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 commun
What is 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.
Overview of second-brain
What it is
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. It runs on your own machine and requires Python 3.11+, git, and Node.js 20.19+ or 22.12+ for the web UI.
Key features
- Acts as an agentic operating system with local file intelligence, workflow automation, and LLMs.
- Supports multiple AI model providers: ChatGPT (Codex), OpenRouter, OpenAI, Anthropic, Gemini, local models via Ollama, and any OpenAI-compatible endpoint.
- Includes widgets (HTML files) that run in a sandboxed iframe for security.
- Provides a web UI accessible at http://localhost:5174.
- Offers a package system to add capabilities like knowledgebase, memory, Gmail, and Telegram frontend.
- Runs locally on your machine with Python 3.11+, git, and Node.js 20.19+ or 22.12+.
Use cases
Second Brain can be used for automating tasks using local files, workflow automation, and LLMs. It can communicate over multiple modalities and messaging platforms. Examples include indexing documents, setting up Telegram, and running widgets like DOOM.
Getting started
bash git clone https://github.com/henrydaum/second-brain cd second-brain python -m venv .venv source .venv/bin/activate # On Windows use .venv/Scripts/activate pip install -r requirements.txt cd frame_ui npm install cd .. python main.py After starting, the web UI opens at http://localhost:5174. Run /setup to connect an AI model.
License and pricing
Second Brain is open source under the MIT license.
Based on the project's public README and repository metadata.