"memory" matching MCP servers:

A memory server that manages a knowledge graph with entities and relations, supports internet search via DuckDuckGo, and stores dialogue history, enabling persistent memory and web interaction for AI assistants.

A lightweight, stateless MCP server utilizing Puppeteer for web searches, returning structured JSON results, easily integratable with other MCP-enabled systems.

Open-source MCP server exposing the Agent402.Tools catalog: 500+ pay-per-call tools for AI agents, including browser rendering, web search, PDFs, OCR, LLM inference, code execution, live financial/crypto/macro data, SEC EDGAR, and wallet-keyed memory. Free via proof-of-work, or pay per call in USDC across ten chains via the x402 protocol. No API keys, no signups

An all-in-one MCP server for local LLMs that provides live web access, math, shell/code execution, filesystem access, memory, and RAG over local files using LM Studio embeddings.

MCP server providing browser automation for AI agents, enabling actions like clicking and typing, structured data extraction, content validation, multi-step task execution, and memory enrichment from web pages.

Enables agents to search and deduplicate UK job vacancies across multiple boards, match them against local CVs, and submit complete applications through an automated browser with persistent logins and application memory.

AgisHub provides a diverse set of pay-per-call tools for AI agents—covering timezones, web extraction, AI, memory, webhooks, finance, and utilities—accessible via a free MCP tier or x402 HTTP micropayments in USDC on Base, with no signup or API keys required.

This MCP server enables AI agents to perform exploratory UI testing of live web apps by providing a structured view of page elements, deterministic correctness oracles, enforced read-only or opt-in write policies, persistent cross-run memory, and gap-checked coverage reports.

Enables AI agents to access pay-per-call web unlocking, structured extraction, clean scraping, Python sandbox execution, persistent key-value memory, and clearinghouse task bounties, with settlement via Bitcoin Lightning L402 or Base/Solana USDC x402.

Serves as a machine perception and action hub, enabling heartbeat monitoring, screen/window/clipboard sensing, todo management, long-term memory, and web/file operations through both CLI and MCP interfaces.

Enables browser automation and API testing for AI agents using Playwright and Chrome DevTools Protocol, with numbered element references, Set-of-Mark screenshots, flow recording/replay, element memory, captcha handoff, and HTTP API test suites.

An MCP server based on Puppeteer and Chrome DevTools Protocol for advanced browser debugging, performance analysis, and memory detection. It enables users to inspect DOM elements, monitor console errors, capture screenshots, and perform heap snapshot analysis through persistent browser connections.

A Chrome DevTools Protocol MCP server that enables direct browser automation with auto-discovery of interactive elements, built-in action verification, and persistent site memory across sessions.

Gives browser agents a reviewed map of 79 real sites — entry URLs, access verdicts, and role/accessible-name button maps for 104 screens — so an agent can find where things are and know whether it may act at all. Safety rules in code halt irreversible actions such as pay, order, submit and delete pending explicit human approval, while per-site memory recalls which routes worked last time.

MCP server that enables AI agents to drive your real, logged-in browser via accessibility snapshots, with hardened credential brokering and local workflow memory.

Enables persistent agent identity, memory, and tools for Claude Code, including messaging, timers, and browser automation.

Browser automation MCP server with persistent memory for AI assistants, enabling automated web testing and workflow replay with self-healing selectors.

He gives AI agents a browser with memory: they explore a website once, then replay the learned route in a single tool call with zero model calls, repairing individual steps when the site changes. It also keeps a per-site map of seen pages and controls, handles manual sign-in and multiple signed-in profiles, and lets agents on one machine share routes.

Gives AI agents a single shared, logged-in Chrome they can drive over MCP or plain HTTP: open and read tabs, click, type, upload files, run short Playwright scripts, hand off whole web tasks to a cheaper model, and keep per-site memory. Agents work in background windows they own without stealing the user's mouse or closing their tabs.

A local-first MCP server that lets any MCP agent drive a job-search cockpit: scan for roles, inspect and click/type in your real logged-in Chrome tabs via a built-in extension, capture postings, gate eligibility, pre-fill applications without ever submitting, record and replay browser workflows, and store local memory facts — all over loopback stdio with no API keys or cloud.