Apps with 'AI Memory' feature Page 2 of 2

Always sync your info on all your devices, just like your info flows around you.

EchoStream is a local AI Agent designed to run directly on your iPhone. It includes a built-in thinking model that helps you do more with less effort.

LangGraph for Swift — build stateful AI agent workflows natively on Apple/Linux platforms.

Build, ship, and operate AI agents on infrastructure you own. Apache 2.0. Self-hostable in one docker compose up.

Keep your work in flow across all AI chat agents. Save context once and reuse it on ChatGPT, Claude, Gemini, Perplexity, and more to get faster results without repeating yourself.

ChainMemory gives AI agents persistent memory that belongs to the user, not the vendor. Save a memory in ChatGPT and recall it in Claude, Gemini, Perplexity or Copilot via Chrome extension, MCP server, or REST API.

Alook is where people and AI agents share the same rooms. Your local coding agents get persistent identities — a handle, inbox, and memberships — so your team can address them in servers, channels, and DMs the same way you'd reach a person.

Open-source, self-hosted memory for AI agents built on belief revision. Keeps both sides of a contradiction instead of overwriting, tracks what was believed and when, answers why with a provenance chain, and gates risky actions behind human approval. MIT, pip install, dashboard included.

Maximem Synap is a managed long-term memory layer for AI agents. It stores what an agent learns across sessions and returns the relevant parts at inference time, instead of re-sending an entire conversation history into the context window.

OzBrain is a shared brain every AI agent you use can read and write. One structured source of truth across Claude, ChatGPT, Cursor, and coding agents.

Give your AI a soul

Alma is a persistent memory layer for AI. Your conversations build knowledge over time — preferences, facts, decisions, patterns. Every interaction makes your AI smarter, more personal, more yours.

Lians is an open-source memory and decision-evidence layer for AI agents. It lets agents remember facts, recall current information, reconstruct what was known at a past point in time, inspect conflicts and lineage, and delete or export stored memory.

Platform for building stateful AI agents with long-term memory that learn and self-improve over time, from the creators of MemGPT.

DoneThat automatically tracks all work and uses this context to boost your productivity: Automated timesheets, long-term memory for AIs, proactive coaching, and social sharing for accountability and remote trust.

Open source Python framework for building real-time, temporally aware knowledge graphs for AI agents, so they can track facts and how those facts change over time.

Hosted semantic memory for AI assistants over MCP, with a quality gate that rejects redundant writes instead of storing everything.

Memory API and context engine for AI applications that stores knowledge from conversations, documents and connected apps, and retrieves it with low-latency hybrid search.

A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs, and speculative context pre assembly. Not a wrapper, a ground up storage engine that thinks.