Memory Plugins for DeepSeek Harness

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.

Connects DeepSeek Harness to ReMe's local-first, self-evolving personal knowledge base: automatically captures completed main-agent conversations as user-owned Markdown memory, searches conversations and source material through reme_search with BM25, optional embeddings, and wikilink expansion, and schedules daily memory consolidation.

Shared Markdown memory for DSH and other coding agents, with automatic capture, pre-step context injection, searchable recall, and memory-to-skill self-evolution through a review panel.

Reads the session files nineteen other coding agents on this machine already wrote — Claude Code, Codex, Cursor, opencode, Antigravity, Kimi, Cline, Zed and more — including sessions from before it was installed: six tools (deja_recall, deja_session, deja_blame, deja_fix, deja_how, deja_remember), a /deja command, and optional automatic recall added to the runtime context. Local BM25 index, no LLM, no embeddings, no network (dsh plugin --profile web add dsh-deja).

Traceable, searchable cross-session memory for DeepSeek Harness — conversation knowledge as typed graph nodes (TASK/SKILL/EVENT) and typed edges.

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

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

Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.

Long-term memory for DeepSeek Harness kept as plain markdown, one fact per file, readable in any editor. The `MEMORY.md` index has a hard 200-line / 25 KB cap enforced by `ctx.tools.guard()`: a write that would grow an over-cap index is denied, while a rewrite that shrinks it always passes, so an oversized index can be compacted step by step. The plugin never writes memories on its own — what is kept is decided by you and the model. The same store is also used by Claude Code, Codex, Kiro and OpenClaw.

Local Git-backed long-term memory for DeepSeek Harness with cited context, usage-aware read tools, safe sync, previews, and rollback.

Long-term memory for DSH agents — durable, inspectable memories with recall, search, browse and knowledge-graph tools, import from ten other AI coding tools, and a settings page.

Bounded, layered, approval-gated, auditable cross-session memory: a typed `ctx.memory` seam with a zero-dependency SQLite provider, a `memory` tool, and frozen snapshot injection, plus the dsh-memory-protocol v1 rehearsal with an adapter registry and a distributable conformance suite.

DeepSeek Harness integration for OpenContext with durable cross-session memory, automatic prompt capture and recall, session summaries, structured insights, and document retrieval.

Self-evolving AI memory engine with heat-powered decay (power-law forgetting), sleep consolidation, entity heat projection, and offline semantic search — memories grow, cool down, and fade just like a real brain.

Project-scoped cross-session memory: seven-layer SQLite store (soul/user/project/fact/lesson/rules/topic) on node:sqlite, cache-friendly first-message injection plus per-message keyword hits, memory_remember/search/find_similar/read/update/project tools, and idle-window consolidation ("dream") with peak-hour suppression. Prompt texts ship as per-language data files — the framework supports multilingual users.

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

Cache-friendly three-layer memory for DSH: lean auto injection, per-turn AI consolidation, proactive calendar reminders and warm greetings, plus memory inheritance from other AI tools.

Automatic conversation distillation: background subagent reflection + skill create/update.

Local-only project memory with zero bundled runtime dependencies or external services: JSON as the source of truth plus generated PROJECT_MEMORY.md, token-bounded session-frozen Hot Memory for prompt-prefix cache stability, cached cross-project BM25 recall, trusted session/turn provenance, explainable pre-write duplicate/conflict governance, editable importance/pin/tags/supersede/archive lifecycle, configurable top-level turn-end distillation, and a bilingual Web GUI for search, inspection, diagnostics, and live settings.

Local Obsidian vault as the agent knowledge store, with read-only DSH tools that route status, preference, correction, memory, project, search, and suggest to the matching page.

StrataGate gives DeepSeek Harness evolving, local-first long-term memory for user preferences, project decisions, conversations, and tool results across sessions; it layers history with user-tunable time decay, reinforces memories through real answer use, shows workspace-aware usage counts, and keeps recalled evidence traceable to its original messages.

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**.

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

ShiGuang Memory Engine (SGME) bridge: multi-agent shared long-term memory via HTTP — L0/L1/L1.5/L2 distillation, scenario-based injection, unified search, and proactive care signals (memory_search / wiki_search / signal_pull / signal_claim / signal_ack), installable as `dsh-sgme`.

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.

Long-term memory for DSH: conversations auto-distilled into atomic facts, scene summaries and a persona profile, with relevant memories injected before every model step. Zero-config out of the box — hybrid BM25 + vector retrieval, optional offline local embeddings, chat/work family separation.

Connect dsh to a local Obsidian vault: search, read, write, move, and trash notes through `obsidian_*` tools.

Local-first persistent memory for DeepSeek Harness: bounded pre-step hot-memory injection, exact and Chinese-bigram BM25 cold recall, six agent tools, approval-gated lease-lock writes with recovery receipts, and read-only governance and trajectory-review candidates.

Semantic retrieval, resource management, auto-recall (user + agent dual spaces) and session memory for DeepSeek Harness: memsearch/memfind/memread/membrowse/memgrep/memglob over viking:// URIs, memadd/memremove resource management, memqueue observer status, memcommit session capture, and memlearn skill playbook minting.

Long-term memory & self-evolving plugin for DSH: L0 capture → L1 memory extraction → L2 scene grouping → L3 user persona, auto recall injection, skill synthesis, fully local (SQLite FTS5 + jieba, optional vector recall).

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

General-purpose knowledge base for DSH: import md/txt/json/yml/docx/pdf, folder management, FTS5 full-text search (BM25), and a Web management UI.

Cross-session memory plugin for DSH (v0.6.1, npm @asherliner/dsh-memory-connect): auto-extraction, SQLite FTS5 indexing, RRF semantic recall injected into the system prompt every turn, scheduled maintenance, LLM-powered consolidation via ctx.llm, context explosion prevention, and global Soul identity via ~/.dsh/soul.md. v0.5.0 added temporal context graph (valid_from/valid_until/supersedes, append-only corrections via reviseMemory), trust model (recalled history injected as untrusted reference, current instruction always wins), turn-end summarization. v0.6.0 added local semantic embeddings (BAAI/bge-small-zh-v1.5 via embed_server.py, cosine + RRF fusion with FTS5, no cloud calls, ~232 msgs/sec on CPU). v0.6.1 fixed ~ expansion in path config. Zero-config install.

Technical-preview local graph memory for DSH and Codex: recalls owner-global and current-project evidence before each turn, writes USER and ASSISTANT records separately, and preserves project, session, actor, and source provenance for a visual atlas and cited knowledge pages.

Local-first Agent Experience Network for DeepSeek Harness, distilling task-level experiences from traces and live manifests, grading by H0-H4 evidence, discovering by compatibility, and promoting only after explicit review.