"Understanding Persistent Memory and Context Management" matching MCP servers:

A lightweight memory layer for MCP servers that persists user context across LLM sessions with minimal token cost, supporting key-value dedup, multi-tenant namespaces, and optional TTL.

Gives Claude Code long-term memory that persists across sessions via hybrid BM25 and vector semantic search, with multi-project isolation.

A local semantic memory and code-indexer that uses AST parsing for structural understanding and persists architectural decisions to help AI assistants bypass context window limits.

Saves the user's exact words as immutable, SHA-256-hashed captures before anything else, then derives events, entities, context cards, and causal hypotheses — every fact traceable to its verbatim source. Local-first personal memory for Claude Code, Codex, and any MCP client.

Enables AI agents to maintain persistent, inspectable understanding through typed, revisable updates, and to coordinate multi-agent work via shared graph-based stigmergy.

A local-first MCP server that gives AI coding assistants persistent, structured, human-readable memory for a software project by storing project knowledge as Markdown files in the project's .dev-context-memory/ folder.

Enables local video inspection and offline transcription with timestamped JSON and Markdown output, enforced filesystem boundaries, and reproducible content-addressed caching.

Enables AI assistants to execute shell commands and manage long-running processes within persistent tmux sessions across isolated workspaces. It features a dual-window architecture to separate raw command execution from interactive terminal output.

Tracks mistakes and solutions from past Claude sessions to avoid repeating failed approaches.

A local-first MCP server providing persistent, searchable knowledge base via SQLite, enabling AI agents to save and recall facts across sessions without cloud dependencies.

Enables AI agents to maintain a structured Markdown or Obsidian memory vault with tools for reading, writing, searching, and organizing notes.

Creates and maintains a semantic knowledge graph of code that allows maintaining context across sessions with Claude, providing advanced search capabilities without requiring the entire codebase in the context window.

Slipstream - Built by Vektor Memory - a persistent multi-layered memory architecture. 4-layer associative graph memory (MAGMA) with autonomous REM cycle, CLI, DXT-MCP Cloak Tools.

A local, read-only MCP server (plus CLI) over your own stock/ETF transaction log. A deterministic core computes drawdown-first risk with bootstrap confidence intervals and validates targets with walk-forward verdicts. The assistant narrates, but the number fence makes it structurally impossible for the model to produce a figure.

Provides persistent memory and a codebase knowledge graph for AI coding assistants, enabling shared context across multiple tools like Claude, Cursor, and ChatGPT, with significant token reduction.

Local stdio MCP server that provides tools for calculating averages, evaluating scores into grades, and retrieving student names by student ID. It logs every call to JSONL files with timestamps and performance metrics.

MCP server providing durable Substrate organizational memory tools, including search, read, query, ingest, remember, and sync. It integrates with Codex to automatically capture completed turns and session boundaries for persistent memory.

An open-source memory layer that provides persistent project context and architectural history for AI development tools across multiple platforms and sessions. It enables AI assistants to maintain a shared understanding of codebases while integrating directly with services like Notion for documentation management.

A lightweight MCP server for semantic search over markdown knowledge bases, enabling AI coding agents to index, search, and answer questions from local markdown documents.

Persistent memory for AI agents enabling saving, searching, and managing knowledge across sessions with local markdown files.