Memory

Focus board for DeepSeek Harness agents: durable, model-maintained notes in the session workspace that pin the objective

Knowledge-base-driven agent preset: wiki long-term memory, a web KB UI, a management page and optional UI polish.

Self-evolving team memory as plain Markdown in git: a native Cordis plugin that registers 38 bare-name memory tools plus

Project-scoped persistent key-value memories with set/get/list/delete/search model tools and JSON-file storage.

Self-maintaining handoff memory per working directory and git branch: records turns, folds them into concise Markdown, a

AGI long-term memory base: multi-agent spatiotemporal memory graph, self-evolving knowledge flywheel, self-cognition, an

Bounded local memory with CBDC authority gating: SQLite + FTS5 claims, scoped recall with explainable use/verify/ignore

File-backed working memory: memorize/recall key premises verbatim in a session notes file so they survive context compac

Bridge into a global Markdown knowledge base shared with the Codex kb.cmd CLI: kb_add/kb_search/kb_show/kb_timeline tool

Session context triage for long DeepSeek Harness sessions: deterministic screeners trim stale, duplicate, failed, and ov

Biomimetic memory system for DeepSeek Harness: plain-Markdown data layer, memory tools, frozen-snapshot injection, grade

Cross-session plaintext memory: deterministic BM25 keyword recall (no embeddings), memory_save/list/search/confirm/forge

One shared Obsidian vault for every agent: dependency-free Python core (search/promote/adjudicate/forget), vault templat

Project-scoped cross-session memory: six-layer SQLite store (soul/user/project/fact/lesson/topic) on node:sqlite, cache-

Conversation history recall for DSH: three-layer (literal/fuzzy/semantic) retrieval over every past session's original t

DSH ↔ agentmemory session-memory bridge: mirrors session lifecycle into a local agentmemory daemon (REST), exposes memor

Model-authored context pruning for DeepSeek Harness through the official compaction API.

Evidence-bound negative-knowledge ledger: persists disproven paths (command_failed, file_missing) with their outcome and

Memory protocol enforcement plugin: bridges the opencode-memory MCP server, forces memory_weave before tool calls, auto-

Automatic, local-first cross-session memory for DeepSeek Harness: layered Event/Element cards, evidence-gated recall, an

The Engramory curated-memory discipline as an installable plugin ([npm: dsh-engramory](https://www.npmjs.com/package/dsh

Cross-session memory vault: remember / recall / forget tools, per-turn prompt injection, and a settings-page entry brows

Native per-workspace memory on the harness's own seams: facts and a bounded always-on profile on the storage-domain JSON

Faithful port of the hermes-agent MEMORY.md / USER.md mechanism for DSH: bounded dual-bank memory (2200/1375 chars), a s

Vector + graph memory backend: observe/remember/search/recall tools against a local memoria server, fusing HNSW semantic

Advanced memoria tools: session context injection (profile + recall), recent decisions, health report, namespace allowli

BM25 keyword-based memory recall.

Organize folders and sessions into projects with shared PROJECT.md memory and AGENTS.md instructions injected into every

Compaction backend replacing LLM summarization with a deterministic semantic extractor (keeps code/paths/commands, drops

Human-readable Markdown memory for DeepSeek Harness: user-level (~/.deepseek-harness/MEMORY.md) + workspace-level memory

Long-term memory & self-evolving plugin for DSH: L0 capture → L1 memory extraction → L2 scene grouping → L3 user persona

Memory Lake as a persistent memory layer for dsh: memory_search, memory_remember, and memory_forget tools over the memor

Structured memory engine for DeepSeek Harness. Offline semantic search, entity-attribute-timeline, autoDream self-consol

Hana-style assistant manager for DSH: visual preset management (cards, yuan personalities, avatar cropping) plus a full

Honcho memory bridge: auto-syncs every conversation turn to a self-hosted Honcho service, with recall/search/remember/co

PLUR memory rendered into the system prompt on each assembly rather than exposed as a tool call, so the block is replace

Technical-preview local graph memory for DSH and Codex: recalls owner-global and current-project evidence before each tu

Vision for text-only agents: a vision_agent tool that delegates image reading to a one-shot subagent on a configurable v

Project memory for coding agents on DeepSeek Harness: similar past edits surface as precedents, out-of-scope edits are b

Enhanced auto-compaction defaults for DeepSeek Harness agent presets: apply tuned threshold/retention budgets and per-mo

Tracks the agent's state as Yogācāra mental factors over a durable seed store, and feeds it back into the prompt as firs

Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflect

OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture,

Long-term memory injected at session start: preferences/facts/summaries/knowledge in global and per-project scopes, budg

Notion connector for DeepSeek Harness: search, read, query, create, update, and append Notion pages and databases via si