381 results
Durable layered memory (global / user / project / branch / daily), confirmation-gated writes, todos and skills. Preserves ~/.dsh/memories files in place with in-place adoption, SHA-256 verified backup and rollback.
DSH 自定义模型思考等级管理、渠道重试策略与偏好记忆插件：原生设计语言、全档位思考配置、渠道级重试控制与无感隔离式跨会话偏好记忆。
DeepSeek Harness dual-ledger cross-session memory: auto-extracted long-term facts (MEMORY.md) plus a living project progress ledger (PROGRESS.md), recalled into every new session.
DeepSeek Harness native immersive roleplay studio & companion system. Unifies decoupled character cards with Hindsight graph memory.
订阅 turn/end 对本轮完整对话做 LLM 蒸馏（被否决方案/踩坑记录/工程约束），打 type:rejected_solution 标签写入 MemOS；编码任务时对 rejected_solution 记忆做检索权重提升。复用 MemOS 向量检索、归档淘汰、生命周期能力。
DSH 本地向量记忆插件:本地 embedding 向量化 + SQLite 存储;四信号混合检索(向量+BM25+时间新鲜度+标签命中)自动召回;云端 deepseek-v4-pro 自动提取;支持取代链、置顶、软删回收站、memory_merge 合并与 memory_health 健康报告、定时备份。
DeepSeek Harness plugin: multi-tier memory management, semantic retrieval, structured memory, and model-context awareness for infinite context.
Mnemosyne 永久记忆插件 - 为 DSH 提供长期记忆、向量搜索和 LLM 反思功能
Hybrid memory plugin for DeepSeek Harness: L1 snapshot memory (MEMORY.md/USER.md, read on demand, zero context cost) + L2 searchable knowledge base (one-fact-per-file, SQLite FTS5) + L3 import from Hermes/Claude Code/Codex/WorkBuddy and approved Agent Hub documents. No automatic injection. Data lives on D drive, never C.
边做边学知识库：CRAG 式纠错检索（L1 Markdown wiki + L2 Hindsight）→ 未命中后台经 L3 限流联网补料 → 蒸馏落 staged → 两段式 commit 升入 L1。
Memory plugin with built-in governance for DeepSeek Harness
Git-native, auditable long-term memory for AI agents
dsh的跨会话记忆管理插件，让agent记住每一个任务的内容和进度。包含命题图、三层内存漏斗、混合向量 + 词法检索（RRF）以及浏览器端审查面板。 ｜ Cross-session memory management for DSH — lets the agent remember the content and progress of every task while executing. Includes a proposition graph, three-layer memory funnel, hybrid vector + lexical retrieval (RRF), and a browser-side review panel.
Cross-session long-term memory for the DeepSeek Harness: a two-phase extraction/consolidation pipeline over a file-based memory workspace, recall injection, a citation feedback loop, lease-based job semantics, plus a settings page, a sidebar status panel and a memory viewer.
DSH cross-session self-improvement: memory, error/session retrospectives, SOP extraction and improvement proposals
Per-project memory for DeepSeek Harness: auto-creates memory/PROJECT.md, DECISIONS.md and SESSIONS.md per project, loads them into every session, and records durable outcomes by classification.
Translation toolkit for DeepSeek Harness agents: segmentation, term extraction, durable glossary and tone memory, cross-segment consistency checks, source-target QA, heuristic quality scoring, tone guides, and a durable translation memory
DeepBrain (深脑) plugin for DeepSeek Harness: give your agent an organization's second brain — judgments with evidence chains, verbatim-verified quotes, people's historical positions, and 200+ analysis methods it can borrow
Yogacara eight-consciousness agent society for DeepSeek Harness: auditable double-loop runtime bridge, mneme memory consolidation tuning, MCP society tools, and six seed skills
Recover deleted/corrupted dsh sessions (session.jsonl.zstd) and memory (memory.db) straight from the raw disk. Battle-tested recovery manual + scripts + a /session-repair command plugin for the dsh web UI.
DSH web plugin: event-driven skill self-evolution. Watches agent execution traces, crystallizes reusable skills from successful turns via LLM review, progressively improves them, and manages everything in a dedicated Settings section.
Import chat history and memory from other AI agents (Claude Code, Codex CLI, Gemini CLI, Aider, Cline, OpenCode, Hermes Agent, OpenClaw) into DeepSeek Harness
Cross-session memory plugin for DSH — auto-extraction, semantic recall, scheduled maintenance, LLM-powered consolidation, context explosion prevention, global Soul identity
A persistent memory plugin for DeepSeek Harness that enables agents to store and recall information across sessions — DSH-native tools with atomic storage, validation, and concurrency-safe reads