Skip to content

README.md

Latest commit

 

History

History
282 lines (224 loc) · 11.9 KB

README.md

File metadata and controls

282 lines (224 loc) · 11.9 KB
Raw
CORE butler — attentive

Your Personal AI OS

Not a chatbot you open. An AI that is always on, always watching. Name it. Shape it. Connect it to everything you use. Reach it however you work. Open source, self-hosted, yours forever.

Website Docs Discord License: AGPL 3.0 GitHub Stars

See it work

Watch CORE take a plain-text task, gather context from GitHub and memory, plan the work, run a Claude Code session, and open a PR:

CORE Demo

Overview

Memory

CORE indexes email, meetings, GitHub, Linear, Slack and every assistant conversation into a temporal knowledge graph. Every task starts with the full picture — preferences, decisions, and prior context already loaded. 		Memory graph screenshot

Tasks

Every unit of work is a task with your spec, CORE's plan, live state, and a dedicated chat thread. One-shot or recurring. Each task can spawn a coding session, drive the browser, or run terminal commands. 		Tasks screenshot

Scratchpad

Your daily page. Write [ ] Fix the auth bug from issue #47 and CORE picks it up within 3 minutes, loads context from your repo and memory, and drafts a plan. 		Scratchpad screenshot

Voice

Press Ctrl+Option on Mac and speak. CORE runs the task in the background without breaking your flow — no window to open, no context switch. 		Voice overlay screenshot

Messaging

Reach CORE from WhatsApp, Slack, or Telegram. Send a task from the airport or from bed — CORE has the same memory and context regardless of where the message comes from. 		Messaging screenshot

Coding agents

CORE spins up Claude Code or Codex sessions with the full task context, runs them on your machine or in Docker/Railway, and opens a PR when done. Sessions keep running when your laptop is closed. Point CORE at your existing Claude or Codex subscription — the whole stack runs on it, no separate API key needed. 		Coding agents screenshot

Browser

A built-in browser CORE can drive on your behalf. Because it's isolated from your main browser, you log in only to the accounts you want the assistant to access. 		Browser screenshot

Integrations

One-click integrations to 50+ apps via MCP — GitHub, Linear, Jira, Slack, Gmail, Calendar, Sentry, Notion, Todoist. Webhook triggers turn inbound events into proactive work. 		Integrations screenshot

How CORE compares

CORE OpenClaw Hermes Agent Devin / Copilot
Multiple interfaces (voice, scratchpad, chat, messaging) ✅ Partial ❌ ❌
Persistent memory across tasks ✅ ❌ ✅ ❌
Delegates to coding agents (Claude Code, Codex) ✅ ❌ ❌ ✅
Structured task planning with human approval ✅ ❌ ❌ Partial
Custom name, personality, and voice ✅ ❌ ❌ ❌
50+ app connectors ✅ Partial Partial ❌
Terminal and browser access via gateway ✅ ✅ ✅ ✅
Human-in-loop by default ✅ ❌ ❌ ❌
Open source and self-hostable ✅ ✅ ✅ ❌

Run CORE on your Claude or Codex subscription

CORE can point at your existing Claude Pro or Codex subscription instead of API keys. Memory, planning, task execution, and coding sessions all run on the subscription you already pay for — no per-token bill on top.

Set up the subscription proxy →

Quickstart

Open source and self-hosted. Your data stays in your infrastructure.

Choose your path:

I want to... How
Try it on my machine Run the one-step install below (requires Docker)
Deploy on a server or VPS One-click Railway deploy
Use the Mac app Join the waitlist

Install and start CORE:

npm install -g @redplanethq/corebrain && corebrain setup

The setup wizard asks for an install directory, AI provider, API key, and chat model. It generates secrets, starts the stack, and opens http://localhost:3033.

Most local installs take a few minutes once Docker is running.

Or deploy on Railway:

Deploy on Railway

Connect a gateway so CORE can run coding agents, drive your browser, and access local folders:

corebrain login
corebrain gateway setup

Requirements: Docker 20.10+, Docker Compose 2.20+, 4 vCPU / 8GB RAM

Full self-hosting guide

Your first task (2 minutes after setup):

  1. Open the Scratchpad (your daily page at http://localhost:3033)
  2. Type [ ] Summarize my open GitHub issues or any task you would normally do yourself
  3. CORE picks it up within 3 minutes, gathers context from connected apps, and drafts a plan
  4. Approve the plan and CORE runs it and brings back the result

Connect your first app

Docs

  • Memory - Temporal knowledge graph, fact classification, intent-driven retrieval
  • Scratchpad - The daily surface where tasks and ideas start
  • Tasks - Plans, state, recurring work, and task-scoped context
  • Toolkit - 1000+ actions across 50+ apps via MCP
  • CORE Agent - Triggers, memory, tools, and execution
  • Gateway - WhatsApp, Slack, Telegram, email, web, and API access
  • Skills - Reusable instructions for repeatable workflows
  • Self-hosting - Full deployment guide
  • Changelog - What has shipped

Benchmark

CORE achieves 88.24% average accuracy on the LoCoMo benchmark across single-hop, multi-hop, open-domain, and temporal reasoning. See the benchmark repo for full results and baseline comparisons.

Security

  • CASA Tier 2 Certified
  • TLS 1.3 in transit
  • AES-256 at rest
  • Your data is never used for model training
  • Self-host for full isolation
  • Security policy
  • Vulnerabilities: harshith@poozle.dev

Community

We are building CORE in public.

We share the roadmap and architectural decisions openly because the hardest problems in building a personal OS are best solved with the people using it. Star the repo, self-host it, share what you build, and open issues for what is broken or missing.

Self-host your personal AI OS.

Star this repo · Read the docs · Join Discord