henrydaum/second-brain

Second Brain is an agentic framework that acts as an operating system, using local file intelligence, workflow automation, and LLMs to complete tasks and communicate over multiple modalities and messaging platforms.

What it solves

Second Brain is a personal AI agent that acts as a centralized hub for your digital life, allowing you to interact with your data, files, and various applications through a single interface. It solves the problem of fragmented AI tools by providing a unified system that can be extended with packages for specific capabilities like email access or knowledge base management.

How it works

It runs locally on your machine and connects to an LLM of your choice via providers like OpenRouter, OpenAI, Anthropic, Gemini, or local models via Ollama. The system uses a modular architecture where users can install "packages" (such as bundle_knowledgebase for RAG over PDFs and Office files, or bundle_memory for self-maintaining memory) to add new tools and capabilities. It includes a web UI and a terminal interface, and can be extended to work with chat apps like Telegram.

Who it’s for

Individuals who want a powerful, locally-hosted AI assistant that can manage their personal files, integrate with their communication tools, and be customized with specialized AI bundles.

Highlights

  • Extensible Package System: Install additional capabilities like Gmail integration or a knowledge base for searching personal documents.
  • Sandboxed Widgets: The agent can write and execute HTML files (widgets) in a secure iframe, capable of running complex applications like DOOM.
  • Flexible Model Connectivity: Supports a wide range of LLM providers, including local models and direct ChatGPT account integration via Codex.
  • Cross-Platform Access: Can be deployed via Docker or accessed on mobile devices using Tailscale or Telegram.

Related

  • Project
    s2b-dev/smart-second-brain

    The ​​​  ​  ​  …...............

  • Project
    undefined-ui/second-brain-os

    An open‑source guide and starter kit that turns an Obsidian vault into a personal “second brain” automatically curated by a Claude Code LLM agent. It provides a vault template, 18 LLM‑driven skills, 72 slash commands, scheduled sub‑agents, and detailed docs covering setup, ingestion, graph handling, and maintenance.

  • Project
    Intelligent-Internet/ii-agent

    An open-source AI agent for professional work that enables users to build apps, conduct deep research, and automate workflows using their own LLM API keys.

  • Project
    HKUDS/nanobot

    An ultra-lightweight, self-hosted personal AI agent framework that integrates multiple LLM providers, long-term memory, and various chat apps into a single runtime.

  • Project
    SAIL-Research-Lab/cheetahclaws

    A Python-native agent harness for AI coding assistants that supports any LLM provider or local model, offering a hackable alternative to closed-source agent frameworks.