px0-ai/px0

px0 is a review workbench and speed-first IDE built for AI-generated code. It turns your browser into a zero-latency console with native Git and GitHub integrations, instant search across massive codebases, in-place quick fixes, and seamless handoff to local AI coding harnesses.

What it solves

px0 is designed to solve the bottleneck of reviewing AI-generated code. As AI agents author code faster than humans can read it, traditional heavy IDEs can be slow and resource-intensive. px0 provides a lightweight, high-speed environment specifically optimized for the review, navigation, and verification loop of agent-authored changes.

How it works

It operates as a single static Go binary that runs a lightweight server daemon (consuming very little RAM) and renders the UI in a web browser. This architecture avoids the overhead of Electron-based editors. It includes native Git and GitHub integrations for PR reviews and diff inspections, and integrates with AI coding harnesses (like Claude Code, Aider, and Cursor Agent) to allow for live reloading of edits.

Who it’s for

It is built for software engineers and engineering teams who use AI coding agents to generate large volumes of code and need a fast, distraction-free tool for verifying those changes.

Highlights

  • Extreme Performance: Cold starts in under 1ms and a total memory footprint significantly lower than VS Code.
  • AI Harness Integration: Direct dispatch of edits to tools like Claude Code, Gemini CLI, and Aider.
  • GitHub Integration: Review pull requests directly via URL and manage Git operations from the browser.
  • Remote-First: Can be run on remote servers or containers without needing complex SSH setups.
  • Virtual Rendering: Smoothly handles massive files (up to 400,000 lines) by only mounting visible rows.

Related

  • Project
    smallnest/pigo

    pigo is a Go‑based CLI AI coding assistant (a clone of the pi agent) that can read/write files, run shell commands, fetch web content, and interact with many LLM providers. It works in headless script mode or an interactive REPL, supports tool‑level allow/deny lists, project trust, prompt templates, skills, plugins, self‑update, and provides a Go SDK for embedding.

  • Project
    Twigpine/zero

    Zero is a Go‑based terminal AI coding agent that lets you pick any LLM (OpenAI, Anthropic, local Ollama, etc.) to inspect, edit, and run code in your repository. It offers a rich TUI, a scriptable `zero exec` mode, sandboxed permissions, persistent local sessions, and extensibility via plugins and MCP servers. Install via npm, a one‑line script, or by building from source, and keep full control over what files or commands the agent can access.

  • Project
    LiuMengxuan04/MiniCode

    MiniCode is a small, terminal‑first AI coding assistant that implements a Claude‑Code‑style model‑tool‑model loop. It lets you issue natural‑language requests, runs built‑in tools (file edit, search, shell, web fetch), maintains in‑memory plans/goals, and shows a full‑screen TUI where you approve changes before they’re written. Designed for learning and extensibility, it runs locally via Anthropic/Claude or any model exposed through the Sidrune AI unified API.

  • Project
    Edge0-AI/Edge0

    Edge0 is an open-source inference framework that allows large sparse-MoE models to run on consumer devices by streaming expert weights from storage and using predictive routing to maintain high performance.

  • Dispatch
    Paseo: An Open-Source Unified Interface for Coding Agents

    Paseo is an open-source, self-hosted interface that allows developers to manage and orchestrate multiple coding agents like Claude Code, Codex, and Copilot across mobile, desktop, and CLI environments.