by LAYZR114

北极星记忆：DSH 项目记忆插件。Project Memory plugin: tiered injection, semantic recall, hard-guard for critical memories, per-project isolation.

Vector + graph memory backend: observe/remember/search/recall tools against a local memoria server, fusing HNSW semantic recall, FTS5 keyword search, and knowledge-graph signals via RRF ranking, with

Write notes and memos to flomo (浮墨笔记) from any agent via the flomo_send tool, configured once with the flomo API URL or API Key.

Project-scoped local memory with review-before-recall, source references, reversible consolidation, and a portable Cordis service; the Harness adapter provides search and settings, with optional Brain

Post-compaction premise-drift guard: injects a one-shot notice when a compaction summary drops a critical literal anchor.

Hindsight long-term memory for DeepSeek Harness: injects relevant memories before each turn and retains finished turns to a Hindsight bank.

Dual-ledger cross-session memory: auto-extracts lasting facts from conversations into MEMORY.md and maintains a PROGRESS.md project ledger, recalling both into every new session.

Persistent memory for DeepSeek Harness with curated facts, automatic turn retention, and graph- and vector-ranked recall.

Connect Trilium notes to the DSH agent via ETAPI with 20 agent tools: durable memory (remember/recall + auto-injected index), note management (CRUD/clone/attributes/revisions), full-text search, weekl

Auto-supplement QMD semantic search when the model greps/globs a knowledge-base directory: zero-dependency DSH plugin, async injection via next-step, no manual invocation.

Bridges the MemOS memory service over MCP: the agent gets add/search/update/delete memory, multi-cube sharing, and a memory scheduler as mcp__memos__* tools.

Yuque knowledge base as external memory for dsh — auto-injects matching document fragments into conversation, with catalogue search, cloud full-text search and online reading.

Coding retrospect distilled memory for DSH: distills rejected solutions, pitfalls and constraints from each turn via a local LLM, tags them into MemOS (type:rejected_solution), and boosts weighted rec

Decision-and-goal memory with lineage: explicit commands and a model tool record decisions deterministically, a status card re-anchors them across compaction, a lossless event stream with BM25+jieba r

Bi-temporal memory backed by a SodaMem daemon: recall is contributed to the prompt while each turn is assembled and every closed turn is ingested, with no tool call and no model call on the read path;

Permanent memory plugin for DSH with vector search, LLM reflection, and knowledge pages.

Reading archive for dsh: after reading open-source code, capture quick notes or write full deep notes that group into one card per repo / file / symbol, stored as an append-only log of Markdown notes

Long-term memory injected at session start: preferences/facts/summaries/knowledge in global and per-project scopes, budgeted recall via `agent/pre-step`, durable JSON store.

Scans the skills visible to the current session and ranks them by relevance to the recent conversation.

Context trimmer: lists the current session's context entries with role, preview and ≈token estimate (cl100k), highlights over-threshold items, and removes selected entries exactly without LLM summariz

LLM-driven remember/forget memory: after each turn a model decides what to keep (MemoryDirector), injects relevant memories before each step, dedups, and persists cross-session.

Knowledge base with a corrective acquisition loop for DeepSeek Harness: when the agent keeps hitting the same failure, a background worker fetches the web under a rate limit, distills the result into

Memory consolidation tuning for dsh-mneme (autoDream enabled, schema-max output budget, deepseek-chat route) plus the llm-deepseek reasoning-effort fix, an MCP bridge to the auditable seed-society age

by SeanWang114514

Per-workspace memo/todo panel that auto-captures queued and running user instructions, marks preempted tasks as interrupted, and restores them to their previous state with one click.