crewly weekly downloads statistics

Crewly

Website: crewlyai.com

Your judgment, run by an AI crew.

You're closest to the problem. Crewly gives you an AI crew that works the way you'd decide — even when you're not in the room.

Under the hood, Crewly is an open-source multi-agent orchestration platform that coordinates AI coding agents (Claude Code, Gemini CLI, Codex, OpenCode) to work together as a team. It provides a web dashboard for real-time monitoring, task management, and team coordination — all running locally on your machine.

Features

• Multi-agent teams — Create teams with different roles (developer, QA, PM, orchestrator) and watch them collaborate • Multi-runtime support — Use Claude Code, Gemini CLI, OpenAI Codex, or OpenCode — mix and match per agent • Real-time dashboard — Monitor all agents through live terminal streams, task boards, and activity feeds • Skill system — Agents coordinate through bash skills (report status, delegate tasks, manage memory) • Agent memory — Persistent knowledge that agents build and share across sessions • Slack integration — Optional two-way Slack bridge for team notifications • Local-first — Everything runs on your machine. No data leaves your environment.

Quick Start

The installer needs no sudo: if your global npm folder is not writable (a system Node on Linux), it installs Crewly under ~/.crewly/npm-global and adds that to your PATH. Then it runs the setup wizard (the same as crewly init). When it finishes, open a new terminal and run:

Prefer npm? With Node from nvm, fnm or Homebrew (your user owns the global npm folder):

EACCES: permission denied from npm install -g on Linux? A system Node (from apt, NodeSource or the official Docker images) keeps its global packages under /usr/local, which a normal user cannot write. Do not use sudo. Install into your home folder instead, which is what the installer script does, and crewly upgrade keeps using that folder:

The init command walks you through provider selection, installs agent skills, and scaffolds a .crewly/ directory. Then crewly start launches the backend server and prints the web dashboard URL (add --open or set CREWLY_OPEN_BROWSER=1 to open it). From there:

1. Create a team with agents assigned to roles 2. Assign the team to a project (any local code directory) 3. Watch agents work in real time through live terminal streams

Requirements

• Node.js 22 or later (with npm). Node 20 is end-of-life and its better-sqlite3 has no prebuilt binary. • No C/C++ toolchain on macOS (x64/arm64) or glibc Linux (x64/arm64). The native modules install from prebuilt binaries there. You do need python3, make and g++ (Xcode Command Line Tools on macOS) in these cases: • Alpine/musl, glibc older than 2.28, or other architectures, where node-pty compiles from source • a network that blocks the prebuilt download: better-sqlite3 fetches its binary from GitHub at install time and compiles from source if it cannot

On Debian/Ubuntu, install the toolchain with sudo apt-get install -y python3 make g++. crewly doctor tells you whether you need it. • jq (brew install jq on macOS, sudo apt-get install -y jq on Debian/Ubuntu). Agent skills use it, and crewly init stops if it is missing. • curl • One AI coding CLI, installed and logged in: Claude Code (claude), Gemini CLI (gemini) or Codex (codex). OpenCode also works. • A normal user account, not root. Run Crewly as a normal user, not with sudo or as root. Claude Code refuses to start its agents under root.

tmux is not required.

| Runtime | Install | Verify |

| Claude Code (default) | npm install -g @anthropic-ai/claude-code | claude --version | | Gemini CLI | npm install -g @google/gemini-cli | gemini --version | | Codex (OpenAI) | npm install -g @openai/codex | codex --version | | OpenCode | npm install -g opencode-ai | opencode --version |

API keys: Gemini CLI requires GEMINI_API_KEY. On a Gemini agent's first run, answer its two terminal prompts: authentication (Use Gemini API Key) and folder trust (Yes). Codex requires an OpenAI API key. Claude Code: run claude once in a terminal, finish its first-run setup (choose a theme) and log in before you start a team. A Claude agent cannot get past those screens on its own. OpenCode uses whichever provider you connect via opencode auth login (or the ANTHROPIC_API_KEY / OPENAI_API_KEY / GEMINI_API_KEY env vars Crewly already exports to agent sessions).

Architecture

How It Works

1. You create a team in the dashboard with agents assigned to roles 2. You assign the team to a project (any local code directory) 3. Crewly launches each agent as a CLI process in its own PTY session 4. Agents receive role-specific prompts and use skills (bash scripts) to communicate, report progress, and manage tasks 5. You monitor everything in real time through the web dashboard

Agent Runtimes

| Runtime | Default Command | Notes |

| Claude Code | claude --dangerously-skip-permissions | Default runtime | | Gemini CLI | gemini --yolo | Requires GEMINI_API_KEY | | Codex (OpenAI) | codex -a never -s danger-full-access | Requires OpenAI API key | | OpenCode | opencode --auto | Any provider/model (-m provider/model); reads AGENTS.md; auth via opencode auth login |

You can change the default runtime or customize launch commands in Settings.

CLI Commands

Configuration

Optional environment variables (.env file or shell):

Slack

One click (recommended). Log in to Crewly Cloud (Settings → Cloud), open Settings → Integrations → Slack and press Connect Slack. Slack asks you to approve the Crewly app once; from then on every Crewly instance signed in to the same Crewly account gets Slack automatically — team channels, and one real Slack bot user per agent — with no tokens to copy. The instance pulls its config from Cloud on boot and every 10 minutes (cached 0600 at ~/.crewly/slack-cloud-config.json); Slack events reach it through the Cloud relay, so no Socket Mode connection is opened.…

Description from the npm listing.