Superagentsys/novalclaw

novalclaw is next generation AI format

What it solves

OmniNova is designed to provide enterprise-grade security for AI agents. It addresses the privacy concerns of businesses by ensuring that model keys, session data, and skills remain stored locally on the user's machine rather than on a remote server.

How it works

It operates as a local-first agent with a Rust core. It can interact with various system tools including the terminal, browser, files, and native applications. It supports a wide range of AI providers (such as OpenAI, Anthropic, and Ollama for offline models) and integrates with multiple communication channels like Slack, Discord, and Telegram.

Who it’s for

Enterprise users and security-conscious individuals who need an AI agent capable of executing system-level tasks while maintaining strict control over their data and API keys.

Highlights

  • Local-first architecture: Keeps keys and sessions on disk.
  • Tool execution: Ability to drive the shell, Git, PDF, and web browser.
  • Safety features: Includes dangerous-command filters, tool policies, and an emergency stop.
  • Broad compatibility: Supports multiple OS platforms and a variety of LLM providers, including fully offline models.

Related

  • Project
    thClaws/thClaws

    A native-Rust AI agent workspace that allows users to run multiple isolated agents for coding and automation locally on their own machine.

  • Project
    microclaw/microclaw

    MicroClaw is a self‑hosted Rust platform for AI agents that can run as a server, a native desktop “Work” app, or be embedded via an SDK. It offers multi‑step tool use, durable sessions, SQLite‑based memory, many chat channel adapters, and built‑in safety guardrails, all share‑able across its three product surfaces.

  • 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
    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
    zeroclaw-labs/zeroclaw

    A self-hosted agent runtime written in Rust that connects LLM providers to multiple communication channels and hardware tools while ensuring user ownership of data and infrastructure.