"Understanding Context Memory in Chat Systems" matching MCP servers:

A conversational chat interface that uses RAG over a synthetic test corpus and a domain-knowledge corpus, exposing retrieval via MCP.

Local-first MCP server for long-term memory of dev sessions. It indexes session metadata with embeddings in Postgres/pgvector, enables semantic search over past sessions, and resolves only relevant session files for context.

Claude Context is an MCP plugin that adds semantic code search to Claude Code and other AI coding agents, giving them deep context from your entire codebase.

Enables Claude to index and retrieve context from codebases using self-hosted Milvus for semantic search, with hardened reliability and security for production use.

Context Portal (ConPort): A memory bank MCP server building a project-specific knowledge graph to supercharge AI assistants. Enables powerful Retrieval Augmented Generation (RAG) for context-aware development in your IDE.

Enables AI coding assistants to automatically scan, store, and query API endpoints from codebases, providing instant lookup and semantic search to reduce context switching and token consumption.

Enables personal memory management through tools to find people, get profiles, remember notes, and perform semantic search, integrated with Claude via SSE.

Personal memory service using semantic vector retrieval and knowledge graphs to persist long-term context, supporting memory evolution and conflict labeling for the same entity.

Facilitates semantic analysis of chat conversations through vector embeddings and knowledge graphs, offering tools for semantic search, concept extraction, and conversation pattern analysis.

Enables AI agents to use a neuro-symbolic memory fabric with bi-temporal knowledge graph and holographic VSA, providing tools for adding, searching, temporal queries, auditing, and proving memories with cryptographic provenance and zero-LLM ingest.

Multi-modal RAG engine for AI assistants. Stores conversation history, conclusions, diffs, error traces, and other development artifacts in LanceDB with vector search, multi-factor scoring, and an LLM-driven consolidation pipeline.

Embedded, local-first agent memory: facts extracted into a per-namespace SQLite file (vec0 + FTS5) with hybrid retrieval and point-in-time (time-travel) queries. ADD-only history over stdio — no server process, no cloud dependency.

Provides persistent memory for AI agents using hybrid search (vector embeddings + BM25) with neural reranking, enabling storage and retrieval of insights, debugging solutions, and patterns across coding sessions.

Enables AI agents to parse PDFs and search local document context through multimodal extraction and vector-based retrieval, all exposed as MCP tools.

Provides AI agents with persistent, searchable memory using semantic search, auto-linking, and categorization, with zero-config local setup or production-ready external providers.

Enables AI agents to maintain long-term, cross-session memory by extracting facts, reconciling state conflicts, and retrieving relevant memories via vector search.

Enhanced MCP knowledge graph memory server with cloud persistence and semantic search, acting as a drop-in replacement for the standard memory server.

Enables Claude Desktop and compatible agents to search, read, add, update, and delete a locally stored, user-curated memory using hybrid retrieval with reranking and Qdrant. All processing runs locally without cloud services or API keys.

Local-first memory for Claude Code and any MCP client: hybrid vector + keyword search and a bi-temporal knowledge graph in one SQLite file. Local embeddings, no API key, $0/token.

Enables persistent memory management with semantic vector recall, BM25 keyword search, and 3-way fused retrieval combining lexical, semantic, and tag-based signals.