Skip to content
Claude-Mem / Compare

Claude-Mem vs Basic Memory

Build lasting knowledge as your agents work.

Every decision and discovery should give your next session a head start. We turn supported agent activity into searchable observations in the background, then connect recall to the timeline and evidence behind it. Keep building while your agents build the knowledge you can carry forward.

Source review:

The Claude-Mem mascot’s laptop work becomes a ribbon of saved fixes and discoveries. Reused from the illustrated work-history series.
Today’s discoveries. Tomorrow’s starting point.

Production experience

Built for real work. Used in production.

Alessandro ran our open-source engine on three machines for 70 days. His customized deployment captured 22,718 observations, including 1,262 bug fixes and 757 decisions. Explore the fleet, the search index and the data he published.

Read the production case study

AI memory for agents

Turn useful experience into knowledge you can use.

Capture knowledge inside the workflow.

Our hooks send supported agent activity to a background observer that creates observations and session summaries. Build a lasting record of useful decisions and discoveries as the task moves forward.

See automatic capture

Open the context behind the answer.

We connect compact search results to their timeline and full observations. Inspect what happened around a decision and give your agent evidence it can build on.

Explore source-backed recall

Keep knowledge through the next change.

Start with our open-source engine and local memory. Add CMEM Pro to sync eligible memory across devices and retrieve it from connected MCP clients when your tools or workflow change.

Connect your agents

Basic Memory puts shared knowledge in Markdown files that people and agents can read and edit. We turn supported agent activity into lasting observations in the background, with a timeline that keeps the context behind each discovery within reach.

Why choose Claude-Mem

Choose a memory loop that keeps up.

Choose us to build useful memory while your agents work. Our observer captures supported activity, our retrieval tools connect answers to observations and their timeline, and CMEM Pro carries eligible memory into connected tools. Start with one real task and put what you learn to work in the next session.

Build knowledge without breaking your flow.

Let our background observer turn supported agent activity into observations and session summaries. Keep the context behind useful discoveries available while you focus on the task.

Make the next session a continuation.

Search for a past decision, open its surrounding timeline and read the full observation. Add CMEM Pro when you want synced memory available across connected tools and devices.

Side by side

Follow the memory.

From what gets saved to what comes back in the next session. Each detail below links to its documentation.

Claude-Mem and Basic Memory: capture, recall, deployment and setup
WorkflowClaude-MemBasic Memory
What becomes memory?

Supported agent hooks feed a worker that turns activity into structured observations and session summaries.

Claude-Mem architecture

Notes are Markdown files. The Claude Code plugin adds a session briefing and an agent-authored checkpoint around compaction; its lifecycle event envelopes are not transcripts or knowledge-graph notes.

Basic Memory harness capture · Basic Memory Claude Code integration
Finding the reason behind a decision

Session context plus a search → timeline → full-observation workflow, so the agent can inspect the notes behind an answer.

Claude-Mem progressive disclosure

Search notes, read full or sliced content, and expand context through relations. Keyword and semantic search are available; a local vector-runtime problem can cause keyword-only fallback.

Basic Memory local MCP tools · What is Basic Memory
Local storage and editing

The open-source engine stores memory in local SQLite with full-text search. Optional Chroma adds semantic search; observation uses your configured model provider.

Claude-Mem architecture · Claude-Mem installation

The local engine stores Markdown files with a secondary database index. Files can be read and edited outside Basic Memory, then indexed for retrieval.

Basic Memory technical information
Across tools and devices

Optional CMEM Pro sync moves eligible memory records between your devices and makes synced notes available through your private MCP connection. Capture still needs a supported integration.

Claude-Mem cloud sync

MCP connects assistants to a common knowledge base. A hosted cloud service is available as well as local operation; the Claude Code cloud setup uses remote MCP and OAuth.

Basic Memory Claude Code integration · What is Basic Memory
What lifecycle capture guarantees

Supported hooks send tool activity to the worker for observation processing. Verify the integration and actual saved records; a running agent alone is not proof that every action was captured.

Claude-Mem architecture

SessionStart and PreCompact hooks coordinate context and checkpoints. Flushing lifecycle envelopes archives them locally; the documented flush does not create graph notes.

Basic Memory harness capture
Getting started

Run the installer on your computer, select your agents and memory provider, then verify a captured observation and a recall query.

Claude-Mem installation

Install the local package or connect cloud MCP. For Claude Code plugin features, install the plugin, map the repository to a project, and verify the MCP connection and hooks.

Basic Memory Claude Code integration

Try it on real work

Give your next session a head start.

Start with one real task. See what we capture, then put that memory to work in a fresh session.

  1. 01

    Connect your agent.

    Run our installer, choose your supported agent and memory provider, and finish setup. The installation guide walks you through the connection.

  2. 02

    Build useful memory.

    Work through a task with a decision worth remembering. Our observer turns supported agent activity into observations you can inspect.

  3. 03

    Use what you learned.

    Start a fresh session and ask about that decision. Search the memory, follow its timeline and open the supporting observation. Add CMEM Pro when you want synced memory in connected tools.

Try Claude-Mem on your computer.

The installer guides your agent and provider choices. Then check the captured notes and ask a recall question.

npx claude-mem install

Questions

Before you choose.

Is Basic Memory just manual note taking?

No. It supports assistant-written notes, coding-agent plugins, session briefings and checkpoints. Compare its documented note and checkpoint workflow with Claude-Mem’s background observation workflow rather than assuming it has no automation.

Can both tools run locally?

Yes. Claude-Mem stores local memory in SQLite; Basic Memory stores Markdown with a database index. Claude-Mem’s observer uses your configured model provider. Local storage does not by itself mean every model request stays on your computer.

Which has better recall or lower cost?

This guide does not establish a benchmark winner. Use the same project, decisions and later questions. Compare whether each answer has supporting evidence, how much context it reads, and the total model and hosting cost.

Can I use my existing Markdown notes?

Basic Memory is designed around Markdown files. This page does not promise automatic migration of its files, relations or checkpoints into Claude-Mem. Keep the originals and check a documented import path before changing your source of truth.

Check the details

Sources and scope.

Written by Claude-Mem from the documentation linked below. Product documentation was reviewed on 18 November 2026; this is not a hands-on benchmark or a promise that every deployment has the same features.