Memoria

Markdown folder long-term memory for DeepSeek Harness: one file per fact, an index line per memory, mounted into every request as a system prompt section

A typed, inference-capable ontology (TBox + ABox) plugin for DeepSeek Harness — durable domain knowledge the agent can define, assert against, and query under schema constraints.

DeepSeek Harness (DSH) plugin — inject context when user input or model output hits configured keywords, with toggleable/configurable rules and model-editable memory.

Project knowledge base plugin for DeepSeek Harness: Open Knowledge Format (OKF) bundles per project, agent search/read tools, a Web UI browser/editor, and a bundled OKF authoring skill

Industrial-grade 4-tier cognitive memory, red-light guard, and vector semantic engine for DeepSeek Harness (dsh).

Generate AI-narrated DSH session reports (daily/weekly/monthly, any date range) and sync them to flomo (浮墨笔记) with one configurable tag (default #write/dsh) and automatic # stripping, via a web settings panel with daily reminder.

DeepSeek Harness community Bundle for local, evidence-backed Agent Memory

File-based self-evolving memory for DeepSeek Harness v2: compression & extraction over official compaction, daily episodic layer, dream consolidation to semantic files (user/agent/memory/dream + project), catalog disclosure injection, no confidence machin

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

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.

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.

Project memory for coding agents on DeepSeek Harness: similar past edits surface as precedents, out-of-scope edits are blocked, and cognition persists across sessions (47 upstream-verified fixes, gold-free 20-task run).

PLUR memory rendered into the system prompt on each assembly rather than exposed as a tool call, so the block is replaced instead of appended and context stays flat across a session. Fully local hybrid search (BM25 + BGE fused with RRF), plain YAML storage you can edit, per-workspace scoping, and a /plur-memory browser.

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, weekly-report workflow, attachments, calendar notes, backup/import, and a settings card.

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.

Compaction backend replacing LLM summarization with a deterministic semantic extractor (keeps code/paths/commands, drops chatter) plus 28.4x KV-compression accounting.

Session context triage for long DeepSeek Harness sessions: deterministic screeners trim stale, duplicate, failed, and oversized content through the official ctx.compaction seam.

PostgreSQL-backed durable memory for DSH agents: MCP memory tools plus a Web panel for reviewing memories and candidates.

Herramientas avanzadas de memoria: inyección de contexto de sesión (perfil + recuperación), decisiones recientes, informe de salud, lista de permitidos de espacios de nombres, grafo de relaciones de memoria y búsqueda de entidades; complemento de dsh-memoria.

Guardián de deriva de premisas tras la compactación: inyecta un aviso de un solo uso cuando un resumen de compactación pierde un anclaje literal crítico.

Puente hacia una base de conocimiento global en Markdown compartida con la CLI kb.cmd de Codex: herramientas kb_add/kb_search/kb_show/kb_timeline con frontmatter compatible byte a byte.

Memoria de trabajo respaldada por archivo: memoriza/recupera premisas clave textualmente en un archivo de notas de sesión, para que sobrevivan a la compactación de contexto sin pérdida.