知识记忆 MCP 服务器

Lossless archive and search for AI agent sessions across clients, exposed to agents over MCP.

Self-hosted decision memory for AI coding agents; warns before re-proposing a rejected approach.

Security-hardened NotebookLM MCP with post-quantum encryption

Self-hosted documentation indexer that serves docs from various sources to agents with semantic search.

Persistent, encrypted cognitive memory that works offline.

Record development decisions as structured JSON with Gemini embeddings and search them semantically from a local store shared across AI…

Persistent coding memory across sessions, machines and teammates, with memory search, optional sync, project sharing and automatic capture.

Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.

Persistent memory for AI agents — 36 cited neuroscience mechanisms, local-first, hybrid retrieval.

Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall

Local-first agent memory: a Markdown Obsidian vault as source of truth plus a rebuildable DuckDB index for hybrid BM25, vector and graph…

MCP server for Scrivener: read, write, analyze, and search your manuscripts with AI assistants.

Memory for LLM agents: a local graph where the agent itself keeps decisions, tasks, hypotheses and reasoning between sessions, and gets a…

Agent-first cognitive substrate: 20 verbs + 50 lint dims over a self-validating graph.

Read and edit Word (.docx) documents with tracked changes, threaded comments, footnotes, OOXML-level validation and document auditing.

Local-first memory for coding agents: hybrid LanceDB/Tantivy search, Markdown and code indexes, per-project vaults and recall that…

Lightweight local RAG MCP server. 40x token reduction.

MCP server for accessing curated awesome list documentation

Local-first MCP server giving AI agents contextual knowledge about the people in your life

Local-first AI PKM memory for coding conversations.

Outcome-based persistent memory for Claude Code and OpenCode: memories that help get promoted, misleading ones get demoted.

MCP server for Callimachus: local index and search of your AI coding-agent threads

Search your Mendeley library, browse folders, get document metadata, search the global catalog and add papers to your collection.

Intelligent agent memory with automatic extraction, consolidation, and bi-temporal recall.

The context platform for AI agents: code search, team decisions, and grounded project context.

OSS to create Personas, Skills, Templates, Agents, and Memories to customize your AI experience.

Connect to your Pinecone Assistant and retrieve context from its knowledge engine.

Persistent graph-backed conversational memory for AI agents.

Embedded, local-first agent memory: one SQLite file per namespace, no server, no cloud.

Verified memory for coding agents: claims cited against code, stale withheld, savings receipts.

Long-term memory for AI coding agents, stored as a tree of plain local files.

Contemplative reasoning with Lotus Sutra wisdom framework and ext-apps visualization.

Standalone MCP server for Obsidian vaults — hybrid search, notes & files, memory, tasks, OAuth 2.1

Deterministic state layer for agents: versioned entities like contacts, tasks and decisions with immutable observations and provenance, in…

Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.

Graph-backed session memory for LLMs: checkpoint, resume, file analysis, token-savings stats.

Long-term memory for AI agents — your Obsidian vault as searchable persistent memory.

Local-first automatic memory for Claude Code and Codex: capture, distill, recall from SQLite.

Obsidian vault access: full-text search, note CRUD, frontmatter queries, tags, backlinks, graph traversal, orphan and broken link…

Claude Code memory plugin that mines past sessions for decisions, conventions and bug fixes, stores them in an Obsidian vault and briefs…

Zero-config MCP server for searchable documentation. SQLite or PostgreSQL.

Static server providing persistent tool-specific context and rules to AI models.

One section in, one section out — on Markdown/GEML files, bad writes refused.

Pre-action gates that block AI agents from repeating known mistakes.

Governance-grade knowledge-base format (OKF-compatible) plus CLI and single-writer MCP server

Agent memory: working, episodic, semantic, procedural and core layers. Local SQLite, no account.

Hierarchical memory for AI agents. Three-layer (buffer/working/core) with decay and promotion.

Hosted agent memory that learns from outcomes, with shared rooms. No key: mcp.mnemoverse.com/mcp

Local retrieval for AI agents: index code, docs, PDFs, data in SQLite; 24 parsers, served via MCP.

Search, chat, upload, and scrape a serverless RAGStack knowledge base on AWS.

Memory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.

Recall locally stored agent memories through an MCP-compatible host.

Temporal knowledge graph for codebases with constraint enforcement at the edit boundary.

Semantic knowledge engine for Obsidian with auto-classification and DAG hierarchy

Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.

Four-tier memory (episodic, semantic, project, procedural) with temporal scoring, contradiction detection, entity tracking and a desktop…

Store and retrieve conversation memories from multiple LLMs in MongoDB, with timestamps and LLM identification.

Search, read, and edit any MediaWiki wiki. Works with Wikipedia, Fandom, and more.

Persistent memory for coding agents storing architecture decisions, bug root causes and conventions, with full-text search and…

Cognitive memory engine with knowledge modules, circadian rhythm awareness, emotional state tracking, hybrid PostgreSQL/Qdrant search and…