442 results
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.
Unofficial community plugin: per-session Engram memory for DeepSeek Harness — spawns an engram MCP child per agent session rooted at the session workspace, registers mem_* tools per agent scope, and injects the Memory Protocol as a system-prompt section.
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
Deterministic cross-session transcript retrieval for DeepSeek Harness: the model-facing `recall` tool searches past session logs with explicit scope control
Cross-session task-list memory for DeepSeek Harness
What will your agent's context cost before it runs? Audit instruction files, skills, MCP tool schemas and memory per source — with duplicates, always-on versus on-demand costs, and a budget you can enforce in CI.
Layered, approval-gated, auditable cross-session memory for DeepSeek Harness — a capability seam (ctx.memory service + local SQLite provider + memory tool + frozen snapshot injection), not another memory warehouse
DeepSeek Harness plugin bundle: the 墨墨学习 mirror MCP server (mcp__maimemo__*) plus the momo-daily-learning skill
为 DeepSeek Harness 带来分层记忆（全局 / 用户 / 项目 / GIT 分支 / 每日）与自我进化（经验沉淀 + 技能自动创建）和技能管理、待办管理、CLI 调度（kimi/codex/grok/hermes 等外部 AI 统一调度）、临时信息便签，带 WebUI 管理界面。Hermes-style long-term memory, self-evolution, skills, todos and external CLI agent dispatch for DeepSeek Harness. 本构建另内置三份记忆运维技能（压缩 / 整理 / 注入轨毒源取证）。
DSH memory plugin gated by the TypeSafe Jev decision model: mem_* tools whose every read/write is a typed judgement (choice/noul) — write gate, recall gate and a fail-closed injection gate with budget, audit log and restore/merge.
Native DeepSeek Harness bundle for governed MemOS memory, a Markdown wiki, and local Mirobody health-data normalization.
DeepSeek Harness agent tool (session_search) for full-text search across historical sessions backed by core SQLite FTS5 engine without memory overhead.
Cross-session memory for your dsh agent: remembered, recalled, and re-verified instead of assumed.
Cross-session project engineering memory for DSH coding agents: durable per-project records of problems, failed attempts, verified root causes and constraints, recalled automatically before the agent plans.
DeepSeek Harness 长期记忆插件：四通道检索 + 演化闭环 + 分层治理（SQLite 单一事实源 + Markdown 快照）
DSH desktop plugin: cross-session memory (topics, inbox, index injection).
Adds Chinese web-fiction planning, file-backed memory, chapter workflow, consistency review, and style profiling skills to DeepSeek Harness agents.
按工作区记录未完成任务：自动捕获排队/执行中的用户指令，持久化到磁盘，一键恢复重发。
Shared memory-bank skills and a read-only project dashboard for DSH.
Cross-session project memory for DeepSeek Harness: seven-layer SQLite memory, first-turn snapshot injection, per-message keyword hits, memory_remember/search/project tools, automatic reflection with reflection-fold UI, and idle-triggered dream consolidati
MemoryDirector plugin for DeepSeek Harness: LLM-driven remember/forget across turns (the official harness has no memory concept)
Action-State Memory Engine: typed time-series memory (states + actions) with trend, anomaly, and causal analysis for DeepSeek Harness
Claw persistent memory: vault, daily notes, review, flush. 完整留存：金库、日记、回顾、压缩前冲洗。
dsh 梦境记忆整合插件：凌晨随机触发，把当天会话/Hindsight 记忆生成叙事化梦境日记（法塔人格），高价值洞察晋升回 MEMORY.md，梦境与晋升记录存 SQLite 并在 web 梦境 Tab 展示。