fastclaw-ai/fastclaw

Multi-Agent Framework

What it solves

FastClaw provides a lightweight, single-binary runtime for creating and managing AI agents. It eliminates the complexity of manually setting up LLM connections, tool execution environments, and session management, allowing users to deploy agents with distinct personalities, memories, and skills quickly.

How it works

FastClaw acts as an "Agent Factory" that manages agents via a central database (SQLite by default) and a filesystem for skills. It handles the communication between various LLM providers and the agents, executes tools within isolated sandboxes (Docker or E2B), and manages conversation history and long-term memory through specific system files like SOUL.md and MEMORY.md. It offers a web dashboard for configuration and a CLI for automation.

Who it’s for

It is designed for developers and organizations who want to host their own AI agent infrastructure, integrate agents into messaging platforms like Telegram, Discord, or Slack, or build multi-tenant applications where agents are provisioned for end-users.

Highlights

  • Multi-LLM Support: Compatible with OpenAI, Anthropic, Ollama, OpenRouter, Groq, DeepSeek, and Mistral.
  • Sandbox Isolation: Supports Docker and E2B cloud sandboxes to safely execute code and manage files.
  • Omnichannel Integration: Built-in bindings for Telegram, Discord, and Slack bots.
  • Extensible Skills: Ability to install shared skills from ClawHub or GitHub and create agent-private skills.
  • Agent Management: Comprehensive dashboard for editing agent personalities, managing cron-based schedules, and overseeing sessions.
  • Developer Friendly: Provides an OpenAI-compatible API and a plugin system using JSON-RPC subprocesses.

Related

  • Project
    nextlevelbuilder/goclaw

    A multi-tenant AI agent platform built in Go that provides a gateway for managing agents across 20+ LLM providers and 7 messaging channels.

  • Project
    swarmclawai/swarmclaw

    A self-hosted AI agent runtime and multi-agent framework for creating autonomous agent swarms with durable memory, scheduling, and multi-provider LLM support.

  • Project
    zeroclaw-labs/zeroclaw

    A self-hosted AI agent runtime written in Rust that connects various LLM providers to multiple communication channels and local system tools while prioritizing user data ownership.

  • Project
    qhkm/zeptoclaw

    A fast, secure, and local-first personal AI assistant infrastructure written in Rust, providing sandboxed autonomy and multi-provider LLM support in a single 6MB binary.

  • Project
    microclaw/microclaw

    A self-hosted Rust agent platform providing a durable execution runtime for long-running AI tasks across a server-based automation backend and a native desktop workspace.