dsh-mnemon
Composable three-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggable long-term memory, guarded strategies, WebUI, and headless tools.
26 results
Composable three-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggable long-term memory, guarded strategies, WebUI, and headless tools.
Codex-style temporary side conversations for DeepSeek Harness.
Native continuity recovery for long-running DeepSeek Harness agents
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).
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.
Adaptive Reversible Context (ARC) for DeepSeek Harness — provider-aware, cache-conscious context governance with reversible recovery.
Agentic Surface Compaction (ASC) for DeepSeek Harness: the model decides when and what to compact, committed as durable session-log replacements with full replay, search, and degradation
DeepSeek Harness dynamic context pruning plugin (model-driven context management)
DSH 记忆管理插件(宿主级,标准化重写版):文件夹记忆库、印象、组合与双向链接、会话级注入计划与消息注入、规约记忆与最近会话总结的新会话自动注入、会话总结、跨工作区会话列表、6 个 Agent 记忆工具、左侧图谱双视图浮层与消息跳转、设置页开关。只依赖 DSH 核心扩展点(settings/tools/agent 事件/webServer),功能实现自包含,官方升级影响面最小。
Forgetting engine for AI agents — memory TTL, decay, eviction, audit. The opposite of memory programming.
Minimal epoch bootstrap, full-tool promotion, and hard handoff compaction for DeepSeek Harness
Token-efficient tool-result pruning policy for DeepSeek Harness presets.
Context Transparency Manager: the model context as a visible, editable, effectiveness-scored surface (self-contained dsh bundle plugin)
High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness — a drop-in upgrade over dsh-compaction-basic.
Model-driven context-window rollover bundle for the DeepSeek Harness: fresh working context, durable model-managed notes, a small verbatim recent tail, and targeted history recovery — no summarization.
Windowed, reversible context management for DeepSeek Harness; replaces Basic compaction.
DSH 上下文管理插件:任务边界、项目帧、自动判别与上下文优化(开发中,R2 判别域 P8–P14b1 已施工)
Keeps long coding-agent sessions lean: wrap work in named tasks and, when one is done, fold its whole span into a short titled summary. The conversation stays readable, context costs stay low, and every fold's original content can be read back on demand. For DeepSeek Harness.
Reusable trajectory-tree context, exact-turn forks, and bounded cross-session recall for DeepSeek Harness
Agent instruction manager for DeepSeek Harness: edit, refine, and template the AGENTS.md files the harness actually reads — the user-global ~/.dsh/AGENTS.md and per-workspace AGENTS.md — from a sidebar panel.
High-fidelity, faithful, bilingual, recursive compaction backend for DeepSeek Harness — a drop-in upgrade over dsh-compaction-basic.
Persistent, searchable, per-project memory for the DeepSeek Harness: decisions, rules, and sprint context in a queryable DuckDB file, rules enforced on every model request, with a full management UI in the Web Client
Active Context Pruning (ACP) for the DeepSeek Harness — model-driven context management as a CompactionEngine backend.
Session health for DeepSeek Harness: real token-meter data, configurable continue-vs-new decision model. Reactive header badge (compaction-aware), /compass command, context_compass tool.