CEREBRO.md

Your agentic memory. A persistent knowledge system that works across every coding agent.

Every AI session starts from scratch. Cerebro fixes that. It records your sessions, captures your knowledge, and loads your context automatically — so your AI picks up right where you left off.

Get StartedView on GitHub
> /cerebro start

Hey Diego! Welcome back.

Health Check       ✓ All systems go
Last Session       Yesterday — API rate-limit review for checkout
Streak             5 days
Pinned             Ship v2.4 changelog before all-hands
Reminder (due)     Run quarterly dependency audit

Recent Activity:
  • 2026-03-12 — Tweaked OpenAPI examples for the payments flow
  • 2026-03-11 — Compared SQLite vs Postgres for a sidecar service
  • 2026-03-09 — Fixed flaky integration test in notifications

What would you like to work on today?

Why Cerebro?

Context that persists

Your AI assistant forgets everything between sessions. Cerebro doesn't. Every session summary, decision, and note is saved and searchable — across days, weeks, months.

Works across every tool

Not locked into one platform. Cerebro installs into Claude Code, Cursor, Windsurf, and Cline. One memory, everywhere you work.

You own your data

100% local. No cloud. No accounts. No tracking. Your data lives on your machine in plain markdown files. Export everything, delete everything, go anonymous — anytime.

One memory across every AI coding assistant

Supported assistants: Claude Code, Cursor, Windsurf, Cline.

Full hook support on Claude Code. Slash commands work on all platforms. More platforms coming soon.

Everything you need to never lose context again

Session Recording

Automatically logs every prompt and response. Know exactly what you worked on, when, and for how long.

Activity History

An append-only journal across all sessions. Never lose track of what you did last Tuesday.

Knowledge Capture

Notes, decisions, code snippets, TILs — all searchable, taggable, and linked.

Smart Start

Every session begins with context. Recent activity, reminders, goals, and pinned items — all surfaced automatically.

Privacy Controls

Anonymous mode, private sessions, granular consent, full data export, one-click delete.

Token Tracking

Know exactly how many tokens each session uses. Track costs across projects.

Daily Dashboard

/cerebro today — everything from today in one view: notes, sessions, reminders, goals.

Team Collaboration

Share decisions, hand off context, generate standups. Self-hosted via git.

Plain Markdown

Sessions, notes, and knowledge live in ordinary .md files — readable, diffable, and yours forever.

Get started in 2 minutes

  1. 1

    Step 1: Install

    git clone https://github.com/rcktshp/cerebro.md.git
cd cerebro.md && bash install.sh

    Copies hooks and the slash command to all detected AI platforms.

  2. 2

    Step 2: Onboard

    /cerebro

    Cerebro walks you through setup — your name, preferences, privacy settings, storage location. Personalized to you.

  3. 3

    Step 3: Work

    Cerebro records your sessions automatically in the background. Capture notes, decisions, and snippets as you go with quick commands.

  4. 4

    Step 4: Remember

    /cerebro start

    Every session begins with your full context. Recent activity, reminders, goals, and knowledge — loaded automatically.

45+ commands for your entire workflow

All commands invoked as /cerebro <command>. Expand a category to see commands.

Session
/cerebro start/cerebro end/cerebro private/cerebro log
Capture
/cerebro note/cerebro til/cerebro snippet/cerebro decision/cerebro inbox/cerebro bookmark/cerebro pin
Focus
/cerebro goal/cerebro blocked/cerebro checkin/cerebro workspace/cerebro context
Search
/cerebro search/cerebro find/cerebro query/cerebro tag
Knowledge
/cerebro memory/cerebro map/cerebro graph/cerebro links
Review
/cerebro today/cerebro digest/cerebro review/cerebro changelog/cerebro flashback/cerebro stats/cerebro streaks/cerebro patterns
Collaboration
/cerebro team/cerebro join/cerebro share/cerebro handoff/cerebro standup/cerebro mention/cerebro delegate/cerebro push/cerebro pull
Automation
/cerebro template/cerebro alias/cerebro watch
System
/cerebro status/cerebro profile/cerebro consent/cerebro privacy/cerebro clean/cerebro update/cerebro setup/cerebro uninstall/cerebro export

See it in action

A realistic session transcript with timestamps, context load, and token stats inline.

# Session: 2026-03-12 14:30:22

**Model**: example-model-2x
**Session ID**: demo7f3a

---

### 14:30:22

/cerebro start

### 14:30:25

Hey! Welcome back. You're on a 5-day streak.

Pinned: Ship v2.4 changelog before all-hands
Reminder (due today): Run quarterly dependency audit

Recent activity:
  • Yesterday — Tweaked OpenAPI examples for the payments flow
  • 2 days ago — Compared SQLite vs Postgres for a sidecar service

What would you like to work on today?

_Turn 1 | 3s active | Tokens: 2.1k in, 0.8k out | Total: 3s_

### 14:30:30

Let's sketch the Redis cache layer for search

### 14:45:12

_Turn 2 | 14m 42s active | Tokens: 45.2k in, 12.1k out | Total: 14m 45s_

Your data. Your rules.

Privacy-first by design — your memory stays on your machine unless you choose otherwise.

100% local

No cloud, no accounts, no telemetry. Plain markdown files on your machine.

Opt-in everything

You choose what Cerebro tracks during onboarding. Change anytime.

Private sessions

/cerebro private — zero logging, zero trace.Anonymous mode strips identity from stored content.

Full export

/cerebro privacy export — download everything.

Nuclear option

/cerebro privacy delete-all — wipe it all.

Open source

Read the code. Verify every claim.

Lightweight. No dependencies. Just files.

~/.cerebro/           → Config, hooks, session map (~15 KB)
~/Cerebro/            → Sessions, notes, history, knowledge

No databases. No background processes. No daemons.
No npm install. No pip install. Just Python 3.
~15 KB
install footprint
Python 3
only dependency
None
background processes
Linux
supported
macOS
supported
Windows
supported

Free forever. Pay for team power.

Open Source

Free

  • ✓All personal features
  • ✓Unlimited sessions & storage
  • ✓All platforms supported
  • ✓Self-hosted team collaboration
  • ✓Community support

Team

Coming soon

  • ✓Hosted team hub
  • ✓Cloud sync across devices
  • ✓Web dashboard with analytics
  • ✓Slack, Linear, Jira integrations
  • ✓Priority support

Enterprise

Coming soon

  • ✓Everything in Team
  • ✓SSO & audit logs
  • ✓Dedicated support
  • ✓Custom integrations
  • ✓SLAs, compliance & data residency

Get started in 2 minutes

git clone https://github.com/rcktshp/cerebro.md.git
cd cerebro.md && bash install.sh

Then type /cerebro in your AI assistant.