core: Self-Host a Personal AI Assistant for Everyday Work
Summary
CORE is a self-hosted AI assistant that combines persistent memory, task planning, app integrations, and coding agents. It suits people who want one assistant to work across their tools, with human approval and control over their data.
At a glance
- Language
- TypeScript
- License
- NOASSERTION
- Stars
- 2k
- Forks
- 196
- Added to OSRepos
- November 23, 2025
- Last analyzed
- October 3, 2026
Topics
Click on any tag to explore related repositories
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
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.
Project Facts
- Language: TypeScript
- License: NOASSERTION
- Stars: 2k
- Forks: 196
- Topics: ai-agent, ai-memory, automation, automations, claude-code, codex, developer-tools, mcp, ollama, personal-assistant
- Archived: false
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.
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.
Source repository
Open the original repository on GitHub.
22 counted GitHub visits
Related repositories
Similar repositories that may be relevant next.
OrcaReplay: Time Travel for AI Agents, Debugging and Evaluation
October 2, 2026
OrcaReplay introduces "time travel" capabilities for AI agents, allowing developers to record, replay, fork, and debug any agent run with any model. It addresses the challenges of AI agent debugging by providing byte-for-byte reproducibility, offline analysis, and the ability to compare different models from specific checkpoints. This tool, built by the OrcaRouter.ai team, enhances observability and control over complex agent behaviors.
OpenMake LLM: Self-Hosted AI Workspace for Local and Open-Weight LLMs
October 1, 2026
OpenMake LLM is an open-source, self-hosted AI workspace for local and open-weight LLMs. It coordinates specialized models, autonomous agents, and tools for deep research and artifact generation. This platform supports vLLM, LiteLLM, and BYOK providers, offering a robust environment for managing AI workloads.
ZenNotes: Keyboard-First Markdown Notes with Vim, Diagrams, and MCP Integration
October 1, 2026
ZenNotes is a versatile, keyboard-first Markdown notes app designed for speed and flexibility. It stores notes as plain Markdown files, offering Vim-friendly editing, diagram support, and integration with MCP tools. Available as a desktop app (Electron) and a self-hosted web app, ZenNotes provides a powerful solution for organizing your thoughts.
lat.md: A Knowledge Graph for Your Codebase, Written in Markdown
September 26, 2026
lat.md is an innovative tool that transforms your codebase knowledge into an interconnected graph of markdown files. It helps both AI agents and human developers quickly understand project architecture, business logic, and design decisions. By integrating directly into your project, lat.md ensures documentation remains consistent and up-to-date.