🎉 gald3r v5.0.57 is out — gald3r 5.0.57 — choose one recommended download for your computer..See release notes →
Gald3r

Quickstart

Install gald3r's signed binary in any project and run your first commands in under 10 minutes.

Full install + first-run walkthrough

Prerequisites

  • • Nothing to install first — gald3r is a single signed binary (Windows, macOS, Linux). No Python, no Docker, no git clone.
  • • Any supported AI coding tool: Cursor, Claude Code, Gemini CLI, Codex, OpenCode, or Copilot (optional — the bare CLI works standalone too)
1

Install gald3r

gald3r --version

Download the installer for your OS from the Gald3r-Labs/gald3r_core releases page — gald3r-windows-x86_64.msi on Windows, gald3r-macos-arm64.pkg on macOS, gald3r-linux-x86_64.tar.gz (with install.sh) on Linux — run it, then confirm in a fresh terminal. No Python, no Docker, no build step. Upgrades later are one command: gald3r install update.

2

Scaffold a project

gald3r setup

Run from your project root. Creates a .gald3r/ folder with TASKS.md, PROJECT.md, PLAN.md, CONSTRAINTS.md, BUGS.md, and an initial config.

3

Open your IDE of choice

gald3r platform install claude

gald3r platform install <name> writes that platform's overlay into your project. gald3r works with Cursor, Claude Code, Gemini CLI, OpenAI Codex, GitHub Copilot, and 32 other platforms — the same .gald3r/ folder is read by all of them, so you can switch tools mid-task without losing context.

4

Create your first task

gald3r task add "Your feature or bug here"

Or /g-task-add in Claude Code, @g-task-add in Cursor. Creates a task spec file in .gald3r/tasks/ with acceptance criteria, status history, and metadata. Tasks are plain markdown — readable by agents and humans alike.

5

Implement against the spec

gald3r go-code

Or /g-go-code / @g-go-code. Reads the task spec, implements against the acceptance criteria, and gates completion behind a fresh independent reviewer. The implementing agent cannot mark its own work done.

6

Check what's open

gald3r status

Shows active tasks by priority, blocked items, recent completions, and next recommended actions.

What gets installed

.gald3r/
├── TASKS.md          ← active task index
├── PROJECT.md        ← mission, goals, project linking
├── PLAN.md           ← master strategy and roadmap
├── CONSTRAINTS.md    ← guardrails agents must never violate
├── BUGS.md           ← bug registry (zero-ignore policy)
├── config/           ← agent config, sprint, KPI settings
├── tasks/            ← individual task spec files
└── bugs/             ← individual bug spec files

.cursor/  (or .claude/, .gemini/, etc. -- via gald3r platform install)
└── commands/, rules/, skills/, agents/, hooks/

All files are plain markdown. No database required for the file-first surface. Commit them to git — your task history is version-controlled alongside your code.

Explore Commands →How gald3r works →