Plugins
Durchsuche, filtere und installiere DeepSeek-Harness-Plugins.
228 Plugins gefunden
dsh-native-memory
highland0971/dsh-native-memory
Native Workspace-pro-Workspace-Speicher auf den eigenen Nähten des Harness: Fakten und ein begrenztes, immer aktives Profil auf der JSON-Einheit der Storage-Domain, schreibgeschützte Freigaben mit `(sessionId, seq)`-Zitaten, deterministisches Abrufen plus session-query-FTS über frühere Sitzungen — ohne externen Server, ohne benutzerdefiniertes SQLite.
dsh-kb-sieve
omdsh-dev/dsh-kb-sieve
Erstellt prüfbare Wissensdatenbank-Pakete (SQLite FTS5) aus md/txt/docx/pdf mit deterministischem Retrieval und Lesen des Originaltexts.
dsh-memory-gate
git121995/dsh-memory-gate
Begrenztes lokales Gedächtnis mit CBDC-Autoritätskontrolle: SQLite + FTS5-Claims, bereichsbezogener Abruf mit erklärbaren Use/Verify/Ignore-Entscheidungen und vollständigem Audit-Trail, /memory-Befehle, ≤3 Claims/1200 Zeichen Injektion pro Aufruf, kein zusätzlicher Modellaufruf.
dsh-seed-of-memory
ruiyuanyisu/dsh-seed-of-memory
Local-first memory for DSH — identity root, layered memories, beliefs, an emotion kernel and QQ chat continuity, all in one SQLite file. The QQ chat bridge replies only to the QQ numbers and groups on its allow-list, which is empty by default, so it answers nobody until you fill it in.
meow-starmap
hirschno/meow-starmap
Star map of the meow-memory store: each memory a glowing star, project memories gathered around a galaxy core, edges from project membership and shared keywords, fading into galaxies when zoomed out. Read-only.
dsh-plugins (dsh-datasource)
skillpie/dsh-plugins
Connect SQLite, PostgreSQL, or MySQL databases in DeepSeek Harness: browse table structure and data, run SQL, and let the assistant query and edit data directly in the conversation.
dsh-workbench (storage)
ityyq777/dsh-workbench
Storage records for DSH: names, brands, locations, units, stock text and tags with local SQLite and optional metadata sync.
dsh-memory
rosesssss66/dsh-memory
Local long-term memory for DSH: extracts preferences and project facts from sessions, injects the most relevant ones before each turn using local SQLite FTS5 search, and supersedes outdated facts. Requires Node 24+; the offline self-evolution loop needs an OpenAI-compatible LLM endpoint and API key.
dsh-workbench (host)
ityyq777/dsh-workbench
Shared runtime for the Personal Workbench: local SQLite, domain registration, agent tool, HTTP/SSE and opt-in cloud sync for the Tasks, Tags, Sites and Storage plugins.
dsh-db-studio
etshaw-zh/dsh-db-studio
Connect to databases in DeepSeek Harness (DSH), then query and edit data right in the conversation.
mirror-dsh-adapter
gjhhjfgh/mirror-dsh-adapter
Local-first memory governance: distills conversations into categorized memories, surfaces conflicts for human arbitration, and previews what gets injected next turn.
dsh-plugin-context-mode
domush/dsh-plugin-context-mode
Native DSH support for context-mode (mksglu/context-mode), intercepting large tool outputs with SQLite FTS5 indexing, BM25+RRF search, and session continuity. On by default: tool outputs over 4 KB are replaced with a short preview while the full text is indexed into ~/.context-mode/context.db, and a section is added to the system prompt. Its ctx_execute and ctx_batch tools run shell, Node, Python, PowerShell or cmd commands with DSH's own permissions and environment (not sandboxed), and ctx_index reads any local file path or fetches any http(s) URL it is given.
alice-memory-llm
cycocyco/alice-memory-llm
Long-term memory for DSH where an LLM decides what to keep: turns pool while the session is idle, then the main chat model distills them into one-line entries in a single batched call; vector dedup runs before insert, so near-duplicates and saturated topics are dropped; recall uses hybrid vector plus FTS5 search over tiered hot, warm and cold storage; ships remember, recall, forget and prune tools. Zero dependencies, Node only.
alice-memory
cycocyco/alice-memory
Long-term memory for DSH: rule gates capture durable facts from conversation turns into a single SQLite database with tiered hot, warm and cold storage; recall injects hybrid vector plus FTS5 hits into the prompt each turn; ships remember, recall, forget and cold-memory prune tools. Zero dependencies, Node only.
dsh-session-hub (plugin)
zyf2492313716-cloud/dsh-session-hub
Cross-agent session browser for DeepSeek Harness: mounts /session-hub/api/* and a Settings > General status row to read and search OpenCode SQLite, Claude Code JSONL, Antigravity, Qoder CN and DSH zstd logs, plus explicit continue-in-DSH and export. Its /session-hub/api routes are mounted without DSH's access check, and on startup it registers the workspaces found in those other agents' histories into DSH.
dsh-spirit
drscrewdriver/dsh-spirit
DSH 第一人称体验与本体记忆插件:把流程事件编译成角色的体验点滴,并从交付/实体/任务线维度建立可回查的工作记忆(SQLite),在模型步骤前注入「此刻状态 + 刚发生的 + 被勾起的回忆 + 正在推进的事」。
dlr
ljwzhaoxiaoniu/dlr
dsh bundle for TSM / DLR: MCP semantic gateway to tsm-core-dlr, the scenario-independent paradigm skill, the TSM status overlay, and the agent rules (AGENTS.md). Assembly face = preset-dlr.
campfire (dsh-campfire)
gxfc9867/campfire
Bridges campfire group chats into DeepSeek Harness, delivering messages addressed to your member into a DSH session and posting the reply back to the group. Needs a self-hosted campfire server plus a member handle and channel token; anyone who @-mentions that member in the configured chat can start a turn.
blue
fgcgdroid/blue
Blue-team defense mode for CTF and incident response: 37 defensive tools, MITRE ATT&CK coverage mapping, six worker roles, SQLite findings and tasks, an optional decoy server, deception/honeypot workflows, and a standalone console with full view.
dsh-any-preview
actcwlf/dsh-any-preview
Previews what DSH does not cover, including video and audio, 3D models, archives, SQLite and model weights, and searches large CSV, log and JSONL files.
dsh-db-mcp
halcyon6669/dsh-db-mcp
Database workbench inside DSH: import the connections DBeaver already stores (data-sources.json, decrypting saved passwords locally) or register SQLite, PostgreSQL, MySQL and Oracle sources by hand, then hand them to the agent through eight mcp__db__ tools — list_datasources, list_tables, describe_table, sample_rows, execute_sql, explain_query, get_ddl and test_connection. Sources start read-only; one global switch enables INSERT/UPDATE/DDL, every call is row-capped and appended to a JSONL audit log. Also covers groups, bulk actions, a read-only schema browser and a bundled Python MCP server whose dependencies install from the panel. No DSH files to edit.
dsh-rag (plugin)
fqh22/dsh-rag
Per-project long-term memory for DeepSeek Harness: a panel to browse, search and edit what each project knows, and a pointer injected after the first user message telling the agent to read the handoff pack. The memory store itself is a local MCP server (Python + SQLite) in the same repository; install the plugin from npm, then clone the repo, set up the MCP server per the README, and the plugin locates the checkout through DSH_RAG_ROOT or a common install path. Handoff packs are ordered for prompt-cache reuse: stable baseline first, facts appended at the end.
life-innovation
leon-dbh/life-innovation
Ein cybernetisches Lebewesen in DSH: Es erinnert sich an Menschen, Versprechen und gemeinsame Tage und kehrt in einen schreibgeschützten Raum mit vier Ansichten zurück: heute, Erinnerungen, Zimmer und Identität. Erinnerungen werden nur nach Bestätigung vergessen oder wiederhergestellt. Bei Müdigkeit kann es Aufgaben vertagen oder ablehnen. Benötigt Node 22+ und einen DeepSeek-API-Schlüssel; Installer und Desktop-Benachrichtigungen sind nur für Windows verfügbar.
ai-calendar-deepseek-harness
dengyinxi100-crypto/ai-calendar-deepseek-harness
Bettet eine Kalender-App als Seitenleisten-Panel ein und ergänzt auf der DSH-Seite ein verschieb- und skalierbares Widget für geplante Aufgaben. Sechs Agenten-Tools (Status, Liste, Erstellen, Aktualisieren, Löschen, Zusammenfassen) teilen eine SQLite-Datenbank. Die Kalender-KI nutzt die in DSH konfigurierte DeepSeek-Route und zeigt Tokenverbrauch sowie Tageskosten je Antwort.