agor
Agor · Coding · Productivity
Agor is a multiplayer spatial canvas platform where humans and AI assistants work on the same board in real time. It's a team collaboration tool for AI workflows, giving teams persistent AI teammates with shared memory, skills, and schedules. A good workflow built once reaches everyone instead of dying in a single terminal. Sound familiar? If your team loses context between AI sessions, Agor is built to fix that.
About agor
What Is Agor
Agor is the command center for AI enablement. It's an AI team collaboration platform that puts humans and AI assistants on one shared canvas with live cursors, shared sessions, and queued follow-ups, so work stops living in private terminals that no one else can see. That visibility changes daily habits.
The product's core idea is simple: a one-off prompt doesn't compound, but a teammate does. Each AI teammate gets durable memory, a searchable knowledge namespace, and the tools your team already trusts. You teach it by talking to it, and the useful parts become reusable context the whole team can draw on. No scripting required.
The main limitation is that Agor targets teams, not solo casual users. Setup assumes you're comfortable with AI assistants, GitHub-linked worktrees, and MCP servers. A beginner looking for a simple chat box will find more machinery than they need. Know that going in.
Getting Started
- Sign in to Agor and create your workspace from the persona gallery, or start from a blank template.
- Name your first AI teammate and let the guided onboarding walk you through its identity and memory files.
- Teach the teammate by talking to it, then connect the MCP servers and channels your team already uses.
- Attach a GitHub-linked worktree so the teammate can work on real branches and isolated test environments.
- Add schedules and heartbeat tasks, then invite teammates to the shared canvas and start a session together.
Product Information
A quick look at agor's pricing, supported platforms, and performance.
Best for
The users, tasks, and scenarios where this tool fits best.
Users
- Engineering teams
- AI enablement leads
- Ops and business teams
Tasks
- Running scheduled audits and daily digests
- Coordinating multi-agent workflows
- Building reusable AI workflows
Scenarios
- A team tired of AI wins dying in personal terminals
- Early-stage AI adoption where nobody knows which work paid off
- Multi-model setups that don't want to marry one provider
Key features
Multiplayer Spatial Canvas
Humans and AI teammates share one board with live cursors, shared sessions, and queued follow-ups. You can watch an assistant work, jump in mid-task, and leave a note for the next session. That visibility is the whole point. AI stops being a black box in someone's terminal.
Persistent AI Teammates
Each teammate is a durable entity with memory, skills, and team-wide reach, not a throwaway prompt. Every session in that teammate's branch picks up its accumulated memory and context, so it gets more useful over time. The framework draws on file-based memory and identity patterns familiar from OpenClaw. Think less chatbot, more colleague.
Shared Knowledge Namespaces
Every teammate gets a namespace in the knowledge base that's semantically searchable and shared with the team. Instead of answering confidently without your business context, a teammate can pull from durable, team-owned documents. That matters most when you have scattered repos, docs, and DMs. Context wins.
Skills and MCP Connections
You can package repeatable workflows as skills and connect teammates to the MCP servers your team already trusts. That means a teammate can use the same internal tools as your engineers rather than a separate, weaker stack. It's how a working setup spreads from one person to the whole org.
GitHub-Linked Worktrees
Teammates work against GitHub-linked worktrees and isolated test environments, so experiments don't touch your main branch. You get a place to try changes safely before they land. Teams that review code carefully will appreciate the isolation more than casual users will. Fair warning.
Scheduled Agency
Heartbeats, daily standups, audits, and digests run on their own schedule without waiting for a prompt. Longer workflows can chain across a day or a week. This is AI workflow automation that keeps running while you sleep. The upside is quiet reliability. The trade-off? You need to actually configure the schedules.
Gateway Channels
Teammates reach you through Slack, GitHub, or wherever work already happens via gateway channels. You don't have to move your team into a new chat app to get value. That lowers the switching cost when you're testing whether AI fits your process. Worth trying.
Pros and cons
Pros
- Shared canvas keeps humans and AI assistants on the same visible board, so AI work stops disappearing into personal terminals.
- Persistent teammates with shared memory and knowledge namespaces carry context across sessions instead of restarting every prompt.
- Skills and MCP connections let teams reuse internal tools, which turns one person's working setup into everyone's.
- Scheduled workflows handle recurring tasks like audits and digests without anyone remembering to trigger them.
- Multi-model flexibility avoids locking your workflow automation to a single provider.
Cons
- Setup assumes familiarity with Git, worktrees, and MCP servers, which is heavy for beginners who just want a chat box.
- The team-first design means individuals get less value from it than groups do. Solo users, look elsewhere.
- Pricing details aren't clearly published on the site, so you'll likely need to contact the team to confirm costs before committing.
Frequently asked questions
Agor is a multiplayer spatial canvas for AI enablement. It lets teams work alongside persistent AI teammates that have memory, skills, and schedules, so AI-assisted work stays visible and reusable across the whole team.
Related content
Explore related tools, skills, and articles for agor.
agor Alternatives
Forefront
Forefront · CodingForefront is a web platform for building with open-source AI. It lets you fine-tune leading open-source language models on your own data, evaluate how they perform, and run them through an API or export them to host yourself. Developers who want the convenience of a closed-source platform but insist on owning their models and data are the target audience here.
Startkit
StartKit.AI · CodingStartkit is a boilerplate for building AI SaaS and AI wrapper products. Think of it as an AI startup boilerplate with the boring parts already wired up: authentication, Stripe and Lemon Squeezy payments, usage limits, transactional email, and an AI API starter that talks to OpenAI, Anthropic, Groq, or Llama. You clone the repo, set your price, and start on the part of your product that people actually pay for. It's Next.js under React and Tailwind, so most of the boilerplate code already feels familiar.
Testim
Tricentis · CodingTestim is an AI-powered test automation platform for building and running end-to-end tests across web, mobile, and Salesforce applications. It leans on machine learning to keep tests stable when an interface changes, so teams spend less time fixing broken selectors. Not bad for an automated testing tool you can start using today. You create tests by recording actions in a browser, then optionally add JavaScript when you need more control. It's a solid pick for busy QA teams.