nanobot
★ 49.3k
vs
ask-user-questions-mcp
★ 147
nanobot vs ask-user-questions-mcp
nanobot: nanobot is an ultra-lightweight, self-hosted personal AI agent framework built in Python, offering a readable core for multi-agent delegation and automation. It supports various interfaces including WebUI, terminal, and chat apps, integrating tools, long-term memory, and OpenAI-compatible APIs.; ask-user-questions-mcp: AUQ is a comprehensive toolset designed to integrate human intent into long-running, multi-agent AI workflows. It allows AI assistants to ask clarifying questions via a dedicated CLI interface, centralizing all interactions in one inbox for convenient user responses.
01
TL;DR
nanobotMulti-Agent · ★ 49.3k
When to choose:
- You want a lightweight, hackable Python personal AI agent framework with clean code, a WebUI, and built-in MCP client support.
- You prefer an easy-to-read, self-hosted agent core without the enterprise boilerplate of heavy agent frameworks.
When to skip:
- You require production-grade distributed state checkpointing, strict Pydantic type validation, or multi-role team SOPs; Pydantic AI or CrewAI offer more mature infrastructure.
- Your production stack is .NET or Go; Microsoft Agent Framework covers those runtimes.
ask-user-questions-mcpMulti-Agent · ★ 147
Guiding AI assistants during coding or complex problem-solving tasks
02
Side-by-Side Comparison
Field
nanobotask-user-questions-mcpCategory
Multi-Agent
Multi-Agent
Stars
★ 49.3k
★ 147
License
MIT
MIT
Install Command
curl -fsSL https://raw.githubusercontent.com/HKUDS/nanobot/main/scripts/install.sh | sh
bun add -g auq-mcp-server
Updated
1d ago
4mo ago
Open Source
Yes
Yes
Tags
AI Agent Framework, Self-hosted, Python
AI, Multi-Agent, Human-in-the-loop
03
Features
nanobot01Persistent workflows: goals, memory, tools, and chat context survive long-running work.
02Chat-native reach: WebUI, API, Telegram, Feishu, Slack, Discord, Teams, email, and Mattermost.
03Model freedom: OpenAI-compatible APIs, local LLMs, image generation, search, and fallbacks.
04Small core: readable internals with MCP, memory, deployment, and automation built in.
05Own your stack: inspect, customize, self-host, and extend without a giant platform.
ask-user-questions-mcp01Supports single/multiple choice questions with custom options
02Enables multi-agent interoperability and question queueing
03Human-in-the-loop capabilities: question rejection with explanation, elaboration requesting, quick recommendations
04Non-invasive CLI interface with native OS notifications and terminal progress bar
05Multi-language support and customizable color themes
04
Use Cases
nanobot↳Running long-horizon goals and scheduled automations.
↳Connecting to various chat applications like Telegram, Discord, Slack for AI interaction.
↳Exposing a Python SDK and OpenAI-compatible API for custom integrations and development.
↳Deploying as a long-running local or server-side agent gateway.
ask-user-questions-mcp↳Guiding AI assistants during coding or complex problem-solving tasks
↳Injecting human intent into long-running autonomous AI workflows to prevent hallucinations
↳Centralizing clarifying questions from multiple AI agents into a single, manageable inbox
↳Responding to AI queries remotely via SSH without disrupting workflow
↳Providing a unified interface for questioning across various AI clients and platforms (MCP, OpenCode)
05
Best For
nanobotMost PopularEssential
ask-user-questions-mcp—
FAQ
FAQ
What is the difference between nanobot and ask-user-questions-mcp?
Both nanobot and ask-user-questions-mcp are in the Multi-Agent category. nanobot has 49.3k stars, while ask-user-questions-mcp has 147 stars.
Which is better, nanobot or ask-user-questions-mcp?
The best choice depends on your use case. Choose nanobot if Running long-horizon goals and scheduled automations., and ask-user-questions-mcp if Guiding AI assistants during coding or complex problem-solving tasks.
Is nanobot free or open source?
Yes, nanobot is open source on GitHub (MIT).
Is ask-user-questions-mcp free or open source?
Yes, ask-user-questions-mcp is open source on GitHub (MIT).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→