Leonxlnx/tastecode

Personal Harness - a beautiful, adaptive control panel for AI coding agents. Windows-first, design-agent powered.

What it solves

TasteCode provides a centralized local desktop workspace for managing multiple AI coding agents. It eliminates the need to jump between different tools by integrating various agent providers into a single interface while keeping project state, terminal access, and history on the user's local machine.

How it works

The application acts as a local orchestration layer. It connects to supported provider CLIs (such as Codex, Claude Code, and Grok) installed on the user's machine. A local server manages the state and orchestration, ensuring that credentials stay with the provider or the OS credential store rather than being handled by the renderer.

Who it’s for

Developers who use multiple AI coding agents and want a unified, local-first environment that includes integrated terminal access, browser previews, and version control context.

Highlights

  • Multi-Agent Support: Integrates Codex, Claude Code, and Grok in one app.
  • Design Mode: Built-in capability for inspecting and editing web interfaces.
  • Local-First Security: Orchestration and state are kept local; raw credentials are not passed to the renderer.
  • Developer Tooling: Includes readable diffs, project checkpoints, git context, and session search.

Related

  • Project
    GRCEngClub/claude-grc-engineering

    An open-source GRC engineering toolkit for Claude that automates evidence collection, gap assessment, and remediation across multiple compliance frameworks.

  • Project
    stephenleo/cship

    A customizable, Rust-based statusline for Claude Code that displays real-time session cost, context usage, and API limits.

  • Project
    ghostsecurity/skills

    A plugin marketplace for Claude Code that provides AI-orchestrated application security tools to find, validate, and fix vulnerabilities in code.

  • Project
    Community-Access/accessibility-agents

    A collection of agent skills for AI coding assistants that enforces WCAG 2.2 AA accessibility standards by auditing code, blocking unreviewed edits, and running local accessibility scans.