dsh-df-memory
dsh-df-memory
382 results
dsh-df-memory
基于 DeepSeek-OCR1 光学压缩记忆系统:把记忆渲染为图像存储,支持 SoM 分段、年龄衰减/模糊化、激活召回、DSH Agent 检索
Galgame Doctor for DeepSeek Harness: multi-release translation memory, reviewer CSV queues, evidence plans, strict QA, and rollback.
Eyes for text-only DeepSeek on DeepSeek Harness: image understanding via Antigravity IDE quota (default, flash/pro), OpenAI-compatible VLM endpoints, Gemini API, or local Ollama — model-invokable vision tool, wrapper adapters for deepseek/opencode-go, evidence memory, and a polished client panel.
Native layered memory for DeepSeek Harness with persona files, workspace scope, semantic recall, and background consolidation
Generic stateless dialogue compression that mimics human memory — forgetting-curve bounded context for LLM conversations, with a ready-to-use adapter module for DeepSeek Harness (DSH).
Git-backed, reviewable long-term context for DeepSeek Harness.
DSH 插件:/gamemode 1 = 一键切换到内置创造模式(cordis)预设。DSH plugin: /gamemode 1 = switch to the built-in Creative Mode (cordis) agent preset.
本地优先的 Agent 五层记忆体组件 - DSH 插件
An original high-key prismatic memory theme for the DeepSeek Harness web UI.
LMA (Layered Memory Architecture) 是一个为 DeepSeek Harness 设计的地基插件(Foundation Plugin)。它定义了 “记忆体(Memory Body)” 这一抽象概念及其挂载/卸载协议。 它与其他记忆插件的本质区别在于:LMA 是一个容器和载体,让 dsh-memory-evolve、EchoCore 等“能力性插件”可以挂载其上,它本身也内置了一套可开关的基础记忆流程,作为可选能力。LMA结束记忆功能的“一锅乱炖”,实现跨会话的结构化记忆机制。(目前功能还在持续完善以及测试,对于其他插件的接口在构想完整后逐步推动)
把 Codex(OpenAI Codex CLI / Desktop)的 MCP、技能、全局配置、记忆以适配 DSH 的形式迁移进 DeepSeek Harness(DSH 插件)
Honcho memory for DeepSeek Harness — persistent, cross-session memory that survives context resets and restarts.
Memory protocol enforcement plugin for DeepSeek Harness — forces memory_weave before tool calls, auto-ingests session turns, injects memory context into agent steps. Bridges the opencode-memory MCP server with a hard protocol gate.
Project Memory gives coding agents a single, trustworthy memory for a software repository — so they stop re-learning the same facts and stop writing conflicting "memory" files.
把 WorkBuddy 的文件式记忆系统移植进 DeepSeek Harness:用户级 + 工作区的人类可读 Markdown 记忆(~/.deepseek-harness/MEMORY.md 与 <cwd>/.deepseek-harness/memory/)。
VSCode-like bottom status bar for DSH Web: conversation token usage, host CPU/memory with Linux-style colored char bars, clock, and a public API for other plugins.
Local, storage-bounded cross-session search for DeepSeek Harness conversations with SQLite FTS5, Chinese segmentation, and message-level jump targeting
DeepSeek Harness 记忆插件 - 零外部依赖的 LLM 长期记忆系统
给 DeepSeek Harness 补上时间轴记忆:定宽只追加的事实日志 + agent 自己维护的摘要金字塔,固定阅读预算下 recall 成本不随记忆量增长。
记忆搬家:把 Claude / ChatGPT / Claude Code 的历史记忆搬进 DeepSeek Harness —— 带逐字证据,逐条批准 | Move your Claude & ChatGPT memory into DeepSeek Harness (DSH), with verbatim evidence and one-by-one approval
把「记忆」带进 DeepSeek Harness:极简文本记忆系统,双轨记忆(流水日志 + 人物/产品实体画像),大模型为核心驱动。无需安装其他软件,无需编译,无第三方依赖。
MemoryHub (mh) integration for DeepSeek Harness: loads .memoryhub checkpoint memory on session start, saves dsh sessions back into checkpoints, and registers the mh workflow skill and tools
Find and install DeepSeek Harness (DSH) plugins. Use when the user asks to add a capability to DeepSeek Harness, asks which DSH plugin does X, mentions dsh plugin add, or wants memory, vision, a terminal UI, themes, or any other extension for their DSH agent.