Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

zeroclaw

zeroclaw• Pinned

zeroclaw: An agent runtime delivered as a single Rust binary you configure and run.

What problem it solves

Personal AI agents need to connect language model providers, communication channels, and tools while remaining under the user's control. They also need configurable autonomy, security boundaries, and operational features such as background services, approvals, and persistent workflows.

Key features

  • Multiple channels and providers — The agent can receive messages through configured channels and use pluggable model providers, including Anthropic, OpenAI, local Ollama, and OpenAI-compatible endpoints. Provider fallback chains and routing help maintain operation when a provider is unavailable.

    Source: README

  • Configurable autonomy and security — The default supervised mode requires approval for medium-risk operations and blocks high-risk operations. Workspace boundaries, command policies, OS-level sandboxes, and cryptographic tool receipts provide additional controls.

    Source: README

  • Tools and hardware access — The runtime can act through shell, browser, HTTP, hardware, and custom MCP server tools. Hardware integrations include GPIO, I2C, SPI, and USB through the `Peripheral` trait.

    Source: README, crates/zeroclaw-tools

  • Gateway and dashboard — An HTTP and WebSocket gateway connects clients to the runtime. Its web dashboard supports chat, memory browsing, configuration editing, cron management, and tool inspection.

    Source: README, crates/zeroclaw-gateway

  • Event-triggered procedures — Standard Operating Procedures can be triggered by MQTT, webhooks, cron, or peripheral events. Runs include approval gates and can be resumed.

    Source: README, crates/zeroclaw-sop-graph

Quick start

Copied verbatim from the project's README.

curl -fsSL https://raw.githubusercontent.com/zeroclaw-labs/zeroclaw/master/install.sh | sh
"${CARGO_HOME:-$HOME/.cargo}/bin/zeroclaw" quickstart
zeroclaw quickstart               # one-shot setup: pick a provider, write a working config
zeroclaw agent -a <alias>         # interactive chat using the [agents.<alias>] entry
zeroclaw service install          # register as systemd/launchctl/Windows Service
zeroclaw service start            # run it always-on in the background

Who it may suit

This project may suit developers and operators who want to run a self-hosted, configurable personal AI agent across messaging services, local tools, and supported hardware.

Topics to discuss

  • Which channel or provider integration would be most useful to add next?

  • How should supervised autonomy and approval policies evolve for local agent workloads?

  • What kind of Standard Operating Procedure or hardware workflow would you build with this runtime?

Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/zeroclaw-labs/zeroclaw#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.

github.comhttps://github.com/zeroclaw-labs/zeroclaw

Comments

…