spacedriveapp/spacebot

An AI agent for teams, communities, and multi-user environments.

What it solves

Spacebot is a multi-threaded agent harness designed for teams and communities rather than solo users. It solves the "blocking" problem common in most AI agents, where a single conversation loop prevents the agent from handling new messages or performing background tasks while it is executing a tool call. By decoupling the conversation from the execution, Spacebot ensures the orchestrator remains available and responsive even during heavy workloads.

How it works

Spacebot uses a system of four distinct process types to ensure concurrency:

  • Channels: The user-facing LLM processes that handle identity and personality. They cannot block and are responsible for replying, branching, and spawning workers.
  • Branches: Concurrent forks of a channel's context used for thinking, recalling memories, and weighing options without cluttering the main conversation.
  • Branches: Independent processes that execute the actual work (e.g., shell commands, browser automation) using inherited context from the channel.
  • The Compactor: A programmatic monitor that summarizes context in the background to prevent the conversation from filling up, using either "rolling" summaries or "chronicle" checkpoints.

Who it’s for

  • Teams and Organizations: Those needing a shared agent with shared memory across multiple platforms (Slack, Discord, Telegram) and different user permissions.
  • Community Managers: Those running Discord servers where dozens of people can interact with an agent simultaneously.
  • Solo Power Users: Individuals who want a more structured, autonomous agent with better memory and concurrency.

Highlights

  • Chronicles: A durable, navigable record of long-running sessions that replaces rolling summaries with append-only checkpoints.
  • Multi-Platform Support: Native adapters for Discord, Slack, Telegram, Twitch, Signal, Mattermost, Email, and Webchat.
  • Coded-in-Rust: A single binary, local-first architecture with embedded databases (SQLite and LanceDB).
  • Graph-Based Memory: A typed knowledge system that distinguishes between facts, preferences, decisions, and goals using hybrid vector and full-text search.
  • Autonomous Task System: A goal-driven system where the agent proposes tasks and waits for human approval before execution.
  • MCP Integration: Support for the Model Context Protocol to connect workers to external databases and APIs.

Related

  • Project
    openairymax/agentrt

    AgentRT is an AI Agent runtime platform that provides a unified orchestration layer for multi-agent cognitive cycles, memory, and security isolation.

  • Project
    AstrBotDevs/AstrBot

    AstrBot is an open-source agent chatbot platform that connects LLMs to various instant messaging apps, featuring a plugin system, secure sandbox execution, and support for multiple AI model providers.

  • Project
    KroMiose/nekro-agent

    A highly extensible AI bot framework that enables LLMs to execute code in secure sandboxes and interact across multiple chat platforms via a unified adapter architecture.

  • Project
    agentconnect-md/agentconnect

    AgentConnect is an open‑source, self‑hosted platform that lets teams run many AI agents (Claude Code, OpenAI Codex, Grok Build, etc.) inside Slack, Discord, Telegram, Google Chat, GitHub, GitLab, Linear and other tools. Agents can call each other, keep memory, be routed by Jev, and act on webhooks or schedules. The system consists of Daemons (run agents), an optional Relay, and a Control‑Plane UI for config, auth and observability. It ships via Docker‑Compose for local use and a Helm chart for Kubernetes, all under Apache‑2.0.

  • Project
    fuyuxiang/echo-agent

    Echo Agent is an open‑source, self‑hosted AI‑agent runtime that provides long‑term memory, automatic skill extraction/evolution, and pluggable tool integration. It can run interactively in a terminal, as a long‑living Gateway service with a web dashboard and API, or be embedded in a desktop application (EchoAgent Desktop). The core runtime manages the agent loop, session context, model routing, permissions, and automation channels, while the memory system recalls past facts and the evolution system turns execution traces into reusable Skills. Install via `pip install "echo-agent[all]"`, configure an LLM API key, and start with `echo-agent run` or `echo-agent gateway`.