Memoria

OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.

Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.

Deepseek Harness、Openclaw知识图谱记忆插件。2026年4月受邀发布在清华大学讨论会。Knowledge Graph + Memory；Knowledge Graph Context Engine for OpenClaw — extracts structured triples from conversations, compresses context 75%, enables cross-session experience reuse

Memoria persistente supervisionata da LLM per agenti AI — recupero basato su grafo, conoscenza cross-sessione, binario singolo. Funziona con DeepSeek Harness, Claude Code, OpenClaw e qualsiasi runtime agente.

Failure-recovery memory: search and record failure-recovery lessons from real engineering sessions, with BM25 + semantic RAG retrieval and a lessons knowledge base.

MemOS Cloud lifecycle memory plugin for DeepSeek Harness

Registers the local flowix-cli MCP server so the agent can search, read, create, and edit Flowix memos and mind-map artifacts.

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()

The Engramory curated-memory discipline as an installable plugin ([npm: dsh-engramory](https://www.npmjs.com/package/dsh-engramory)): a deterministic 200-line / 25 KB cap on the `MEMORY.md` index via `ctx.tools.guard()` — growth denied, a shrinking rewrite always passes — plus the protocol registered as a runtime skill. The store is plain markdown, one file per fact, shared with Claude Code, Codex, Kiro, and OpenClaw.

Integrazione approfondita con Mnemon: memoria locale a tre livelli (Runtime Memory, Documents recuperabili, Memory Spaces supervisionati).

Implementazione puramente a plugin che porta a DeepSeek Harness capacità di «memoria a lungo termine cross-sessione + auto-evoluzione in background»: memoria a cinque binari, consapevolezza dei branch Git, auto-revisione durante il turno, auto-evoluzione delle skill con gestore delle skill, to-do a quattro binari, scheduling COI, broadcast tra sessioni, ricerca tra sessioni, gestore dei prompt e note temporanee — zero modifiche al core, zero dipendenze a runtime, pronto all'uso e pulizia completa alla disinstallazione.

Memoria cross-sessione limitata, a strati, soggetta ad approvazione e verificabile: un'interfaccia tipizzata `ctx.memory` con un provider SQLite a dipendenza zero, uno strumento `memory` e l'iniezione di snapshot congelati; ogni scrittura passa dal gate di approvazione e resta ricostruibile dal log di sessione.

Model-driven context compression (Active Context Pruning) for DeepSeek Harness: the model decides when and what to compress.

Cross-session memory engine for DeepSeek Harness: SQLite store + human-editable Markdown mirror, autoDream consolidation, offline semantic search (local vector/rerank/clustering), entity-attribute-timeline, Sleep Mode, custom-model autoSummarize, and 7 memory tools.

Grafo di memoria spazio-temporale multi-agente con persistenza cross-sessione e richiamo filtrato per importanza

Distillazione automatica delle conversazioni: riflessione in background tramite subagent + creazione/aggiornamento delle skill.

Plugin di memoria automatica per la GUI web di DeepSeek Harness: memoria a tre livelli (utente / note di progetto / log giornalieri) con iniezione e recupero automatici, riflessioni giornaliere, un pannello visuale e una pagina impostazioni, con eredità della memoria da altri strumenti AI.

Cache-aware local project memory for DeepSeek Harness (DSH): agents distill session work, lessons and next actions into a local JSON store (~/.dsh/dsh-memoir.json, source of truth) with a per-project PROJECT_MEMORY.md projection; bounded hot-memory (ranke

A markdown notes manager for DSH: full **MD notes manager** and **MD notes editor**, quickly capture conversations into notes, maintain notes by **syncing to Git repositories**, and **bring notes into the conversation context**.

Project-scoped cross-session memory: six-layer SQLite store (soul/user/project/fact/lesson/topic) on node:sqlite, cache-friendly first-message injection, memory_remember/search/find_similar/read/update tools, and per-window nightly consolidation ("dream").

Self-evolving team memory as plain Markdown in git: a native Cordis plugin that registers 38 bare-name memory tools plus a prompt-signals section re-evaluated at every assembly, with RPE reinforcement, decay and sleep consolidation; shares one data repo with its Claude Code (MCP) and OpenClaw hosts; verified against DSH 0.1.0-rc.6.

Memoria cross-sessione: SQLite con uno specchio Markdown modificabile manualmente, consolidamento in background (deduplicazione, merge, risoluzione dei conflitti) e sei strumenti di memoria.

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

Persistent AI memory backed by a local Obsidian/Codex vault: five obsidian_memory_* read/write/search tools plus a sidebar vault browser.