Back to directory

ZeroClaw

A fully autonomous AI assistant runtime written entirely in Rust, distributed as a roughly 3.4 MB static binary with no Node.js runtime required, designed to run on low-power hardware.

ZeroClaw

ZeroClaw is an autonomous agent runtime built to be small and provider-agnostic, contrasting itself with Node.js-based alternatives that carry a much larger runtime overhead. It ships as a static binary with every subsystem structured as a trait, so backends and integrations can be swapped without changing the core.

It builds with a standard Rust toolchain and, on low-memory devices such as a Raspberry Pi, defaults to a single-codegen-unit release build for compatibility, with a faster release profile available on more capable machines. An optional Docker-based sandboxed runtime is supported for isolating tool execution, and the project documents exact commands for reproducing its own resource-usage measurements.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.