dsh-memflow
Per-directory context composition for DeepSeek Harness — .dsh/context.yaml declares systemPrompt + preload for every agent loop; memory is a baseline, not a preset
407 results
Per-directory context composition for DeepSeek Harness — .dsh/context.yaml declares systemPrompt + preload for every agent loop; memory is a baseline, not a preset
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, automatic context injection, an archive on clear, and an optional read-only web panel
DeepSeek Harness bundle that registers the session-summarize skill pack on ctx.skills.
Local-first automatic Wiki and Skill distillation for DeepSeek Harness
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。
WikiBridge:DSH 与 Obsidian vault 的知识库桥接 —— 约束工具(wiki_search/read/write)+ 自动词典检索 + 持久化配置
运动记忆 Motion Memory — DeepSeek Harness 本地记忆管理插件:对话跟踪 + 周期总结,会话沉淀为可溯源的本地记忆文档。
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.
DSH local cross-session memory plugin: capture turn summaries, inject recent days, and search all historical memory with pure JS keyword matching.
Let the AI know you. 让模型主动记下你的判断依据(原则/红线/工作方式),跨会话复用 —— 有容量、会遗忘、每条都说得出为什么记。
为 AI Agent 提供短期记忆缓存、长期知识沉淀、语义检索与持久化存储的统一记忆管理层
Long-term memory for stock DeepSeek Harness: key/value store with question-time recall, plus optional migration from official ChatGPT, Claude, Gemini, and DeepSeek exports.
A living memory workbench for DeepSeek Harness — watch Hindsight memory grow, read and use it, in a persistent sidebar.
Maestro Harness meta-bundle: thin v2 aggregator over eight granular dsh-maestro-* runtime rows (remote, review, govard, memory, mobile, notifier, config, dashboard).
PRO-LONG-style programmatic memory for DeepSeek Harness: appends every session event to a per-workspace log.txt that the agent retrieves with grep/python. Built-in write probe, /prolong status command and permission-deny counter.
Stage-gate governance tools for DeepSeek Harness: model-callable gate_open / gate_check / gate_list / gate_close for in-memory, per-session acceptance checks.
Bridge OpenAI Codex's memory, skills, and configuration into DeepSeek Harness
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。
Edit DeepSeek Harness global AGENTS.md instructions and memory directly in Web settings.
Local Markdown wiki as long-term memory for DeepSeek Harness — ported from llmwiki
Automatic cross-session GoodMemory recall and writeback for DeepSeek Harness
DSH plugin exposing Windows device information tools — one tool per Win32 device category (time, system, cpu, memory, disk, gpu, network, battery, processes, usb, audio, printers). Read-only WMI/CIM + Node os collectors.
DeepSeek Harness plugin: Nocturne Memory client — automated long-term memory (boot/read/search/create/update/delete) backed by your own Nocturne MCP server.
A DeepSeek Harness plugin that integrates claude-mem: query, context injection, manual save, and session lifecycle over a local claude-mem worker's HTTP API