memU

Image: memU Banner

<div align="center">

memU

Personal memory, stored as Wiki

Across Sessions. Across Agents. Across Devices.

Image: PyPI version Image: License: Apache 2.0 Image: Python 3.11+ Image: Discord Image: Twitter

<a href="https://trendshift.io/repositories/17374" target="_blank"><img src="https://trendshift.io/api/badge/repositories/17374" alt="NevaMind-AI%2FmemU | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>

</div>

memU is a lightweight, agent-driven memory system that gives users a shared LLM wiki across sessions, agents, and devices. It automatically distills your own reusable skills from your agent history. Its core memory logic is only 500 lines — compact enough to inspect, understand, and adapt.

Quick start

memU works with Codex, Claude Code, Cursor, OpenClaw, Hermes, WorkBuddy, Cola, pi, and more. See Host adapters.

Cross-device · Free · Unlimited · View online

Get your API key from memu.so, then send this message to your agent:

Read https://memu.pro/SKILL.md, follow its instructions to install and configure memU, API Key is memu_•••••••••(get Api Key from memu.so).

Agent support

This matrix lists the currently tested memU integrations by operating system.

• Memorize — capture useful session knowledge through a scheduled background task and turn it into reusable memory.

• Retrieve — bring relevant memory into a future task.

• ⚠️ — supported with an important limitation; see the user note.

macOS

Windows

Linux

Support status reflects the current release and may change as host integrations evolve.

How it works

Image: memU memory system architecture

Automatic skill extraction

Once the scheduled bridging task is installed, memU can turn useful agent history into reusable Markdown skills automatically.

Image: How memU turns agent history into reusable skills

1. Capture new sessions. The host adapter reads new session history, including messages and tool calls.

2. Prepare self-evolve jobs. prepare slices each session into a self-contained job with the paths and context the agent needs.

3. Let the agent decide. The agent reads related existing skills, then chooses to do nothing, patch an existing skill, or create a new one.

4. Write readable skill Markdown. Each skill has a name, description, and reusable workflow, including useful branches, edge cases, and pitfalls.

5. Commit and index. commit submits changed skill files through commit_results; memU embeds the skill name and description and stores it under the skill track.

6. Retrieve it later. On a similar future task, memU returns the relevant skill so any connected agent can use the learned workflow.

The judgment and synthesis stay inside the agent. MemoryService makes no LLM or chat calls; it stores, embeds, and retrieves the skill Markdown the agent prepared.

Self-hosted

Private · Single-device · Embedding key required

To run memU locally with your own storage and embedding provider, send this message to your agent:

Read https://raw.githubusercontent.com/NevaMind-AI/MemU/main/SKILL.md and follow it to install memU.

Uninstall

To uninstall memU, send this message to your agent:

Read https://memu.pro/SKILL.md and follow its instructions to uninstall memU.

By default, uninstalling removes the host integration and tooling while keeping your memory store and ~/.memu/config.env, so a later reinstall can resume where you left off. Memory is erased only when you explicitly ask for it.

Host adapters: memory for desktop coding agents

memU runs as a sidecar to a desktop agent, one binary per host. Each binds two seams:

• record — a scheduled bridging task slices new session logs into self-contained job files; the agent itself distills them into memory/skill Markdown; commit submits whatever the agent left on disk back through commit_results.

• inject — a standing instruction in the host's instruction file tells the agent to run <binary> retrieve (→ progressive_retrieve) before answering.

For agents without a dedicated binary, memu-agent detect probes the machine and reports per agent whether memorization works (a recognizable session log exists) and whether retrieval works (an instruction file exists to patch) — then the same verbs run against what it found.

All hosts share one configured memory backend via ~/.memu/config.env — local or MemU Cloud. What one host's sessions taught memU, another host retrieves.

Installation is the one-message setup in Quick start or Self-hosted. SKILL.md is the routing skill it hands your agent: install the package, identify which host you are (falling back to memu-agent detect for anything without a dedicated adapter), print that host's packaged install guide (<binary> docs install), and follow it — configure the memory backend, register the scheduled bridging task, patch the instruction file, each step behind a verify gate — then report which seams (memorization / retrieval) are now active.

Afterwards <binary> doctor proves the whole loop resolves: config, selected mode, and a live retrieval.

Adding another host means implementing one TranscriptSource (where its session logs live, how its records are shaped) plus a HostSpec-sized CLI — the pipeline, verbs, and instruction text are shared.

Developer integration

Use memu memorize to turn application-owned conversations into memory and skills.

CLI

With memU Cloud, sign in at memu.so to view your memory files. With a local installation, memory lives in the shared store configured by MEMU_DB in ~/.memu/config.env — typically ~/.memu/memu.sqlite3 for local SQLite, or a Postgres DSN.

Once installed, your agent retrieves relevant memory automatically before answering. To retrieve manually, run the adapter for your host:

memu-codex retrieve "What should I remember about this project?"
# or: memu-claude-code / memu-cursor / memu-openclaw / memu-hermes / memu-workbuddy / memu-cola / memu-pi / memu-agent

For pi, run memu-pi install to configure the memory backend and install the extension, then run /reload or open a new session. Submitted prompts start retrieval in the background; results enter the model context and resume an idle agent. After the user turn and pending retrieval settle, a background worker processes the saved conversation into memory using the active session's model. Workers share a lock and a 30-minute cooldown. Long prompts use an isolated, tool-free pi request to extract a search query with the active provider/model; extraction has a 12-second timeout and falls back to the original prefix. The installer registers and verifies the extension. Run memu-pi uninstall and reload to remove it.

Host retrieval returns compact JSON with at most five self-contained hits plus independent resources. Each hit combines matched text with its source's description, track, and local mirror path (or inline content when no mirror is available). Its score describes the matched segment; created_at and updated_at describe the source file when available. Hits retain segment order, including excerpts whose source is missing; sources without matched excerpts remain source-only hits. Resources contain path, caption, and available scores/timestamps. Database IDs and scope metadata are omitted from the agent-facing output.

Install or invoke the CLI directly:

pip install memu-cli         # library + memu + memu-codex CLIs
npx memu-cli --help          # CLI via npm launcher (engine: PyPI package memu-cli)
uvx --from memu-cli memu     # CLI via uv, no install

Configuration

Values resolve in order: process env → ~/.memu/config.env → default. memU supports Local and Cloud memory backends, selected by MEMU_MEMORY_MODE; an unset mode remains Local for backward compatibility.

For Local / self-hosted installations, every CLI flag has a matching variable:

Run <binary> doctor to display the resolved mode and verify the same retrieval path the host uses.

Storage backends

service = MemoryService(
    database_config={"metadata_store": {"provider": "postgres", "dsn": "postgresql://..."}},
    embedding_profiles={"default": {"provider": "jina"}},
)

Community contributions

Explore the community tasks (English / 简体中文) and claim a task in issue #790. Each task has a stable link, a difficulty rating, and acceptance criteria. See CONTRIBUTING.md for development and PR guidelines.

License

Apache-2.0

_{Partnership Community: <a href="https://linux.do">LINUX DO</a>}