Memória

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

Memória de transferência autoexplicativa por diretório de trabalho e branch do git: registra os turnos, condensa-os em Markdown conciso e injeta o resultado em sessões futuras a partir de ~/.agent/agent-handoff, compatível byte a byte com o pi-handoff

Wiki local em Markdown como memória de longo prazo para o DeepSeek Harness — portado do llmwiki

Memória de persona persistente e de longo prazo para o DeepSeek Harness: armazenamento em MEMORY.md/USER.md, ferramentas memory + memory_search, injeção de contexto por requisição e verificação de segredos. Portado em espírito a partir do pi-hermes-memory

Um plugin do DeepSeek Harness que transforma a sincronização git do anywhere-claude-mem em um peer do DSH: puxa memória entre máquinas no início da sessão e envia novos prompts/observações assim que chegam ao worker do claude-mem

Backend de memória vetorial + em grafo: ferramentas observe/remember/search/recall contra um servidor memoria local, combinando recuperação semântica HNSW, busca por palavras-chave FTS5 e sinais de grafo de conhecimento via ranking RRF, com persistência automática ao final do turno e isolamento de namespace por agente

Ponte para uma base de conhecimento global em Markdown compartilhada com a CLI kb.cmd do Codex: ferramentas kb_add/kb_search/kb_show/kb_timeline com frontmatter compatível byte a byte

Cofre de memória entre sessões: ferramentas remember / recall / forget, injeção de prompt por turno e um navegador de entradas na página de configurações

A super-simplified LLM-wiki memory plugin: one index document (auto-loaded) + one markdown file per topic (read only when needed) — no dumping everything into the context and burning tokens. Simple and lightweight, painless to install/uninstall, and freely editable however you like.

DSH自记忆插件：结构化记录问题、方案与模型调用，支持加权检索、前提感知排序与外部导入。

DeepSeek Harness 分层长期记忆插件：瞬时/情景/语义三层记忆，自动捕获、AI 提炼、跨会话召回与可视化管理。

DeepSeek Harness (DSH) plugin for local-first automatic Wiki memory and native Skill generation.

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

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

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

Import chat history and memory from other AI agents (Claude Code, Codex CLI, Gemini CLI, Aider, Cline, OpenCode, Hermes Agent, OpenClaw) into DeepSeek Harness

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

Notion connector for DeepSeek Harness: search, read, query, create, update, and append Notion pages and databases via six agent tools, with a Web settings page — configured once with an Integration Token.

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.

DSH ↔ agentmemory session-memory bridge: mirrors session lifecycle into a local agentmemory daemon (REST), exposes memory_recall / memory_remember tools, and injects a per-session memory context window via agent/pre-step.

Tracks the agent's state as Yogācāra mental factors over a durable seed store, and feeds it back into the prompt as first-person inclination.

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; each recalled fact cites the turn it came from and carries validity dates, so superseded facts stop being retrieved.