Memory MCP servers

Windows x64dbg/x32dbg debugging with guarded sessions, breakpoints, memory and runtime evidence.

Deterministic code map for AI coding agents: a tree-sitter symbol and call graph served over MCP and a CLI, with no embeddings, network or telemetry.

Client-side encrypted agent memory where the server only sees ciphertext, with post-quantum identity and sharing and crypto-shredding for GDPR erasure.

Markdown memory for AI agents. Files you can read, edit, grep, and commit. Not a database.

Read, cite, compose and remember over a Markdown knowledge Bundle, as MCP tools over stdio.

ZeroDB agent-memory MCP — 18 tools: memory + write-back to Slack, Gmail, Calendar, GitHub.

Personality runtime for agents: persistent memory, identity (SOUL) and relationships that carry across AI clients.

Hosted agent memory with an audit trail: writes carry provenance, contradictions surface as inspectable changes, and bad runs are recovered from snapshots.

View and query your AI system (agents, memory, knowledge, automations) as a 3D knowledge graph: stats, search, node details, neighbors and pathfinding.

Personal memory for Claude Code in plain Markdown notes, with a router note that decides what context to load and a layer for thoughts and feelings.

Claude Code session handoffs: turns any transcript, even crashed ones, into a handoff file and distills project history into a cited memory brief.

Session memory with tiered storage, context health monitoring, reasoning quality checks and truthfulness verification.

Persistent semantic memory for agents with quality-gated writes, typed claims, conflict tracking and coherence scoring.

Generate vector embeddings for semantic search and RAG with Forge, Voxell's text-embedding API, including Matryoshka truncation.

Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.

Local memory shared by all coding agents on a machine, built from sessions, commits, CLAUDE.md/AGENTS.md and ADRs, with claims that lock in-progress work.

Structured memory for coding agents: typed lore and doc entries with status and links that agents read and write.

Local-first chronological memory: write dated, editable memory banks in a local UI, and Claude recalls them on demand via SQLite FTS5.

MCP server for local markdown notes — ranked search, tags, todos, and a wiki-link knowledge graph, from any MCP client.

Read-only queries of the NOVAI layer-1 blockchain: blocks, transactions, AI entities, on-chain signals, oracle anchors and memory objects.

Persistent memory for coding agents in plain repo files (AGENTS.md, issues.jsonl): captures bugs, fixes, decisions and corrections and recalls them later.

Persistent coding memory for AI assistants with hybrid search, a knowledge graph and token-efficient context, self-hostable on D1, Postgres, MariaDB or Docker.

Shared, git-tracked memory for AI agents on the same codebase: facts, decisions and gotchas stored in a committed repo directory and synced via git.

Google SERP search via the Ace Data Cloud API: web, image, news, maps, places, video and knowledge graph results.

Local-first shared team memory for coding agents: decisions, fixes and gotchas persist per repo and are shared across teammates' agents.

Read Markdown with inlined images and heading indexes for agentic RAG over local docs or allowed URLs.

Persistent agent memory with semantic search and recency decay, local ONNX embeddings, background summarization and Prometheus/Grafana observability.

Git-aware memory store for coding agents: memories anchored to git blob hashes are flagged for review when the linked code changes.

Connect agents to 6DuckLearn memory, approvals, and runtime control.

AI Mind Map — MCP server that reduces AI coding agent token usage by 80-99% through persistent codebase memory, knowledge graphs, and intelligent context management

Nostalgic food memory reconstruction MCP server — recreates childhood dishes using ingredients available where you are

Shared memory and delegation for Codex, Cursor, Claude Code, and OpenCode.

Local-first persistent memory MCP server for AI coding agents.

Persistent memory for AI agents — history, context, semantic search, queues. 46 tools, stdio/SSE.

Persistent, verified memory for AI coding agents: recall, capture, guardrails, review queue.

Local, dependency-free memory server shipped as a single binary.

AI NPCs with persistent memory for game studios. NPC CRUD, dialogue, voice. Stdio or remote SSE.

Long-term memory for AI assistants. Hybrid retrieval, query expansion, auto-topics.

Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth

Tamper-evident memory + governance MCP for Claude Code, Cursor, Codex. Ships the Seatbelt kit.

Adaptive error memory and code intelligence system with Hebbian synapse network, hybrid search, and REST API

Local-first, governable long-term memory for AI coding agents

Clarity and memory persistent workspace context manager for Claude.

🎭 Claude Opera by VERSATIL v6.4.0 - Production-ready OPERA orchestration with 17 agents (7 core + 10 language-specific sub-agents), automatic roadmap generation, 11-MCP ecosystem, RAG memory achieving 98%+ context retention, proactive daemon with file-ba

Memlink — MCP server for persistent AI agent memory. Self-hosted, one URL, no cloud.

Session memory for AI coding agents: records decisions and dead ends, flags what went stale.

28-layer cognitive substrate with cross-session ToT evolutionary memory and self-telemetry tools

Six pure, in-memory CSS color tools: parse, convert, WCAG/APCA contrast, gamut map, ramps, solver