Memory MCP servers

NVIDIA GPU metrics as MCP tools — utilization, memory, temperature, power. Supports MIG.

MAMA MCP Server - Memory-Augmented MCP Assistant for Claude Code & Desktop

Local deterministic knowledge graph on redb with no LLM or embedding calls, BLAKE3 state hashing and canonical export for byte-identical audits.

Lightweight MCP for infinite agent memory. Any agent, any session, anytime.

Markdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.

Persistent memory for AI assistants with semantic search and knowledge graph relationships.

PMLL Memory MCP — persistent KV context memory and Q-promise deduplication.

Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.

Local-first memory for coding agents: hybrid vector/BM25 retrieval with reranking, knowledge graph, session checkpoint/resume and multi-scope isolation.

Portable, project-scoped memory and session handoffs for coding agents. Readable files, MCP recall, and optional user-passphrase encrypted backups.

iOS memory leak and performance investigation: reads .memgraph and .trace files, classifies retain cycles against known patterns and suggests Swift fixes.

Behavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex.

Local semantic search and RAG over Apple Notes with on-device embeddings, full CRUD, folder management and fuzzy title matching.

Self-hosted memory for agent teams. Bi-temporal replay, deterministic retrieval, audit log.

Shared, project-aware memory for Claude Code, Codex, and other agents with human review.

Local multi-repo code graph over MCP. Blast radius, call graphs, and memory anchored to code.

Persistent local AI memory. SQLite + FTS5 + vector search, knowledge graph. No cloud, no API keys.

Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.

Task queue, decisions and memory for coding agents. Local SQLite, no network. Requires Bun.

Git-native project memory for coding agents: Markdown in your repo, reviewable staged updates, secret/PII-safe and branch-aware, without cloud or vector DB.

Local grounded memory for coding agents: MCP over stdio, stdlib only, a verdict per answer

Hebbian memory for AI agents. Learns file patterns, predicts next tools, saves tokens.

Five-level AI collaboration system with persistent local-first memory via MemDocs and anticipatory capabilities.

Local-first knowledge engine for AI agents: memory, graph, and recall over MCP.

Local adaptive memory for AI coding agents through a five-tool MCP lifecycle.

MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.

Pull Deep Memory from across your Claude Code Sessions — when you need it.

Semantic search over CS and AI papers with citation-graph traversal, full-text extraction, embeddings and BibTeX export.

Watches git repos and builds a temporal knowledge graph of modules, symbols, decisions and open problems via Graphiti and Neo4j, served to AI coding agents.

XMemo: user-owned agent memory to save, search, recall and manage scoped memories across AI tools.

Local-first persistent memory for AI coding agents - 96.0% R@5 on LongMemEval, zero LLM calls.

Search Google's Knowledge Graph for structured information about real-world entities

Persistent memory for AI assistants: store, search, and connect knowledge across conversations.

Protected RAG storage — agents discover public metadata, content only by access token.

Persistent memory with SQLite hybrid search (FTS5 and semantic), built-in Qwen3 embeddings and rclone sync across machines.

Persistent AI memory with hybrid search and embedded sync. Open, free, unlimited.

Local-first, source-cited memory for AI agents with proposal review, failure memory, and MCP tools.

Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.

Code-pinned team memory for AI coding agents — typed artifacts, MCP-native, self-host.

Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM

Codebase memory for coding agents: a deterministic AST index finds task-relevant files, and in-repo Markdown notes flag themselves stale when code changes.

Agent runtime with typed memory, knowledge and code graphs, plus file and web tools

Two-layer memory for AI agents with an immune system. Zero dependencies.

Local-first, read-only MCP server for evidence-backed repository memory.

Persistent identity for AI agents: servers for drives, relationships, semantic memory with decay, working threads, learned patterns, journaling and forecasting.

Local-first persistent session memory for Claude Code and other agents. SQLite + FTS5, no cloud.

AI memory system for coding agents. Local-first MCP runtime with connectors (Google Drive, GitHub, Slack, Notion), knowledge graphs, decay scoring, and multi-tier deployment. Free locally, paid Cloud for sync and teams.

Lightning-fast RAG for AI agents. 4-layer fusion, ONNX Runtime, sub-200ms search.