run-a-lightweight-personal-ai-agent-with-nanobot

name	run-a-lightweight-personal-ai-agent-with-nanobot
description	Use Nanobot to configure a lightweight local personal agent with model providers, MCP tools, memory, chat channels, search, and gateway deployment paths. Use when this capability is needed.
metadata	{"author":"agentskillexchange"}

Run a lightweight personal AI agent with Nanobot

Use Nanobot to configure a lightweight local personal agent with model providers, MCP tools, memory, chat channels, search, and gateway deployment paths.

Prerequisites

Python 3.11+, nanobot-ai package, model provider credentials or local model runtime, optional MCP servers and chat/search integrations

Installation

Use the upstream install or setup path that matches your environment:

• git clone https://github.com/HKUDS/nanobot.git
• pip install -e .
• Install with uv
• uv tool install nanobot-ai

Requirements and caveats from upstream:

• 
• 2026-04-21 🚀 Released v0.1.5.post2 — Windows & Python 3.14 support, Office document reading, SSE streaming for the OpenAI-compatible API, and stronger reliability across sessions, memory, and channels. Please...
• 2026-04-17 🪟 Windows & Python 3.14 CI, Dream line-age memory, email self-loop guard.

Basic usage or getting-started notes:

• 2026-04-02 🧱 Long-running tasks run more reliably — core runtime hardening.

• 🚀 Quick Start

• Source: https://github.com/HKUDS/nanobot

• Extracted from upstream docs: https://raw.githubusercontent.com/HKUDS/nanobot/HEAD/README.md

Documentation

• https://nanobot.wiki

Source

• Agent Skill Exchange

---

Source: agentskillexchange/skills — distributed by TomeVault.