Our take
- Activity
- 77
- Community
- 49
- Issues
- 46
- Pull requests
- 70
+25 stars in the last 30 days
- Releases more often than 89% of the projects we track
Project history
Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.
Stars
2,025Forks
198Change since Nov 17, 2026: +1 stars·0 forks
Overview
CORE is a self-hosted personal AI assistant designed to carry context across tasks and tools. It indexes information from connected services and assistant conversations, then uses that context to plan and carry out work through integrations, a browser, terminal access, or coding agents.
It is aimed at developers and productivity-focused users who want a persistent assistant rather than a chatbot used one conversation at a time. Tasks can start from CORE's web interface or supported messaging channels, and the README describes a human-approval step before execution.
Key Features
- Builds a temporal knowledge graph from connected services and assistant conversations.
- Organizes work into tasks with plans, live state, and task-specific chat threads.
- Supports one-shot and recurring tasks, including work initiated from a scratchpad.
- Connects to 50+ apps through MCP, with webhooks for event-triggered work.
- Delegates coding work to Claude Code or Codex and can open a pull request when a session finishes.
- Provides browser and terminal access through a gateway, with local or remote execution options described in the README.
- Offers access through its web interface, voice, WhatsApp, Slack, and Telegram.
Use Cases
- Developers can ask CORE to gather repository context, plan a change, and delegate implementation to a coding agent.
- Individuals managing work across email, calendars, project trackers, and chat can use its memory to bring prior decisions into new tasks.
- Teams or solo operators can turn recurring work or incoming webhooks into tasks, reviewing the plan before execution.
- Users away from their computer can send tasks through supported messaging channels and continue working with the same assistant context.
Getting Started
The README's quickstart installs the CLI and starts its setup wizard:
npm install -g @redplanethq/corebrain && corebrain setup
The setup requires Docker. For configuration, deployment options, and gateway setup, see the repository README.
Alternatives
- QwenPaw: QwenPaw focuses on connecting a customizable assistant to chat apps and models, while CORE emphasizes task planning, app integrations, and coding agents.
| Project | Language | License | Stars | Status |
|---|---|---|---|---|
| core | TypeScript | Other | 2k | Not checked yet |
| QwenPaw | TypeScript | Apache-2.0 | 35.5k | Active |
Considerations
- Self-hosting requires Docker 20.10+, Docker Compose 2.20+, and the README recommends 4 vCPU and 8 GB RAM.
- Connecting integrations, running coding agents, and accessing local resources require additional setup, including gateway configuration for those capabilities.
- The README describes support for Claude Code and Codex, so users should check current documentation for the providers and workflows they intend to use.
- The repository has 211 open issues, which may be relevant when assessing project maturity or looking for existing reports.
- The input metadata reports the license as NOASSERTION, while the README displays an AGPL 3.0 badge. Verify the license in the repository before adopting or redistributing the software.
Found this useful?
Share it with someone who would like core.