Agor: Real-Time Collaboration Hub for Multi-Agent AI Development Teams

Agor is an open‑source command center that lets multiple AI coding agents and human developers work together on a shared canvas, each on its own Git branch, with all sessions, environments, prompts, and pull requests unified in one place.

Geek Labs
Geek Labs
Geek Labs
Agor: Real-Time Collaboration Hub for Multi-Agent AI Development Teams

Agor is a newly released open‑source project that serves as a command center for a team of AI agents. It enables several coding agents such as Claude Code, Codex, and Gemini to operate simultaneously on a shared canvas, each running on a separate Git branch, while humans collaborate with the agents in real time; all conversations, development environments, prompt templates, and pull requests are consolidated.

Core Concepts

Branches : Every work task is mapped to a Git branch that stays on the whiteboard, providing its own session history, isolated development environment, and associated pull request.

Sessions & Trees : AI dialogues are non‑linear; Agor supports forking sessions so that a failed line of thought can branch out, with sub‑tasks opening sub‑sessions, forming a tree that can be revisited at any time.

Boards & Zones : A Figma‑style 2D canvas displays branch cards; dragging a card into a "zone" automatically triggers a predefined prompt template, facilitating standardized workflows.

Agor canvas interface
Agor canvas interface

Core Features

Real‑time multi‑user collaboration : Team members see each other's cursors, stacked avatars, range comments, and share a terminal; actions on any branch are visible to everyone instantly.

Multiple agents and runtimes : Within a single session, users can mix Claude Code, Codex, Gemini, OpenCode, Copilot, etc., assigning a specific agent to each session.

Persistent AI assistants : Users can create assistants with identity, memory, and skills that persist across sessions, and the published skills are available to the whole team.

Self‑hosted deployment : All data resides on the user's own server; repositories, databases, and security policies are fully controllable.

Installation

Requires Node.js version 22.12 or higher. npm install -g agor-live Initialize the environment:

agor init   # creates ~/.agor directory and database
agor daemon start   # runs in background
agor open   # opens the Web UI

The first run guides the user to add a repository and create the initial session.

Suitable Teams

Agor is most beneficial for development teams that run multiple AI coding agents concurrently and need coordinated collaboration—for example, a front‑end team using Claude Code, a back‑end team using Codex, and a QA team using Gemini—all working on the same project.

If only a single user employs a single AI tool, the value is limited; the advantage grows with larger teams and more agents.

GitHub: https://github.com/preset-io/agor<br/>Stars: 1,263+ | License: MIT | Language: TypeScript
Original Source

Signed-in readers can open the original source through BestHub's protected redirect.

Sign in to view source
Republication Notice

This article has been distilled and summarized from source material, then republished for learning and reference. If you believe it infringes your rights, please contactadmin@besthub.devand we will review it promptly.

TypeScriptAI agentsGitopen sourcecollaborationAgor
Geek Labs
Written by

Geek Labs

Daily shares of interesting GitHub open-source projects. AI tools, automation gems, technical tutorials, open-source inspiration.

0 followers
Reader feedback

How this landed with the community

Sign in to like

Rate this article

Was this worth your time?

Sign in to rate
Discussion

0 Comments

Thoughtful readers leave field notes, pushback, and hard-won operational detail here.