nanobot
An ultra-lightweight Python AI agent framework that connects LLMs to chat apps, long-term memory, and local tools.
Run custom AI agents with memory, MCP, and multi-channel messaging across Telegram, Slack, and Discord.
nanobot is an open-source Python framework for running self-hosted personal AI agents with long-term memory and tool access. It allows you to operate agents from a browser UI, terminal, or direct integrations with messaging platforms like Slack, Discord, and Telegram. Support teams and developers looking to automate messaging workflows without platform lock-in will find it useful.
What it is
nanobot connects language models to local tools like shell commands, file operations, web fetchers, MCP servers, and scheduled automations. It retains session history across interactions using its Dream memory system and supports multi-agent delegation. You can expose its features through an OpenAI-compatible API or run it continuously as a gateway service.
Who it's for
It suits support engineers, technical customer experience leads, and developers who want to deploy self-hosted agents into existing communication tools like Slack, Email, or Linear. It is less suitable for non-technical teams who need a pre-packaged customer support portal without managing Python environments or server configs.
Key features
Multi-channel messaging integration
Connect your AI agent directly to Telegram, Discord, Slack, WeChat, Email, Mattermost, and Linear channels.
Long-term persistent memory
Retain session history and contextual information across long-running interactions using the Dream memory system.
Model context protocol support
Integrate third-party tools, local shell utilities, web fetchers, and subagents using standardized MCP interfaces.
Scheduled background task automation
Execute recurring workflows and automated long-horizon goals using cron-style scheduling built into the gateway.
Up and running in 3 steps
Our honest verdict
What's great
- Native connectivity with messaging platforms including Slack, Discord, Email, and Linear
- Compact Python codebase that provides an OpenAI-compatible API endpoint
- Built-in persistent memory system for long-horizon customer support tasks
- Flexible choice of local LLM models or external provider API keys
Where it falls short
- Requires self-hosted infrastructure and external API key management for production use
- Command-line setup is required if installing outside the automated installer
- Initial configuration requires managing provider settings and workspace access permissions manually
Pricing & license
nanobot is free open-source software distributed under the MIT license. There are no paid hosted tiers provided by the maintainers, so your cost is limited to server hosting and API usage.
Open remote AI-training roles
870 open remote AI-training roles, updated November 14, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
Alternatives
These reviewed AI tools do the same job instantly — from our scored directory.
Use it, or have us set it up
FAQ
Which messaging platforms does nanobot support?
nanobot connects to Telegram, Discord, Slack, WeChat, Email, Mattermost, Linear, and custom channels.
Does nanobot require a local GPU?
No, you can connect it to remote OpenAI-compatible API providers or run local LLMs if your hardware allows.
