nextlevelbuilder/goclaw

GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deploy AI agent teams at scale without compromising on safety.

What it solves

GoClaw is a multi-tenant AI agent platform that provides a unified gateway for deploying and managing multiple AI agents across various messaging channels. It solves the complexity of managing multiple LLM providers, user isolation (multi-tenancy), and agent orchestration in a single, production-ready binary.

How it works

Built in Go, the platform uses an 8-stage agent pipeline (context, history, prompt, think, act, observe, memory, summarize) to process requests. It implements a 3-tier memory system (Working, Episodic, and Semantic) and a Knowledge Vault for hybrid search (FTS + pgvector). The system supports multi-tenant PostgreSQL for isolated user workspaces and encrypted API keys. It can be deployed as a server (Standard) or a native desktop app (Lite) using SQLite.

Who it’s for

Developers and organizations needing a scalable, secure AI agent gateway that can connect to 20+ LLM providers and 7 messaging channels (like Telegram, Discord, and Slack) with built-in multi-tenancy and orchestration.

Highlights

  • Multi-Agent Orchestration: Supports agent teams with shared task boards and inter-agent delegation (sync/async).
  • Extensive Provider Support: Integrates with 20+ LLM providers including Anthropic, OpenAI, Groq, and DeepSeek.
  • Multi-Channel Deployment: Connects to Telegram, Discord, Slack, Zalo, Feishu, and WhatsApp.
  • Production Security: Features a 5-layer permission system, RBAC, AES-256-GCM encryption, and prompt injection detection.
  • Self-Evolution: Agents can refine their own communication style and domain expertise based on metrics and suggestions.
  • Lightweight Deployment: Distributed as a single static Go binary (~25 MB) or a native desktop app.
  • C-level Tools: Includes 30+ built-in tools for filesystem operations, web search, browser automation, and media generation.

Related

  • Project
    fastclaw-ai/fastclaw

    A lightweight AI agent runtime written in Go that allows users to create, manage, and deploy multi-agent systems with isolated sandboxes and multi-channel support.

  • 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
    wanikua/danghuangshang

    A multi-agent collaboration system based on the OpenClaw framework that organizes AI agents into a hierarchical government or corporate structure for efficient task delegation and execution.

  • Project
    johnson7788/MultiUserClaw

    MultiUserClaw is a Docker‑based SaaS framework that lets you run isolated AI assistants (Hermes agents) for many users. It includes a React front‑end, a FastAPI gateway for auth, container management and LLM proxying, per‑user Hermes containers, PostgreSQL storage, and features like knowledge bases, skill store, cron jobs, multi‑channel bots, and multi‑model support.

  • Project
    zeroclaw-labs/zeroclaw

    A self-hosted agent runtime written in Rust that lets you run a private AI assistant with local control over data, providers, and hardware interaction.