Plugins

Local-first persistent memory infrastructure for DeepSeek Harness: bounded hot-memory bootstrap, explainable cold recall (exact + Chinese BM25), lease-lock transactional writes, read-only governance, and trajectory review. Pure Python + Markdown, zero ext

Persistent AI memory backed by a local Obsidian/Codex vault: five obsidian_memory_* read/write/search tools plus a sidebar vault browser.

Plugin DeepSeek Harness qui se connecte à un serveur PowerContext via HTTP pour le rappel, la mémoire, le transfert de contexte, l'expérience et les skills.

Vision for text-only DeepSeek via Doubao Web by default (zero-cost, no API key — drives your logged-in Chrome through a Windows CDP bridge), with Antigravity IDE quota (flash/pro) or Gemini fallback; auto detail escalation, vision evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

Semantic retrieval, resource management, auto-recall (user + agent dual spaces) and session memory for DeepSeek Harness: memsearch/memfind/memread/membrowse/memgrep/memglob over viking:// URIs, memadd/memremove resource management, memqueue observer status, memcommit session capture, and memlearn skill playbook minting.

Suite d'agents de recherche : contrôle d'objectifs à long horizon avec des chaînes de preuves auditables, planification cron, équipes d'experts multi-agents, mémoire de recherche auto-évolutive (rappel FTS5 + RRF), espaces de travail par projet, et une UI d'espace de travail personnalisée.

Execution-discipline suite for DSH with identical-retry interception, forced reflection, todo enforcement, memory deduplication, and experience-to-skill promotion (11 plugins + 6 skills).

Multi-character Galgame conversation view with separate character and reply-model selection, per-character affection, memory, dialogue history, and CG galleries, plus responses informed by task events across Harness sessions.

Technical-preview local graph memory for DSH and Codex: recalls owner-global and current-project evidence before each turn, writes USER and ASSISTANT records separately, and preserves project, session, actor, and source provenance for a visual atlas and cited knowledge pages.

Long-term memory & self-evolving plugin for DSH: L0 capture → L1 memory extraction → L2 scene grouping → L3 user persona, auto recall injection, skill synthesis, fully local (SQLite FTS5 + jieba, optional vector recall).

Relie la mémoire, les skills et la configuration de Claude Code à DeepSeek Harness — aucune migration, compatibilité totale

Une seule couche de mémoire pour tous les outils et agents IA : injection de Context Bundle, rappel au moment du prompt, outils MCP, et capture du fil DSH à la fin de chaque tour.

Continual self-refinement loop: persistent memory, periodic review-and-refine, cross-session shared knowledge, and automatic rollback through a model-callable harness_refine tool.

File-based cross-session memory: plain Markdown memory files with automatic retrieval injection, format-compatible with Claude Code's CLAUDE.md and memory files, so migrating is a manual file copy.

Knowledge-base-driven agent preset: wiki long-term memory, a web KB UI, a management page and optional UI polish.

Bundle sélectionné de serveurs MCP : une seule installation apporte des serveurs MCP de démonstration, mémoire, système de fichiers, GitHub, Playwright et HTTP distant, plus un outil de vérification de la connectivité et des contrôles CI.

Planification de tâches avec une mémoire musculaire de l'expérience : rappel réflexe conditionné de solutions passées, mise en correspondance des capacités du LLM, et leçons persistées automatiquement.

Passerelle ShiGuang Memory Engine (SGME) : mémoire à long terme partagée multi-agents via HTTP — distillation L0/L1/L1.5/L2, injection par scénario, recherche unifiée et signaux d'attention proactifs (memory_search / wiki_search / signal_pull / signal_claim / signal_ack), installable comme `dsh-sgme`.

agentmemory for DeepSeek Harness (dsh): full memory_* tools, capture hooks, and context injection over the local REST server

Popup guardian for session logs: opens with the Web UI on a configurable reminder interval (10 min-3 h), with one-click incremental backup of every session.jsonl(.zstd) under ~/.dsh/sessions in raw or readable chat-log format.

Load Claude Code assets into DSH at runtime — skills, slash commands, rules, permission rules (deny/ask/allow), subagents and hooks from .claude/ plus Claude Code plugins (plugin.json / marketplace / skills / agents / MCP), via a memory-IR parse layer that keeps .claude as the source of truth with no writes back. Six installable packages: loader, skills, permissions, agents, hooks, mcp.

Folio (兰亭) @nyantused/folio-dsh-tools: 15 schema-validated tools (memory + quality gates) plus an L0 guard of the consulting document-generation engine; pair with @nyantused/folio-dsh-events for the full session protocol.

Honcho memory bridge: auto-syncs every conversation turn to a self-hosted Honcho service, with recall/search/remember/context/status tools, context injection on session start, and a visual settings panel.

System status floating widget: live CPU/memory/disk usage in the bottom-right corner of the DSH Web UI with threshold colour warnings.