Memory MCP servers

Knowledge graph-based persistent memory for maintaining context.

Hindsight: long-term memory for AI agents modeled on human memory.

Indexes a repo into a persistent local knowledge graph of functions, classes, call chains, HTTP routes and cross-service links, using tree-sitter and LSP.

Memory manager for AI apps and agents using graph and vector stores, with ingestion from many data sources.

Memory that reasons: continual learning for stateful agents. Better context, fewer tokens.

Local-first AI memory: a semantic knowledge graph of Markdown files that humans and LLMs both read and write, with optional cloud sync and team workspaces.

Butterbase MCP server — manage your backend: schemas, auth, functions, storage, RAG, deploys.

MCP server for Memanto - persistent semantic memory for any MCP-compatible agent

Task management for coding agents with task memory, self-reflection and dependency management.

Memory service with semantic search, persistent storage and autonomous memory consolidation.

Markdown knowledge base as agent memory. Runs against the notes directory it is started in.

Implement semantic memory layer on top of the Qdrant vector search engine

The private, owned conversation-memory layer for AI. Record, transcribe, and search every meeting.

Layered memory for AI trading agents (trades, patterns, strategy), supporting MT5, Binance and Alpaca.

Local-first personal memory and model server for trusted MCP agents on macOS.

RAG platform combining Graph RAG, vector search and full-text search for building knowledge graphs and context engineering.

Framework for building multi-agent systems that coordinate over MCP, with task management, shared context and RAG.

Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.

Local memory over session histories from Claude Code, Codex CLI and opencode: lexical search, session-start auto-recall, secret redaction and SSH sync.

Local RAG (on-premises) with MCP server.

Neo4j integration: run queries, use Neo4j as knowledge graph memory and manage Neo4j Aura instances.

Local memory daemon with episodic, semantic and procedural tiers, SQLite and hnswlib storage, sleep-cycle consolidation and AES-256-GCM encryption at rest.

Local-first shared memory layer for AI coding agents across MCP clients, Git history, reasoning context, and project sessions.

Production-ready AI agent orchestration platform with 66 specialized agents, 213 MCP tools, ReasoningBank learning memory, quantum-resistant Jujutsu VCS, and autonomous multi-agent swarms. Built by @ruvnet with Claude Agent SDK, neural networks, memory pe

The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches

Production-ready AI agent orchestration platform with 66 specialized agents, 213 MCP tools, ReasoningBank learning memory, and autonomous multi-agent swarms. Built by @ruvnet with Claude Agent SDK, neural networks, memory persistence, GitHub integration,

Persistent memory with knowledge graph visualization, semantic/hybrid search, cloud sync (S3/R2) and cross-session context management.

Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval

Embeddings, vector search, document storage, and full-text search with the open-source AI application database

Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.

Failure-memory layer for coding agents: search evidence-rated failure lessons by error text.

Mem0-compatible long-term and multimodal agent memory: character-isolated profiles, semantic deduplication, optional local stack and video memory with QA.

Semantic code indexer with a GraphRAG knowledge graph: index a codebase and search it in natural language to understand its architecture.

Persistent agent memory as a single Go binary: knowledge graph, TUI observability, zero infra.

Context control layer for coding agents: compression, prompt-prefix stabilization for caching, cheaper-model routing, local hallucination checks and memory.

Team knowledge base turning Slack, Discord, Teams and Mattermost chats into a knowledge graph and wiki with cited answers, semantic search and expert finding.

Universal MCP Server with advanced AI memory capabilities and semantic search.

Local document search: semantic search over PDF, DOCX, TXT and Markdown files with LanceDB vector storage and local embeddings.

Reasoning-based RAG system for chatting with long PDFs. Supports local and online files.

Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.

Persistent cross-session agent memory that surfaces the most relevant past memories using the Intelligent Distance Protocol.

Graph-based memory focused on AI role-play and story generation.

Cognitive architecture for persistent AI agent memory. Knowledge graph with learning retrieval, ACT-R decay, and spreading activation. Markdown-native, local-first, zero cloud. MCP server + CLI.

Citation-guarded retrieval over 22M Taiwan court judgments and administrative interpretations

Cognitive agent memory with Hebbian learning, a three-tier architecture and knowledge graphs, running offline on edge devices.

Open, local-first engram memory for AI agents: read, correct, delete; shared over MCP.

Web, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.

Offline RAG for Claude Code with hybrid BM25 and semantic search, cross-encoder reranking, Markdown-aware chunking and query expansion.