spacebot

MCP.Pizza Chef: spacedriveapp

This tool runs as a standalone assistant that lives inside your team's chat apps instead of a single browser tab. You install it on a server you control, connect it to Discord, Slack, or Telegram, and it holds conversations with many people at once, remembers what each person told it, and keeps working on tasks in the background even when nobody is actively chatting with it. You'll need an account and a personal access key from an AI provider such as Anthropic, OpenAI, or Google Gemini to power it, and getting it running takes some comfort installing developer tools.

Communication

Use This MCP client To

Run a helper bot that chats with my whole team at once Remember details about every person it talks to over time Keep working on a task quietly in the background for me Coordinate a project across a busy Slack or Discord channel Pick up right where we left off after a restart Get smarter and more useful the more my team uses it

README

Spacebot

Spacebot

The agent harness that runs teams, communities, and companies.

spacebot.sh • How It Works • Goals & Tasks • Quick Start • Spacedrive • Docs

One-click deploy with spacebot.sh — connect your Discord, Slack, Telegram, or Twitch, configure your agent, and go. No self-hosting required.

Spacebot UI


Spacebot is opinionated agent infrastructure, built for teams and usable by anyone. State belongs in structured storage, not markdown files the LLM manages. Memory lives in a typed graph in SQLite. Autonomy runs on a task state machine linked to goals, not a heartbeat.json. The LLM reasons. The system holds state.

It gets smarter the more you use it. After complex tasks, the agent captures what it learned as reusable skills. After conversations go idle, a background process silently saves skills and memories worth keeping. Every session builds on the last — without any user action.

It works out of the box and scales from one person to a whole community.


The Problem

Most AI agent frameworks run everything in a single session. One LLM thread handles conversation, thinking, tool execution, memory retrieval, and context compaction, all in one loop. When it's doing work, it can't talk to you. When it's compacting, it goes dark. When it retrieves memories, raw results pollute the context with noise.

Spacebot splits the monolith into specialized processes that only do one thing, and delegate everything else.


Built for Teams

No other agent harness handles concurrent multi-user conversations, shared memory across channels, and true process-level concurrency. A Discord community with hundreds of active members, a Slack workspace running parallel workstreams, a Telegram group coordinating across time zones. Spacebot handles all of it without any user waiting on another.

Solo users get the same infrastructure. Better memory, better concurrency, better structure. Everything teams rely on, for one person.

spacebot FAQ

Which chat apps does this work with?
It connects to Discord, Slack, Telegram, and Twitch, so your community or team can talk to it right where they already are.
Do I need an account or a special key to use it?
Yes. You need an account with an AI provider like Anthropic, OpenAI, or Google Gemini and a personal access key from them, since that's what powers the assistant's thinking.
How hard is this to set up?
It's built for people comfortable installing developer tools — running it yourself means installing the Rust programming toolchain and configuring it from the command line, though a hosted version is available that skips that step.
Can I use this to run an AI helper for my Discord community?
Yes — it's built to handle many people talking to it at once across different channels, including sudden bursts of messages, without slowing down or losing track of who said what.
Can I use this to keep a project moving even when I'm not actively chatting with it?
Yes — you can give it goals and tasks, and it will keep working on them on its own schedule, then ask for your approval before it acts on anything new it decides to do.
Will it remember past conversations?
Yes. It keeps a running memory of people, topics, and decisions, so it doesn't forget what happened in earlier conversations the way a typical chat assistant does.
Can I run more than one assistant with this?
Yes. You can run several assistants from one installation, each with its own personality, memory, and permissions — for example, one for your community and a separate one for your team.
Does this only work for large teams?
No. A single person gets the same memory and background-task abilities as a large team, just scaled down to one conversation.