agent-memory 56

deja-vu memory for DeepSeek Harness: the session history of forty other coding agents, searchable and recalled before each step — a local index, no LLM.

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.

PLUR memory for DeepSeek Harness — engrams injected straight into the prompt, no tool call required

Curated file-based long-term memory for DeepSeek Harness — human-readable markdown notes, one plain-file store shared across hosts (git-ignored when it lives inside a project repo), and a deterministic index cap enforced by ctx.tools.guard()

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

Bounded, 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

Recent conversations stay vivid. Older ones fade into summaries, not oblivion. StrataGate gives DeepSeek Harness six-layer, time-decaying memory, while lasting events and relationships settle into a knowledge graph. Bring your memories from other AIs with

DeepSeek Harness (DSH) local-first cross-session project memory: bounded cache-friendly Hot Memory, BM25 recall/cache, provenance, lifecycle and bilingual Web GUI; no embeddings, external service or bundled runtime dependencies.

L0~L3 分层蒸馏记忆插件 for DeepSeek Harness：自动捕获对话（L0）、抽取原子记忆（L1）、整合场景块（L2）、蒸馏核心画像/团队方法论（L3），并在模型步骤前自动召回注入。移植自 MemoryCore (TencentDB Agent Memory) 的管线设计。

Co-Engram team memory plugin for DeepSeek Harness (dsh): native Cordis tools + dynamic prompt-signals injection.

File-based memory plugin for DeepSeek Harness (DSH) — cross-session memory in plain markdown files, with a memory star-map view, type/tag filtering, retrieval aliases, and an optional autodream pass that consolidates memories on demand or on a schedule —

Hermes-style persistent memory for DeepSeek Harness (DSH) — a faithful port of the hermes-agent MEMORY.md / USER.md mechanism: bounded dual-bank memory, one `memory` tool (add/replace/remove/batch), frozen-snapshot injection, nudge reminders, restrained m

Local-first persistent memory infrastructure for DeepSeek Harness: bounded hot-memory bootstrap, explainable cold recall (exact + Chinese BM25), lease-lock transactional writes, read-only governance, and trajectory review. Pure Python + Markdown, zero ext

DeepSeek Harness 的 TencentDB Agent Memory 移植：L0 对话捕获 → L1 结构化记忆提取 → L2 场景/L3 画像，自动召回注入 + 记忆/对话搜索工具；复用现有 ~/.memory-tencentdb/memory-tdai 数据；附 Web UI 设置栏。

Keeps long coding-agent sessions lean: wrap a stretch of work in a named task, and when it ends, fold that whole span into one short titled summary. The conversation stays readable, context costs stay low, and any fold's original content can be read back

agentmemory for DeepSeek Harness (dsh): full memory_* tools, capture hooks, and context injection over the local REST server

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).

Cross-session memory with governance, self-evolution and an approval-gated write path for DeepSeek Harness. Heat-ranked recall, environment conventions, forgetting lifecycle, supersession chains, poisoning defense, auto-distillation, and an open measureme

Persistent memory for DeepSeek Harness: per-conversation notes, selective injection, project memory, semantic Vault search (bge-m3, free optional key) and automatic retrieval — agents stop forgetting.

Living memory for DeepSeek Harness — self-tending knowledge base: nightly patrol, temporal decay, RRF hybrid recall, knowledge graph, telemetry. Built by 暖暖 (NuanNuan).

Cairn — long-term memory for the DeepSeek Harness: persistent cross-session memory (store, tools, auto-extraction, context injection) as one installable profile bundle

Native layered memory for DeepSeek Harness with persona files, workspace scope, semantic recall, and background consolidation

anagenesis —— DeepSeek Harness 上的可编程记忆编排层 + 自我进化引擎：自带闭环记忆存储（不依赖任何外部记忆插件）、17 个面向 Agent 的语义记忆工具（召回/提交/提升/降级/拆分/锁定/过期/反事实重思）、运行时可切换的注入策略、带审计与回滚的元策略自调节、全程可逆效应、自动注册 `anagenesis` Agent 预设，以及零依赖可视化层（终端仪表盘 + mermaid/d2/ascii 文本图表 + 可选桌面窗口）。

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。

Native memory for DeepSeek Harness — auditable facts with evidence chains, powered by StateCore

Explicitly governed shared memory spaces for DeepSeek Harness sessions

Memory plugin with built-in governance for DeepSeek Harness

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

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

Evidence-governed experience memory for DeepSeek Harness

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

ego lite for DeepSeek Harness, with a memory it keeps: the agent recalls what it learned about a site before it acts, promotes a script that worked into a reusable site tool, and hands you the keyboard through a real dsh prompt when a page needs a human.

Memory Fortress for DeepSeek Harness: 5-track layered memory, self-evolution, knowledge graph (SQLite+FTS5), status pill. 本地记忆堡垒：五轨记忆·自我进化·知识图谱·状态灯。

A settings page for the Hindsight memory stack in the DeepSeek Harness sidebar.

L0~L3 分层蒸馏记忆插件 for DeepSeek Harness：自动捕获对话（L0）、抽取原子记忆（L1）、整合场景块（L2）、蒸馏核心画像/团队方法论（L3），并在模型步骤前自动召回注入。移植自 MemoryCore (TencentDB Agent Memory) 的管线设计。

Approval-gated workspace instructions and memory for DeepSeek Harness

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

Shared cross-agent memory for DeepSeek Harness: six model tools backed by the portable @domencai/agent-memory CLI.

OpenViking memory integration for DeepSeek Harness with configurable automatic context injection; derived from the official OpenViking DSH plugin.

Curated file-based long-term memory for DeepSeek Harness — human-readable markdown notes, one plain-file store shared across hosts (git-ignored when it lives inside a project repo), and a deterministic index cap enforced by ctx.tools.guard()

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

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

Auditable, workspace-scoped long-term memory runtime for DeepSeek Harness.

--- description: "The dsh-ab-memory package: a cross-session, file-backed agent memory with five tools (remember / recall / forget / load_skill / distill) and an always-on light injection." kind: "package-reference" ---

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)。

Perseus Vault memory plugin for DeepSeek Harness: automatic pre-step recall injection from a governed memory vault

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.

Composable, view-based memory for DeepSeek Harness. Pluggable sources and strategies, with layered memory out of the box.

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

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