Kuberwastaken/claurst

Agentic Coding for Builders who Ship

What it solves

Claurst provides a fast, memory-efficient, and privacy-focused terminal-based coding agent. It allows developers to have an AI pair programmer directly in their command line or integrated into their editor, eliminating the need for proprietary tracking or telemetry while supporting multiple AI providers.

How it works

Built from the ground up in Rust, Claurst implements a clean-room reimplementation of agentic coding behaviors. It operates as a Terminal User Interface (TUI) and supports the Agent Client Protocol (ACP), enabling it to function as a subprocess for ACP-compatible editors like Zed or Neovim. It uses a plan-delegate-integrate-verify workflow for complex tasks and can manage multi-turn objectives through a goal-setting system.

Who it’s for

It is designed for builders and developers who want a high-performance, open-source coding agent that can be run locally and integrated into their existing terminal or editor workflows.

Highlights

  • Multi-provider support: Works with various AI providers and includes a "Free Mode" for accessible agentic coding.
  • Agentic Workflows: Features "ultracode" for high-effort reasoning using subagents, swarms, and background tasks.
  • Editor Integration: Fully compatible with the Agent Client Protocol (ACP) for native chat UI integration in editors.
  • Advanced Session Management: Supports chat forking, memory consolidation, and sharing sessions via GitHub Gists.
  • Goal-Oriented: The /goal command allows the agent to persist on an objective across multiple turns.

Related

  • Project
    charmbracelet/crush

    Crush is a cross‑platform terminal application that lets you converse with any LLM (OpenAI, Anthropic, local Ollama, etc.) to write, edit, and run code. It supports multiple sessions, LSP‑based code understanding, extensible tool back‑ends via Model Context Protocol, and a Bash‑style `crushrc` for per‑project or global configuration.

  • Project
    opendev-to/opendev

    An open-source, Rust-based coding agent that uses a compound AI system to orchestrate parallel agents and mix multiple LLM providers per workflow.

  • Project
    AntigmaLabs/ante

    A high-performance, self-contained Rust-based coding agent for the terminal that supports both cloud LLMs and native offline local inference.

  • Project
    Dicklesworthstone/pi_agent_rust

    A native Rust-based AI coding agent CLI that provides a high-performance, secure, and resource-efficient alternative to managed-runtime AI assistants.

  • Project
    ultraworkers/claw-code

    A Rust-based CLI agent harness that allows users to run AI coding agents locally with support for multiple LLM providers.