Durable Storage for Agent-Prepared Memory

Readable files for agents, searchable records for retrieval.

The host agent decides what memory or skill Markdown to preserve. memU stores those recall files, creates searchable segments and embeddings, and keeps workspace resource records in one shared Cloud or self-hosted backend.

Install memU

The Current Storage Model

Recall Files

Readable Markdown with a name, description, content, and either a memory or skill track.

Searchable Segments

Recall files are represented by searchable text slices whose embeddings are used during retrieval.

Workspace Resources

Resource records preserve a workspace path, description, track, and embedding so relevant workspace context can be found.

Explicit Scope

Records are stored inside the configured user and agent scope rather than an inferred category hierarchy.

Choose the Backend That Fits

Every connected host uses the same memory operations. Only the configured storage backend changes.

memU Cloud

A managed, cross-device backend configured with the API key provided by memu.so.

SQLite

The local default for a private, single-device installation and a single writer.

Postgres + pgvector

A self-hosted option for concurrent access and larger stores.

In-Memory

A lightweight backend for tests and disposable sessions.

What Storage Enables

Session Continuity

Useful context survives after an individual agent session ends.

Cross-Agent Reuse

Multiple configured hosts can retrieve from the same backend and scope.

Inspectable Memory

Recall file content remains readable instead of existing only as embedding vectors.

Pluggable Infrastructure

Move from local SQLite to Postgres or Cloud without changing the host-agent workflow.

Ready to Unlock the Full Potential of AI Memory?

Memory Storage

Store readable memory and skill files with searchable segments in a shared Cloud, SQLite, or Postgres backend.

Now Here

Memory Retrieval

Embed a query once, rank relevant file segments and workspace resources, then return the complete readable files to the agent.

Explore Memory Retrieval

Automatic Skill Extraction

Let the agent turn useful session history into reusable Markdown skills, then index those skills for future tasks.

Explore Skill Extraction

Cross-Agent Memory

Connect multiple host adapters to one configured backend so skills learned in one agent can be retrieved by another.

Explore Cross-Agent Memory

Agent-Driven Memory

Keep judgment and synthesis inside the agent while memU handles durable storage, embeddings, and retrieval.

Explore Agent-Driven Memory

Readable Markdown

Give agents inspectable memory and skill files instead of hiding all useful context inside opaque vector records.

Explore Markdown Memory

Coding Skills

Capture coding sessions and compound successful workflows, debugging lessons, and project conventions into reusable skills.

Explore Coding Skills

Open Source

Inspect the lightweight Python implementation, run locally, and adapt host integrations for the agents you already use.

Explore Open Source

Connect Your Agents to memU

Cloud Platform

Get a memU Cloud key, then give the installation prompt to your agent. The skill configures its host adapter against one managed, cross-device memory backend.

Get the Install Prompt

Self-Hosted Open Source

Ask your agent to follow the open-source SKILL.md. It installs the CLI, configures SQLite or Postgres and an embedding provider, then verifies retrieval with the host adapter.

View SKILL.md

Add Another Agent

Run the installation skill in each additional host. Every configured adapter can record its own sessions and retrieve from the same shared backend.

See Host Adapters

FAQ

memU is a lightweight, agent-driven memory system for the agents you already use. It gives connected agents one shared, inspectable memory layer across sessions, agents, and devices.

The memU installation skill configures a host adapter for your agent. A scheduled task captures new session history, the agent decides what memory or skill Markdown to write, and the adapter retrieves relevant files before future tasks. Users do not need to integrate a public memory API.

No. memU's memory service makes no LLM or chat calls. Judgment and synthesis remain inside the host agent; memU stores the Markdown it prepared, creates embeddings, and retrieves relevant files.

The query is embedded once. memU ranks searchable file segments and workspace resources by vector similarity, rolls matching segments up to their complete recall files, and returns segments, files, and resources without an LLM in the retrieval path.

memU includes dedicated adapters for Codex, Claude Code, Cursor, OpenClaw, Hermes, and WorkBuddy. A generic adapter can detect compatible session logs and instruction files for other agents.

Host adapters use the same configured Cloud or local backend. When they use the same memory scope, a skill learned from one host's sessions can be retrieved by another connected host.

Yes. The self-hosted mode supports SQLite for local use and Postgres with pgvector for larger or concurrent stores. Local mode requires a configured embedding provider. memU Cloud provides a managed, cross-device backend.

Yes. The Python package, CLI, host adapters, and core memory service are available on GitHub under the Apache-2.0 license.

Keep Agent Memory in One Shared Backend

Choose Cloud or self-hosted storage, then connect each agent through its host adapter.

Install memU