Friday

Friday is an open-source desktop application that coordinates multiple coding agents to work together on shared software tasks.

Friday is an open-source tool that lets you run multiple coding agents like Claude Code, Codex, Cursor, and Gemini CLI simultaneously from one interface. It splits work across a shared task board, allows agents to message each other directly, and hands off tasks when an agent hits a usage limit. Designed for developers who use existing coding tools, it operates locally on your computer using your current subscriptions and sign-ins. You can review all changes, run built-in Git commands, and check tests before anything ships. The desktop app supports macOS, Windows, and Linux, and requires no account or external server for local use.

Friday at a glance

Best for: Software engineer
Runs on: macOS, Windows, Linux, Web, CLI
Pricing: Free and MIT licensed for local use; Friday Team hosted version available for multi-user sessions.
Released: October 2026
Category: AI agent tool
Website: github.com/splashxmoon/friday

Key features

Run multiple coding tools from one interface
Manage a shared task board for agent collaboration
Hand off tasks automatically when usage limits are reached
Review changes and leave line-by-line notes
Use built-in Git tools to commit, push, and open pull requests
View live feeds of messages, commands, and file changes
Add custom API keys or local models for Friday Code

Use it for

Running Claude Code and Codex simultaneously on one project
Handing off unfinished tasks between agents when limits hit
Reviewing code changes and test runs before shipping
Managing Git branches and pull requests within agent sessions

Alternatives to Friday

Runway — Control Claude Code and Codex sessions on local or cloud machines from any phone.
Agent Archive — Hand off coding sessions between Claude Code, Codex, and Cursor across machines.
CodePilot — Consolidates multiple AI agents and local model connections in one workspace.
Cc Pair — It coordinates two AI agents to author and review code changes automatically.
OpenRig — Coordinate multiple AI coding agents across long-term projects.
Claude Squad — Manages multiple AI agents in isolated git worktrees.
Claude Codex Bridge — Runs multiple AI coding agents concurrently with stable cross-provider collaboration.
agent.reviews — Real tool reviews written directly by coding agents after task completion.
Array — Runs Claude Code, Codex, and Pi side by side on one canvas.
Flash Agents — Offloads reading and typing to cheap workers while keeping Claude for review
ManyAgents — Runs multiple AI coding agents locally on your Mac with dedicated worktrees and live previews.
Reviewer Agent — It uses a separate AI model to review code and prevent premature agent stopping.

All Friday alternatives