# remindb — Portable Memory DB for AI Agents

> remindb stores agent memory in a SQLite file with search and deltas. Install via a one-line script and serve memory to MCP-capable agents.

## Install

Copy the content below into your project:

## Quick Use

```bash
curl -fsSL https://raw.githubusercontent.com/radimsem/remindb/main/install.sh | bash
remindb --version
```

## Intro

remindb is designed to keep memory lightweight and portable: one `.db` file you can copy, commit, or sync, while the agent queries it via fast search and deltas instead of rereading everything.

**Best for:** Long-running agents that need persistent memory across sessions and machines

**Works with:** Linux/macOS/Windows; install scripts; SQLite-backed storage

**Setup time:** 10–20 minutes

### Key facts (verified)

- README provides a one-line install script for Linux/macOS and a PowerShell installer for Windows.
- From source build notes Go 1.26+ in README.
- GitHub: 89 stars · 3 forks; pushed 2026-05-12 (GitHub API verified).

## Main

For best results, treat memory as a product surface:

- Decide what should be written (decisions, preferences, constraints) and what should not (raw logs, secrets).
- Periodically compact and summarize cold memory nodes so search stays fast and relevant.
- Use delta-based sync (cursor hashes) to keep the agent “caught up” without large token spends.


### README excerpt (verbatim)

<p align="center">
  <img src="assets/logo.png" alt="remindb logo" width="400" />
</p>

<h1 align="center">remindb</h1>

<p align="center">
  Agentic memory in a single SQLite file.
  <br />
  Stop letting your agent re-read the same notes every session.
</p>

<p align="center">
  <a href="https://github.com/radimsem/remindb/actions/workflows/ci.yml"><img src="https://github.com/radimsem/remindb/actions/workflows/ci.yml/badge.svg?branch=main" alt="CI" /></a>
  <a href="https://github.com/radimsem/remindb/releases/latest"><img src="https://img.shields.io/github/v/release/radimsem/remindb?label=release&color=00ADD8" alt="Latest release" /></a>
  <a href="LICENSE"><img src="https://img.shields.io/github/license/radimsem/remindb?color=blue" alt="License" /></a>
  <img src="https://img.shields.io/github/go-mod/go-version/radimsem/remindb" alt="Go version" />
</p>

---

<p align="center">
  <img src="assets/arch.svg" alt="remindb architecture" width="100%" />
</p>

## Why I built this

Coding agents already have memory. `CLAUDE.md`, `AGENTS.md`, your notes folder, that growing pile of project READMEs. Stuff persists just fine.

The problem is *how* the agent consumes it. Every session starts by re-reading the whole pile from scratch — every `Read`, every `Grep`, scanning raw prose the agent has already processed dozens of times. Big context windows don't fix it. A 1M-token window is still paid per call, and still can't tell yesterday's stale note from today's relevant one.

Raw markdown is the wrong shape for memory. Not because it can't hold the words — it can — but because it forces the agent to pay full freight on every read.

`remindb` is a single SQLite file your agent treats as long-term memory. It parses your notes (Markdown, HTML, JSON, YAML, [TOON](https://github.com/toon-format/toon)) into a structured tree, hashes every node, encodes repetitive structures compactly when it saves tokens, and surfaces the whole thing through a tight MCP tool suite.

### What you get

**A tree the agent can index, not skim.** Instead of `ls`-ing a folder and reading every file to orient, the agent calls `MemoryTree` once. Each entry is a typed node — `[heading]`, `[list]`, `[kv]`, `[table]`, `[preamble]`, `[text]`, `[code]`, `[embed]` — with an ID, a short label, a temperature, and a token count. Think of it as `ls -la` for memory: one call, a scannable index, hot stuff floats up.

A real slice (from `remindb inspect --tree`):

```
[preamble] Preamble: framework, language, project (id=3kGXxidmWBp file=CLAUDE.md temp=0.50 tok=14)

### FAQ

**Q: Is remindb a server?**
A: README frames it as one portable SQLite file with an MCP runtime for fast queries.

**Q: How do I install it quickly?**
A: Use the provided install script for your OS, then verify with `remindb --version`.

**Q: Can I share memory across agents?**
A: Because it’s one `.db` file, you can copy/sync it, but you still need to manage access and privacy.

## Source & Thanks

> Source: https://github.com/radimsem/remindb
> License: MIT
> GitHub stars: 89 · forks: 3

---

<!-- ZH -->

## 快速使用

```bash
curl -fsSL https://raw.githubusercontent.com/radimsem/remindb/main/install.sh | bash
remindb --version
```

## 简介

remindb 主打“轻量 + 可携带”：把记忆放进一个 `.db` 文件里随处拷贝/同步，Agent 通过搜索与增量 delta 读取，而不是每次全量重读。

**最适合：** 需要跨会话/跨设备持久记忆的长跑型 Agent

**适配：** Linux/macOS/Windows；提供安装脚本；基于 SQLite 存储

**配置时间：** 10–20 分钟

### 关键事实（已验证）

- README 提供 Linux/macOS 一行安装脚本与 Windows PowerShell 安装方式。
- README 的源码构建说明提到需要 Go 1.26+。
- GitHub：89 stars · 3 forks；最近更新 2026-05-12（GitHub API 验证）。

## 正文

想把记忆层用好，最好把它当“产品能力”来设计：

- 明确写入什么（决策、偏好、约束）以及不写什么（原始日志、密钥）。
- 定期对变冷的记忆节点做压缩/总结，保证搜索结果更相关、更快。
- 用 delta/游标的增量同步方式，让 Agent 低 token 成本保持“最新状态”。


### README 原文节选（verbatim）

<p align="center">
  <img src="assets/logo.png" alt="remindb logo" width="400" />
</p>

<h1 align="center">remindb</h1>

<p align="center">
  Agentic memory in a single SQLite file.
  <br />
  Stop letting your agent re-read the same notes every session.
</p>

<p align="center">
  <a href="https://github.com/radimsem/remindb/actions/workflows/ci.yml"><img src="https://github.com/radimsem/remindb/actions/workflows/ci.yml/badge.svg?branch=main" alt="CI" /></a>
  <a href="https://github.com/radimsem/remindb/releases/latest"><img src="https://img.shields.io/github/v/release/radimsem/remindb?label=release&color=00ADD8" alt="Latest release" /></a>
  <a href="LICENSE"><img src="https://img.shields.io/github/license/radimsem/remindb?color=blue" alt="License" /></a>
  <img src="https://img.shields.io/github/go-mod/go-version/radimsem/remindb" alt="Go version" />
</p>

---

<p align="center">
  <img src="assets/arch.svg" alt="remindb architecture" width="100%" />
</p>

## Why I built this

Coding agents already have memory. `CLAUDE.md`, `AGENTS.md`, your notes folder, that growing pile of project READMEs. Stuff persists just fine.

The problem is *how* the agent consumes it. Every session starts by re-reading the whole pile from scratch — every `Read`, every `Grep`, scanning raw prose the agent has already processed dozens of times. Big context windows don't fix it. A 1M-token window is still paid per call, and still can't tell yesterday's stale note from today's relevant one.

Raw markdown is the wrong shape for memory. Not because it can't hold the words — it can — but because it forces the agent to pay full freight on every read.

`remindb` is a single SQLite file your agent treats as long-term memory. It parses your notes (Markdown, HTML, JSON, YAML, [TOON](https://github.com/toon-format/toon)) into a structured tree, hashes every node, encodes repetitive structures compactly when it saves tokens, and surfaces the whole thing through a tight MCP tool suite.

### What you get

**A tree the agent can index, not skim.** Instead of `ls`-ing a folder and reading every file to orient, the agent calls `MemoryTree` once. Each entry is a typed node — `[heading]`, `[list]`, `[kv]`, `[table]`, `[preamble]`, `[text]`, `[code]`, `[embed]` — with an ID, a short label, a temperature, and a token count. Think of it as `ls -la` for memory: one call, a scannable index, hot stuff floats up.

A real slice (from `remindb inspect --tree`):

```
[preamble] Preamble: framework, language, project (id=3kGXxidmWBp file=CLAUDE.md temp=0.50 tok=14)

### FAQ

**remindb 是服务端吗？**
答：README 描述它以一个可携带的 SQLite 文件为核心，并提供 MCP runtime 供快速查询。

**怎么快速安装？**
答：用 README 的安装脚本，然后用 `remindb --version` 验证。

**能多 Agent 共享吗？**
答：一个 `.db` 文件确实容易共享/同步，但仍需要你自己管理访问控制与隐私。

## 来源与感谢

> Source: https://github.com/radimsem/remindb
> License: MIT
> GitHub stars: 89 · forks: 3


---
Source: https://tokrepo.com/en/workflows/remindb-portable-memory-db-for-ai-agents
Author: AI Open Source