted, because a redacted memory reads as complete while the important part is gone. Zero runtime dependencies; everything comes from the DSH host.
dsh-memory-band
13576751971/dsh-memory-band
Local three-band memory for DeepSeek Harness: a 24h protection band, query recall and scene replay, injected into sessions without embedding or model calls.
dsh-recollect
kirkchinese/dsh-recollect
Memoria compatible con Claude Code para todos los modelos en DeepSeek Harness: instrucciones CLAUDE.md/AGENTS.md por capas con @import y reglas, memoria persistente MEMORY.md con guía completa de escritura, actualización al reanudar y compactar, y recuperación opcional.
dsh-shared-kb
kunjienie50-creator/dsh-shared-kb
Base de conocimiento compartida para equipos: un miembro ejecuta un Hub sin dependencias y los demás instalan el plugin y se unen con un código de invitación. Las cargas se clasifican en diez categorías con resumen, confianza y puntos; 15 herramientas de agente permiten subir, buscar, recordar, comentar y leer. Los elementos importantes se fijan con una recomendación escrita a mano hasta que el miembro los lee. Cada cuenta también tiene biblioteca local privada, colecciones, resumen semanal y diferencias entre versiones.