Always-on listening app that turns your day into a private, searchable memory and serves it to Claude, Codex or Cursor over MCP.
Agent Memory
Persistent recall for AI assistants, so preferences, decisions and past sessions survive the context window.
20 apps, 2 skills and 5 MCP servers tagged Agent Memory.
Apps
Cloud AI employee with its own Linux desktop that runs multi-step work across Gmail, Notion, Linear, GitHub and Slack.
Open-source desktop AI agent that builds a local, readable memory of your work, then orchestrates agent fleets and durable workflows on top of it.
Native macOS harness for AI agents — any model, persistent memory, sandboxed execution and cryptographic identity, fully offline and open source.
A single platform for building internal AI agents and multi-step agent systems, with memory, sandboxed compute, durable workflows, human approvals and 1,000+ integrations.
Voice-first personal AI agents with continuous memory across voice and text — four distinct personalities, ultra-low latency, free on iOS.
Local, 24/7 screen and audio recorder that turns your work into searchable memory for AI agents.
Local-first memory hub that reads your existing AI chat history and gives every agent you use the same long-term context.
Memwyre is a memory layer for AI assistants. It stores context in one place and makes it available across ChatGPT, Claude and other tools through a Chrome extension and MCP.
Turn a Postgres database into working memory for AI agents — relational rows, graph traversal and vector search fused into one ranked, token-budgeted context block.
AI-native CRM that keeps a versioned memory of every customer and runs agents that update records, prep meetings and build pipeline.
A shared channel workspace where people and AI agents run recurring business work together — with goals, approvals and handoffs that survive a pause.
MIT-licensed multi-agent harness that turns the CLI coding agent you already use into a persistent clone of yourself, running around the clock.
A shared memory layer for AI coding tools — tell Claude Code something once and Cursor, Codex and Claude Desktop already know it.
MCP-native context layer that syncs one self-updating memory across Claude, ChatGPT, Cursor, and the tools you already work in.
Open-source, repo-native project memory for coding agents, stored as plain Markdown.
A memory layer for AI agents — remember user preferences and past interactions without stuffing the context window.
The multi-agent framework where agents have roles and collaborate as a crew — plus a platform to run them in production.
Build a team of specialist AI agents — recruit, brief, and manage them like staff, with no code required.
An AI coworker that lives in your Slack — one teammate per channel, each with its own memory, tools, and approval rules.
Skills
Persistent cross-session memory for coding agents: hooks capture each session, a local SQLite + vector store compresses it, and a mem-search skill reads it back.
Skill: VoltAgent Best Practices
by VoltAgent
VoltAgent's official conventions skill — when to reach for an agent versus a workflow, the expected project layout, and the core snippets for agents, workflows, memory and servers.
MCP servers
Persistent memory for coding agents as a single Go binary — SQLite and FTS5 behind MCP, an HTTP API, a CLI and a TUI, with no Node, Python or Docker required.
Git-native persistent memory for coding agents — sub-300µs BM25 search over version-controlled plain text, with no embeddings, no database and no API costs.
MCP: agentmemory
by rohitg00
Self-hosted persistent memory for coding agents: hooks capture what you do, and an MCP server lets any agent recall it across sessions and across tools.
MCP: Dense-Mem
by markhuangai
Self-hosted agent memory server on Postgres/pgvector that tracks evidence, flags contradictions, and never silently rewrites facts.
MCP: Memory
by Model Context Protocol
A knowledge-graph-based persistent memory system that lets an agent remember entities and relations across sessions.
Related tags
Tags that appear alongside this one, ranked by how often.