memory 192

Knowledge-base and memory switch for dsh web: a three-position memory button in the composer tool row (left of the model selector) plus 「我的知识库」 and 「Cherry Studio 知识库」 settings pages. The host half orchestrates the local 我的知识库 toolchain (记忆开关 / idx / cher

即作记忆：创作记忆、设定与知识图谱查询

Native DeepSeek Harness (dsh) plugin: hybrid local and XMemo cloud memory for Cordis-based agents.

Native knowledge context for DeepSeek Harness

Focus board for DeepSeek Harness agents: durable, model-maintained notes in the session workspace that pin the objective, constraints, and decisions across compaction and sessions — with structured entry tags (kind/status), a grouped summary view, automat

Lightweight zero-dependency memory plugin for DeepSeek Harness: Markdown-file memory store, L0 catalog injection, and 5 model-facing tools.

Long-term cross-session memory plugin for DeepSeek Harness (L5 + L7 layers): SQLite-backed, FTS5 + optional embedding recall, append-only audit log, single-bundle dual-face packaging.

Intent fitting for DSH: the agent predicts several directions first, asks a batch of clarifying questions each round, narrows the distribution until one converges, then proposes it for your confirmation. Bottom-right floating panel, local JSONL archive, a

Reflect2Evolve memory plugin: layered L1/L2/L3 memory, reflection-weighted value backprop, cross-task policy induction, skill crystallization, and three-tier retrieval for OpenClaw, Hermes Agent, and DeepSeek Harness.

Canonical project memory for DeepSeek Harness: one governing article per asset, an append-only journal beneath it.

Structured long-term memory for DeepSeek Harness: CJK-aware tokenized search, hybrid rerank, dedupe, expiry review, and migration from dsh-memory — zero mandatory network

IwIw 记忆插件：跨会话记忆，模型自主调用记忆工具（桥接 memory_agent MCP 内核）

DSH 全局经验插件（骨架）：自动探测本地依赖/便捷路径/网络/磁盘并沉淀为跨会话环境档案，订阅 session/event 折叠每会话统计，把低开销摘要注入每轮系统提示，env_profile 工具按需查全量——减少重复探测、加快会话、降低 token 消耗。

Markdown folder long-term memory for DeepSeek Harness: one file per fact, an index line per memory, mounted into every request as a system prompt section

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

Automatic cross-session GoodMemory recall and writeback for DeepSeek Harness

Veyra — Engineering Intelligence for Coding Agents. Persistent, evidence-aware, project-isolated engineering memory and unified hybrid search (memory + RAG documentation) for DeepSeek Harness.

独立本地记忆插件：JSONL 记忆条目、每轮 runtime-context 注入、local_memory_search/local_memory_remember 工具、设置面板管理页。不依赖 Mnemon。

Memory plugin with built-in governance for DeepSeek Harness

Hierarchical Claude Code-style persistent memory for DeepSeek Harness: user + project (git-shared) scopes, session-start auto-injection, MEMORY.md index guards. Pure files, zero dependencies.

Self-evolving memory for DeepSeek Harness (DSH): earned experiences, diary/fact semantic memory, concern tracking, and an append-only audit ledger.

DeepSeek Harness plugin for bounded, provenance-linked context steady state with recoverable raw history

DSH memory plugin: global hot memory + on-demand experience library with FTS5 retrieval and WebUI cards

DSH 全局记忆插件：侧边栏「全局记忆」页，直接查看/编辑 ~/.dsh/AGENTS.md 与 ~/.dsh/memory/*.md。Host 半边注册 /api/dsh-memory 路由（回环限制），client 半边注入侧边栏入口与中心面板。热插拔挂载，不改 DSH 源码。

Long-term cross-session memory and association for DeepSeek Harness: durable memory records, activation-spreading recall, and automatic prompt injection.

The 7-7-7 execution loop for DeepSeek Harness — plan, run, capture, close, compound, with a human gate.

Cross-session long-term memory for DeepSeek Harness (dsh): durable JSON-file memory store with memory_save / memory_recall / memory_forget / memory_list model tools, installable as a dsh bundle.

Memoria long-term memory for DeepSeek Harness: one owned Python subprocess + native store/recall tools + auto recall injection

Durable cross-session memory for DeepSeek Harness: local SQLite FTS5 store, three model-facing tools, and a recall prompt section — no embedding service and no sidecar

Local AI memory for DeepSeek Harness: remember, search, and context tools over a built-in SQLite store

DeepSeek Harness 记忆分诊插件：自动判断记忆保留/归档，并自动路由到项目桶或总体桶（规则优先 + LLM 兜底）

Read-only DeepSeek Harness plugin that surfaces Claude Code's project memory, redacted and byte-budgeted

Git-backed, workspace-scoped memory for the DeepSeek Harness (global layer + per-workspace layers)

Long-term memory and self-learning plugin for DeepSeek Harness (DSH) - observe, learn, and remember across sessions. Also supports OpenCode.

Remembers which DeepSeek Harness tools have been failing, across sessions, and tells the next session — so an agent stops rediscovering a dead endpoint one failed call at a time.

项目记忆（Project Memory）：本地优先的项目记忆插件。每个项目一份 .dsh-memory.json（按 cwd 隔离），提供 memory_read/recall/write/update/delete 五工具、/memory 命令、设置页记忆管理 UI（编辑/删除/拖动排序/状态过滤/搜索/多项目切换），全部遵循'随核心快速适配'（适配器+探测-退化-上报）与'万物皆插件'（可独立挂载/停用）。

脑珊瑚 Coral Memory — 面向 LLM Agent 的热度感知记忆层（DeepSeek Harness 插件）：MCP 记忆工具（memory_search/insert/thread_* 等 16 个）+ 设置面板（统计/容量/检索/配额）。作者：Mr. Code Muggle (@Ne)。

Cross-project experience recall for DeepSeek Harness: when the running work matches something your memory store already learned elsewhere, that lesson is injected before the next step. Runs fully locally, judged by a local small model.

Task-level memory for long-horizon DSH sessions: force-injected, compaction-proof, manually mounted.

DSH 记忆知识库插件：通过 ETAPI 把 Trilium 笔记库接入 agent（记忆读写/笔记管理/搜索/周报/附件/日历/备份），GUI 提供独立设置页。 · DSH memory-knowledge plugin: connect Trilium to the agent via ETAPI.

Bounded-file memory for DeepSeek Harness local agents (ME.md + project MEMORY.md vault, cache-stable inject, inbox, Memory rightbar). No store, no embeddings, no LLM calls.

记忆核心（工作区版 memory-eternal-ws）：按 DSH 工作区自动切库的本地 Markdown 记忆库插件。每个项目用自己的 .dsh/memory-vault，跨项目知识走全局库。fork 自 dsh-memory-eternal v0.7.0，保留自动沉淀 / 自动召回 / 知识卡 / 知识图谱 / 审核中心 / 回收站 / 配置页全部功能。

Persistent cross-session memory for DeepSeek Harness (DSH) agents: injects markdown notes into every session's system prompt and adds a `remember` tool that maintains them host-side, outside the agent's file sandbox.

Cross-session memory plugin for DSH — auto-extraction, semantic recall, scheduled maintenance, LLM-powered consolidation, context explosion prevention, global Soul identity

Workspace-scoped durable memory for DeepSeek Harness and optional voice integrations

AI-memory 深度集成 —— 基于 One Memory 源码的 DSH 语义记忆插件

Six-layer agent memory for the DeepSeek Harness: identity / behavior / cognitive / information / experience / skill layers plus working memory, backed by per-workspace SQLite (FTS5 + vector) with behavior-rule enforcement, LLM consolidation, skill & exper

A per-workspace HindSight switch for the DeepSeek Harness composer: turn memory off for one workspace without uninstalling it anywhere else.

Deterministic cross-session transcript retrieval for DeepSeek Harness: the model-facing `recall` tool searches past session logs with explicit scope control

Long-term memory for DeepSeek Harness backed by Hypatia: a host-side CLI adapter, a plugin-owned SQLite control ledger, same-request recall, and narrow memory tools. Requires the `hypatia` CLI on PATH.