single binary · plain files · zero services

Memory in plain files.

An immutable, versioned log for humans and AI agents. Every entry is a Markdown file with YAML frontmatter on your own disk — grep it, diff it, commit it to git. No database, no server, no cloud account.

terminal
curl -fsSL https://logbook.codicent.ai/cli/install.sh | bash

logbook init
logbook add "Customer prefers dark mode #memory #ux"
data/entries/2026/10/25/2026-10-25T131541Z__cef85f20….md

logbook list -t memory --length 1
logbook find -t memory "dark mode"
0 services
No DB, no daemon, no port
Markdown
YAML frontmatter, human-readable
Immutable
Amend = new version, full history
Remote-ready
logbook login → a Codicent project
Quick start

One binary on your PATH.

The install script picks the right self-contained binary for your platform from GitHub Releases. No .NET SDK needed.

Install script · bash
curl -fsSL https://logbook.codicent.ai/cli/install.sh | bash
logbook init
# pin a version: … | LOGBOOK_VERSION=0.8.0 bash
Install script · PowerShell
iwr https://logbook.codicent.ai/cli/install.ps1 | iex
logbook init
# installs to %USERPROFILE%\.logbook and adds it to your user PATH
Direct download · pick your platform
# assets: logbook-linux-x64, -linux-arm64, -osx-arm64, -osx-x64, -win-x64.exe
curl -Lo logbook \
  https://github.com/izaxon/codicent-logbook/releases/download/logbook-v0.8.0/logbook-linux-x64
chmod +x logbook && ./logbook --version

CLI releases are tagged logbook-v* in github.com/izaxon/codicent-logbook/releases (next to the logbook-server-v* releases).

Choose your level

Start with files. Grow without migrating.

Three layers, one data model: messages with #tags, JSON data messages and immutable versions. Pick the smallest one that does the job.

Level 1 · FilesYou are here

logbook CLI

logbook · Markdown files

Plain files on disk, driven from the shell. For scripts, one agent's memory or a personal work log. Nothing runs in the background.

Level 2 · Local runtime

Logbook server

logbook-server · SQLite + MCP

One process with SQLite, an MCP server, OpenAPI, a file inbox and an optional public tunnel. For Claude Desktop, Cursor and other MCP clients.

Logbook server →
Level 3 · Platform

Codicent

codicent.com · teams + automation

Multi-user projects, apps and 100+ automation tags (#ai, #transform, #ocr…) that turn messages into pipelines. For teams and production workflows.

codicent.com ↗

Same model all the way up: the CLI writes straight to a Codicent project after logbook login, and logbook data export/import moves records between instances.

Commands

A handful of verbs.

Every command is a plain shell call — easy for people, trivial for agents. Run logbook, logbook data or logbook chat for full help.

Entries
initaddgetlistfindhistorystatus

Tags come from #markers in the text or -t a,b. --amend <id> writes a new version; list shows only the latest, newest first, with --from/--to and --start/--length.

Data messages
data setdata getdata amenddata hidedata import

JSON key-value records with --filter k=v, --format entry|json|csv|table|export and idempotent export → import between instances.

Remote & chat
loginlogoutchat listchat export

Device-flow login stores a .logbook-session in the current folder; every command then runs against that Codicent project instead of local files.

Everyday use · entries
logbook add "Deployed 1.12.2 to prod #deploy #prod"
echo "long notes…" | logbook add -t notes
logbook add -t deploy --amend <id> "Deployed 1.12.3"
logbook list -t deploy --from 2026-10-01
logbook find --body-only "rollback"
logbook history <id>
Structured records · data messages
logbook data set -t customer '{"name":"Acme","status":"active"}'
logbook data get -t customer --filter status=active
logbook data get -t customer --format table
logbook data get -t customer --format export --all \
  --output customers.json
logbook data import customers.json --dry-run
On disk

Files you can read without the tool.

Entries are never rewritten or deleted. Tags are folders of links, superseded versions are marked — so plain grep, ls and git log keep working.

An entry · Markdown + YAML
---
id: 3f2a1b4c-…
created_utc: 2026-10-25T13:15:41Z
tags: [agent, memory]
parent_id: 9b7e…     # previous version
original_id: 9b7e…   # chain root
---

User confirmed they prefer dark mode in all apps.
The data folder · LOGBOOK_ROOT
data/
├── entries/YYYY/MM/DD/<ts>__<id>.md
│     # immutable entry files
├── tags/<tag>/<ts>__<id>.md
│     # links into entries/
└── superseded/<id>
      # marker: a newer version exists

On Windows without Developer Mode, tag links fall back to file copies — queries behave the same.

For AI agents

Persistent memory is one shell call away.

Agents forget between sessions. Any agent that can run a command — Claude Code, Codex, OpenClaw, a cron script — can write decisions down and recall them later. No API, no auth, no SDK.

Agent instructions · CLAUDE.md / AGENTS.md
## Memory
Use the `logbook` CLI as persistent memory.
- Recall first: `logbook list -t memory --length 20`
  or `logbook find -t memory "<topic>"`
- Record decisions: `logbook add "<fact> #memory #<topic>"`
- Correct a fact: `logbook add --amend <id> -t memory "<new>"`
- Never edit files under data/ by hand.
OpenClaw · shell tool
tools:
  - name: logbook
    type: shell
    description: Persistent memory log. Immutable, tagged, versioned.
    commands:
      add:     "logbook add -t {tags} {message}"
      list:    "logbook list -t {tags}"
      find:    "logbook find -t {tags} {pattern}"
      get:     "logbook get {id}"
      history: "logbook history {id}"
Need MCP instead of shell calls (Claude Desktop, Cursor)? That's the Logbook server — same model, served over MCP and OpenAPI.
Remote backend

Same commands, shared project.

Log in once and the CLI stores entries in a Codicent project instead of local files — so a team, or several agents on different machines, share one log. Entries become Codicent messages; data commands map to #data messages.

Interactive · device-flow login
logbook login                       # codicent.com, project "logbook"
logbook login --url https://myserver.com --project myproj
logbook status                      # mode, URL, project, expiry
logbook add "Shared note #team"
logbook logout
CI & automation · environment
export LOGBOOK_REMOTE_URL="https://codicent.com"
export LOGBOOK_REMOTE_TOKEN="<api-token>"
export LOGBOOK_PROJECT="myproject"
logbook data get -t customer --format json
# env vars win over .logbook-session

Remote mode searches full message content only — --body-only/--meta-only are local-mode features.

Configuration

A few environment variables.

Nothing to configure for local use: the CLI walks up from the current folder to find data/entries/, like git finds .git.

VariableDefaultDescription
LOGBOOK_ROOT(nearest folder with data/entries/, else cwd)Where the local log lives.
LOGBOOK_REMOTE_URL(none)Codicent base URL; with a token, switches every command to remote mode.
LOGBOOK_REMOTE_TOKEN(none)Bearer token for the remote project.
LOGBOOK_PROJECT(none)Remote project name.
LOGBOOK_VERSION(newest)Install scripts only: pin a CLI version, e.g. 0.8.0.