Show HN: MetaBrain – A local document memory for AI agents

Open source. Local first. Agent ready.

Local document memory for AI tools, coding agents, and the humans who work with them.

Give every agent one durable, searchable place for notes, source snippets, task context, metadata, tags, links, and version history.

Start small

Install it, then give agents a shared memory.

metaBrain ships as the `mb` CLI, the optional `mbd` local daemon, and the embeddable `MetaBrainCore` Swift library.

brew tap OpenCow42/tap && brew install mb

Made for AI and agents alike

A memory layer agents can actually use.

Agents do not need a private file convention for every task. metaBrain gives them a stable local store with predictable paths, searchable content, tags, metadata, references, and retained versions.

Write durable facts

Store summaries, decisions, and task state where the next agent can find them.

mb put /tasks/release-checklist \
  "Prepare first public release." \
  --tag release --meta status=active

Search workspace memory

Retrieve context by words, paths, tags, or metadata instead of hunting through scratch files.

mb search "public release" --tag release

Patch without rewriting

Apply focused unified diffs to stored documents and keep the old versions available.

mb patch /tasks/release-checklist --patch-file change.diff

Why try it

Small CLI. Useful memory model.

metaBrain keeps the interface plain enough for shell scripts and rich enough for long-running agent workflows.

Workspace local

The default store lives at `.metabrain/store.leveldb`, so tools can discover it without setup ceremony.

Searchable

Current document chunks are indexed for lexical search with tag, metadata, and path filters.

Structured

Documents carry metadata, tags, references, retained versions, and filesystem-like paths.

Versioned

Updates keep snapshots, and `patch` can apply unified diffs to stored document bodies.

Daemon ready

`mbd` can serve multiple local metaBrain databases through one daemon, so agents can work with separate stores concurrently.

Embeddable core

`MetaBrainCore` keeps shared behavior in a Swift library for future tools and interfaces.

Five-command tour

Try the CLI in a clean workspace.

Create a store, write a note, browse the tree, search it, and read the body back. That is enough to feel the shape of the tool.

mb init
mb put /notes/today "Remember the lexical store." --tag planning --meta source=agent
mb list /notes --recursive --dates
mb tree --max-depth 2
mb search "lexical store" --tag planning
mb get /notes/today

Open source

Built in the open for local-first agent work.

The project is BSD 3-Clause licensed, hosted on GitHub, and currently supports macOS, Linux, and Windows.

metaBrain - open-source local memory for AI agents