andrihakim146 GitHub avatar

hermes-second-brain

andrihakim146

Hermes Second Brain is a personal AI hub that lets you capture, search, and organize your Obsidian notes from Telegram via the Hermes Agent (MCP), running locally on your own machine.

Stars

14

7-day growth

No data

Forks

2

Open issues

0

License

MIT

Last updated

2026-07-05

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It bridges Telegram and Obsidian using an AI agent with atomic operations, undo, and a capability-based security model, making it a practical, privacy-focused second brain system.

Who it is for

  • Obsidian power users who take notes on the go
  • Telegram users wanting to capture ideas into a knowledge base
  • Developers interested in MCP-based AI tool integrations
  • Privacy-conscious individuals who prefer local-only AI assistants

Use cases

  • Save a web link or quick thought from Telegram directly into your Obsidian inbox
  • Search your entire Obsidian vault by full-text from a Telegram chat
  • Move notes between PARA folders or update note content via Telegram
  • Undo the last note operation if you made a mistake

Strengths

  • Atomic, duplicate-free, reversible note capture with hash guards
  • Full-text search using SQLite FTS5 with privacy-sensitive note detection
  • Capability registry and audit log for secure tool access
  • Works entirely locally on a single machine without cloud dependency

Considerations

  • Requires a 24/7 machine (e.g., Mac mini, VPS) and the Hermes Agent to be running
  • Only supports Obsidian vaults and Telegram as the interface
  • Setup involves multiple dependencies (Hermes Agent, LLM API key, Telegram bot) which may be complex for non-technical users

README quick start

Quick Start

Description

AI second brain for Obsidian, controlled from Telegram via Hermes Agent (MCP)

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482