Memory MCP servers

Durable, build-scoped reverse-engineering evidence memory and query tools for AI agents.

Persistent memory for AI agents: Markdown entries, hybrid search, typed graph links

Java profiling with AI agent integration. Profile CPU, memory, JDBC, HTTP and more.

Local encrypted memory for AI: hybrid search, 8 MCP tools, one file you own. Free, no cloud.

Graph-native memory for AI agents: a knowledge graph built from conversation, via MCP.

Safety-first context & orchestration engine for AI coding agents. MCP server with mandatory research pipeline, knowledge graph, impact analysis, decision memory, and safety guard — works with any MCP client.

Persistent memory for AI coding agents: one Rust binary, one local SQLite database.

Linux MCP server for real-time system monitoring - CPU, memory, disk, network, processes, Docker.

An MCP memory server. One memory your agents share — across models, devices and apps.

Encrypted local memory for Claude Code Telegram bots: captures both sides of conversations, with SQLCipher encryption and CJK-friendly full-text search.

An MCP server that provides persistent memory and context management across sessions

Local-first memory for coding agents: stores facts, decisions, patterns and architecture notes in SQLite to reduce repeated context across sessions.

Memori MCP server — persistent AI memory with recall and augmentation tools

SQLite-based memory with exponential decay: memories strengthen on access and fade when unused, limiting unbounded context growth.

File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.

Local-first memory, hybrid RAG, and agent personalization for AI coding agents (OpenCode, Claude Code, Codex, Gemini CLI, Antigravity). MCP server + CLI with persistent context, document ingestion, vector + SQLite FTS5 retrieval, sync, setup, and safe uni

Local-first agent memory: versioned JSON categories, BM25 search, per-device ACL, fleet sync.

Cross-client AI memory hub: agents share one SQLite memory.db via file-level pointers.

Independent, reproducible benchmark harness for agent-memory backends.

Universal persistent memory and knowledge retrieval layer for AI agents and LLMs.

Governed tacit memory for AI agents: reviewed expert know-how, given only where conditions match

Event-sourced knowledge graph memory for AI coding agents with semantic search

Structured bug-fix analysis and project-local memory of verified fixes for coding agents.

Procedure verification for AR/XR with memory, visual sessions, and DPO trajectory export.

Local-first memory brain for AI coding agents: hooks capture sessions, beliefs injected per prompt.

AI-native runtime with built-in MCP server. 232 builtins, AI pipelines, RAG, single ~8 MB binary.

AI memory across Claude, ChatGPT, Gemini, and Cursor. Save, search, and recall context everywhere.

Local knowledge graph memory for agents. SHACL rules refuse bad facts; SPARQL and time travel.

Add RAG-based AI chat to any website: local vector store, OpenAI, Anthropic or Gemini models, a self-contained chat server and an embeddable widget.

Graph memory for AI agents: entities, cause-effect links, cross-session recall, time travel.

Read-first Redis MCP: SCAN key explorer, keyspace/TTL/memory/slowlog stats, DBA advisor

Flight recorder for RAG retrieval: logs chunks, scores, sources and rankings to audit, replay and diff retrieval runs.

Read/write access to your Filamental knowledge graph vault. 17 tools. Local-first, no auth.

Real-time NSE/BSE stock sentiment, news NLP, technical analysis & RAG search via MCP.

GDB/SWD MCP server over a smolmux broker: breakpoints, memory, Cortex-M fault decode, board probing.

Lossless, project-scoped memory for AI coding tools. Durable context across sessions with MCP tools, FTS5 search, cloud sync, trace optimization, Claude/Codex/OpenCode/Gemini wrappers, skill packs, and automatic hooks.

Universal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support.

Memory for coding agents: the decisions, the dead ends, and where the last session stopped.

A collaborative substrate over your data: vector, knowledge graph, SQL, geospatial, streaming.

Typed record store + hybrid search over MCP: deterministic lookups + semantic memory, per-customer.

Persistent memory layer for AI coding agents — your agent remembers what you taught it.

Indexes codebase into a local knowledge graph with 40+ AI tools and codebase-guard.

Shared memory for coding agents: projects, reusable code, sessions and commits across machines

Deterministic multi-hop graph retrieval for RAG. Zero LLM calls in the query path.

Neo4j-native DIKW memory for Claude Code — knowledge that compounds across sessions

Persistent project memory for AI coding agents: one compact digest instead of re-reading the repo.

Local Redis memory MCP for AI apps with hybrid caching and optional Mem0 cloud backup.

Embedded, local-first memory and retrieval for AI agents. One SQLite file, no server, no API key.