Data

Tools

Indexes

Applications

Experiments

Awesome

An open API service indexing awesome lists of open source software.

https://github.com/redplanethq/core

Your AI butler that get things done
https://github.com/redplanethq/core

ai butler neo4j-graph nodejs postgresql prisma redis remix tailwind-css typescript

Last synced: 17 days ago
JSON representation

Your AI butler that get things done

Awesome Lists containing this project

README 

          


  

    🌐 Language

    


      

    


  






  

    CORE logo

  



# An AI butler that acts.



**Write what needs doing. Your AI butler handles the rest.**





    

        Website

    

    

        Docs

    

    

        Discord

    






---



> You use specialized agents like Claude Code and Cursor. You gather the context, kick off

> the session, babysit the output. You're the context middleman and that makes you the

> bottleneck. CORE's butler gathers the context, runs the agents, coordinates the work.

> You stop babysitting. You start operating.



[![CORE Demo](https://img.youtube.com/vi/PFk4RJvQg1Y/maxresdefault.jpg)](https://www.youtube.com/watch?v=7y_kt_UTYQs)



---



## Why we're building this



Every AI agent you use today is smart. And every single one forgets you the moment the conversation ends.



### You shouldn't have to open a chat window to get things done.



Your EA doesn't wait for you to open a chat window and explain what you need. They already know. They're already on it. Chat forces you to context-switch, explain yourself, and stay in the loop on things that shouldn't need your attention.



We think the right interface is a scratchpad, a shared page, like a note you and a colleague both have open at the same time. You write what's on your mind: tasks, thoughts, half-formed ideas. Butler reads it alongside you, picks up what's meant for it, works in the background, and updates you when something needs your attention or a job is done. No prompting required, no workflow to configure. When you need to go deep on something specific, tasks and direct chat are there, but the default should be the scratchpad.



### Your AI doesn't actually know you.



Every agent starts fresh. No preferences, no past decisions, no team context, no patterns. So it can't act proactively, because proactivity requires context that accumulates over time. Without persistent memory, agents are reactive tools waiting for your next prompt. CORE builds a persistent memory from every conversation, task, and connected app — so butler already knows your context before you open a task.



### You are the bottleneck.



Right now you are the glue. You gather the GitHub issue, read the Slack thread, check the error logs, paste it all into Claude Code, wait for output, and review it. That's not delegating, that's operating as an agent yourself. Every workflow starts with you. Every session depends on you explaining things from scratch. CORE is built to break that loop.



---



## Butler in action



### You described it once. It ran every night since.



`[ ] Delegate my backlog to Claude Code every night and open PRs` — you wrote that once.

Every morning, PRs are waiting. You review, approve, move on. Butler never needed reminding.



### You closed your laptop. Your meeting already produced results.



Butler read the transcript, extracted the follow-ups, created the tasks, and drafted the emails. You open the scratchpad and review. Done in four minutes.



### You wrote one line. You came back to a PR.



`[ ] fix the checkout bug from issue #312` — Butler loaded the context, spun up a Claude Code session, and handled it. You never left the terminal.



### You opened your inbox to review, not to triage.



Butler flagged what needs you, drafted replies for the rest, and turned action items into tasks. Your inbox is a decision queue now.



### You slept. The Sentry alert got handled.



CORE investigated, created the issue, and assigned the right engineer. You woke up to: *"Handled. Issue #847, assigned to Harshith."*



---



## What CORE is not



| | |

|---|---|

| **Not a RAG wrapper.** | Memory isn't "embed chunks and search." It's a temporal knowledge graph where facts are classified, connected, and updated over time. It knows *when* you decided something and *why*. |

| **Not a workflow builder.** | No drag-and-drop. You write what needs doing. Butler figures out the workflow. |



---



## Quickstart



Open source, self-hosted. Your data never leaves your infra.



**One step:**



```bash

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

```



That's it. The wizard asks for an install dir, an AI provider, an API key, and a chat model — then auto-generates secrets, brings the stack up, and opens at `http://localhost:3033`.



**Or one click on Railway:**



[![Deploy on Railway](https://railway.app/button.svg)](https://railway.com/deploy/core)



**Connect a gateway** (laptop, Docker host, or Railway) so CORE can drive your browser, run coding agents, and touch local folders:



```bash

corebrain login              # point at https://app.getcore.me or your self-hosted URL

corebrain gateway setup      # pick native | docker | railway

```



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



[Full self-hosting guide →](https://docs.getcore.me/self-hosting/setup)



> ☁️ Want to download our Mac App, sign up for waitlist [here](https://www.getcore.me/)



---



## Benchmark



CORE achieves **88.24%** average accuracy on the [LoCoMo benchmark](https://github.com/RedPlanetHQ/core-benchmark) — single-hop, multi-hop, open-domain, and temporal reasoning.



---



## Docs



Want to understand how CORE works under the hood?



- [**Memory**](https://docs.getcore.me/concepts/memory/overview) — Temporal knowledge graph, fact classification, intent-driven retrieval

- [**Toolkit**](https://docs.getcore.me/concepts/toolkit) — 1000+ actions across 50+ apps via MCP

- [**CORE Agent**](https://docs.getcore.me/concepts/meta-agent) — The orchestrator: triggers, memory, tools, sub-agents

- [**Gateway**](https://docs.getcore.me/access-core/overview) — WhatsApp, Slack, Telegram, email, web, API

- [**Skills & Triggers**](https://docs.getcore.me/toolkit/overview) — Scheduled automations and event-driven workflows

- [**API Reference**](https://docs.getcore.me/api-reference) — REST API and endpoints

- [**Self-hosting**](https://docs.getcore.me/self-hosting/setup) — Full deployment guide

- [**Changelog**](https://docs.getcore.me/opensource/changelog) — What's shipped



---



## 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 →](SECURITY.md)

- Vulnerabilities: harshith@poozle.dev



---



## Community



We're building the future of personal AI in the open. Come build with us.



- [Discord](https://discord.gg/YGUZcvDjUa) — questions, ideas, show-and-tell

- [CONTRIBUTING.md](CONTRIBUTING.md) — how to set up and send a PR

- [`good-first-issue`](https://github.com/RedPlanetHQ/core/labels/good-first-issue) — start here





  




---






**Write it. Butler handles it.**



[⭐ Star this repo](https://github.com/RedPlanetHQ/core) · [📖 Read the docs](https://docs.getcore.me) · [💬 Join Discord](https://discord.gg/YGUZcvDjUa)