nullclaw/nullhub

Management console for the Null ecosystem — install, configure, and monitor AI agents, orchestration workflows, task pipelines, and system health

What it solves

NullHub provides a centralized management layer for the NullClaw ecosystem. It eliminates the manual effort of installing, configuring, and monitoring multiple related AI components (like NullClaw, NullBoiler, NullTickets, and NullWatch) by providing a single interface to handle their lifecycle.

How it works

It is a single binary written in Zig with an embedded Svelte web UI. It uses a manifest-driven engine to interpret nullhub-manifest.json files, which tell it how to install, launch, and health-check specific components. It acts as a process supervisor for these components and a reverse proxy for their APIs, allowing a user to manage workflows, view logs, and monitor agent traces from one dashboard.

Who it’s for

Developers and operators using the NullClaw ecosystem who need a simplified way to deploy and orchestrate multiple AI agent components and their supporting infrastructure locally.

Highlights

  • Unified Management: Install wizard, process supervision (start/stop/restart), and health monitoring for all ecosystem components.
  • Integrated Tooling: Built-in UI for NullBoiler workflow editing, NullTickets key-value store browsing, and NullWatch flight recording for trace and cost analysis.
  • Mission Control: A specialized local-first replay system for agent missions, allowing users to execute, fork from checkpoints, and analyze failure/recovery scenarios.
  • Hybrid Interface: Offers both a browser-based dashboard for human interaction and a CLI for automation.
  • Config & Log Management: Structured editors for component configurations and live SSE streaming for instance logs.

Related

  • Project
    nullclaw/nullclaw

    A tiny, high-performance AI assistant infrastructure written in Zig that enables autonomous agents to run on minimal hardware with near-zero overhead.

  • 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
    antoinersx/clawhost

    An open-source cloud hosting platform that enables one-click deployment and management of dedicated VPS instances for AI agent runtimes like OpenClaw and Hermes.

  • Project
    qingchencloud/clawpanel

    A visual management panel for AI Agent frameworks like OpenClaw, Hermes Agent, and DeepSeek Harness, featuring a built-in AI assistant for system diagnosis and configuration.

  • Project
    chenjigang4167/testhub_platform

    TestHub is an open‑source, AI‑enhanced test‑management system built with Django (backend) and Vue 3 (frontend). It covers requirement analysis, test‑case creation & review, API testing, web‑UI automation (Selenium/Playwright), Android automation (Airtest), performance testing (Locust), and a data‑factory toolbox. AI models (OpenAI, Anthropic, Gemini, etc.) can auto‑generate cases and drive browsers via a “smart mode”. The stack uses MySQL, Redis, Celery, Channels, JWT auth, and Allure reporting. The README provides full install steps, Docker support, and contribution guidelines.