nanobot

What is nanobot?

nanobot is an open-source AI agent that runs in your own environment and is built around a small core. After installing it, a guided setup opens a browser-based WebUI where you add a model provider and send a first message; a terminal interface and a command-line fallback are also available. The agent can work with your choice of models and tools, connect to chat apps such as Telegram, Discord, Slack, Feishu, WeChat and Email, and add capabilities through Agent Plugins, CLI apps and MCP servers. It supports skills, long-term memory, web search, image generation, scheduled automations with a task calendar, inline subagents and conversations arranged side by side. Developers can embed it with a Python SDK or expose an OpenAI-compatible HTTP endpoint. Deployment options in the docs include Render, Docker, systemd and macOS LaunchAgent. The project uses the MIT license, so there is no license fee; you pay only for the model provider you configure. The latest release shown is 0.3.5, dated September 15, 2026.

Use cases

• Run a self-hosted personal AI agent
• Connect an agent to Telegram or Slack
• Schedule recurring agent tasks
• Add MCP tools to an assistant
• Embed an agent in Python code
• Serve an OpenAI-compatible endpoint

Who it's for

• Developers
• Self-hosting enthusiasts
• AI tinkerers
• Small teams

Why use nanobot

• You keep the agent, its memory and your sessions in your own environment instead of a hosted service.
• You can switch between hosted, OAuth, company or local models without changing how you work.
• One agent can reach you through the WebUI, the terminal or the chat apps you already use.
• Scheduled automations let recurring work, such as a morning brief, run with results kept in the original topic.

nanobot features

• Browser WebUI with guided first-run setup
• Native terminal workbench and side-by-side conversations
• Chat channels including Telegram, Discord, Slack, Feishu, WeChat and Email
• Apps panel for Agent Plugins, CLI Apps and MCP integrations
• Skills, long-term memory and web search
• Automations with a calendar for scheduled runs
• Inline subagents for splitting work in parallel
• Model presets, runtime model switching and fallbacks
• Python SDK and OpenAI-compatible HTTP API
• Deployment guides for Render, Docker, systemd and LaunchAgent

nanobot integrations

• Telegram
• Discord
• Slack
• Feishu
• WeChat
• Anthropic
• Linear
• Render
• Docker

How to get started with nanobot

1. Run the installer, which opens nanobot webui on a local desktop.
2. Add a provider and model in Settings, then send Hello! to confirm the agent replies.
3. Connect chat apps under Channels and add tools or MCP servers under Apps.
4. Keep it running with Render, Docker, systemd or a macOS LaunchAgent, and set schedules for recurring work.

nanobot limitations

• You supply and pay for your own model provider key
• Render deployment needs a paid service because persistent disks are not on the free tier
• Official Docker usage means building from the repository's Dockerfile
• Releases change quickly, so back up config and sessions before upgrading

nanobot pricing

nanobot is open source, so you can use and self-host it for free.

Prices can change and may vary by country or exclude tax. Check the official pricing page.

nanobot alternatives

The main nanobot alternatives listed on Debuly are Open WebUI, LibreChat, AutoGPT, goose, TrustClaw and SwarmClaw. The table compares pricing and platforms; order is A–Z.

1. 

   AutoGPT

   Agent platform with a plain-English AutoPilot, a visual workflow builder and self-hosting, plus a $50/month Pro plan with a 7-day trial.

   Automation and agentsDeveloper platformsProductivity
   FreemiumVisit AutoGPT (official site)
2. 

   goose

   Open source AI agent that runs on your machine as a desktop app, CLI or API and connects to tools through MCP extensions.

   Automation and agentsCodingDeveloper platforms
   Open sourceVisit goose (official site)
3. 

   LibreChat

   Free open-source AI chat platform that puts many model providers, agents, code execution and MCP tools in one self-hostable app.

   Chat assistantsDeveloper platformsAutomation and agents
   Open sourceVisit LibreChat (official site)
4. 

   Open WebUI

   Self-hosted AI chat platform for Ollama and OpenAI-compatible models with RAG, agents, tools, notes, channels and role-based access.

   Chat assistantsDeveloper platformsAutomation and agents
   Open sourceVisit Open WebUI (official site)
5. 

   SwarmClaw

   Open-source, self-hosted runtime for running AI agent teams with memory, schedules, delegation and 24+ model providers.

   Automation and agentsDeveloper platformsCoding
   Open sourceVisit SwarmClaw (official site)
6. 

   TrustClaw

   Open-source personal AI agent from Composio with OAuth tool access, sandboxed execution, memory and Telegram, deployable on Vercel.

   Automation and agentsProductivityDeveloper platforms
   Open sourceVisit TrustClaw (official site)

nanobot FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from nanobot.wiki · fetched 23 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.