Teammates

An AI teammate is a persistent AI companion that lives in your Agor workspace. While a normal branch is where code gets written, an AI teammate is a who — a persistent entity with memory, skills, and the ability to orchestrate work across your entire workspace.

A real Agor instance with a curated mix of coding, ops, and business teammates — each callable from any session via the agor_teammates_list MCP tool.

The teammate framework is heavily inspired by OpenClaw , a proven pattern for building persistent AI agents with file-based memory and identity. Agor’s implementation adapts the core ideas — markdown-based memory, identity files, and scheduled loops — while making the teammate deeply aware of its environment through Agor’s MCP tools. An Agor teammate can create branches, spawn sessions, manage boards, and coordinate multi-agent workflows — capabilities that go well beyond the original pattern.

Framework repository: github.com/preset-io/agor-teammate 

How it works

An AI teammate is a special branch backed by the framework repository — a template repo containing memory files, identity configuration, skills, and task templates. When you create a teammate, Agor:

1. Forks the framework repo into a new branch
2. Tags the branch with teammate metadata (name, framework version)
3. Creates a dedicated board for the teammate’s work
4. Launches your first session — triggering BOOTSTRAP.md

From there, every session in that branch picks up the teammate’s accumulated memory and context.

Key concepts

BOOTSTRAP.md — First boot

When a teammate is created for the first time, it runs through BOOTSTRAP.md — the initialization script that sets up identity, preferences, and initial state. This is where the teammate introduces itself, learns about you, and configures its working environment. Think of it as the teammate’s “first day” checklist.

Memory across sessions

Teammates maintain file-based memory in their branch. Memory is organized into two layers:

Identity files (root of the branch):

• SOUL.md — Personality, communication style, core principles
• IDENTITY.md — Who the teammate is, its name, and purpose
• USER.md — Knowledge about you, your preferences, and patterns

Daily memory (memory/ directory):

• memory/{YYYY-MM-DD}.md — Daily journal entries. Each day the teammate works, it appends observations, decisions, and learnings to that day’s file. This creates a chronological, searchable record of everything the teammate has done and learned.

Each new session reads the identity files and recent memory, giving the teammate continuity across conversations. As the teammate works, it updates these files — building a richer understanding over time. All memory is plain markdown — fully inspectable, editable, and version-controlled.

BOARD.md — Resident board semantics

Every teammate has a BOARD.md file that describes the semantics of its main (resident) board. This file tells the teammate what each zone on the board means, how branches should be organized spatially, and what the overall layout represents. When the teammate creates or moves branches on its board, it refers to BOARD.md to understand the intended structure — ensuring consistent spatial organization across sessions.

HEARTBEAT.md — Scheduled tick workflows

HEARTBEAT.md contains the instructions and workflows the teammate processes every time a scheduled tick occurs. Think of it as a flowchart in pseudo-code: a set of steps the teammate follows on each heartbeat, such as:

• Check the status of in-progress branches
• Review BOARD.md to assess spatial organization
• Look for new issues or PRs to triage
• Summarize progress to daily memory (memory/{YYYY-MM-DD}.md)
• Start new work based on priorities

Configure heartbeat frequency through Agor’s scheduler — from every few minutes to once a day.

Skills

Teammates aren’t limited to code generation — they can be equipped with skills that extend their capabilities through tools, APIs, and integrations. Skills are defined in the framework repo and give your teammate the ability to interact with external systems.

Examples of what skills enable:

• SaaS integrations — Query Jira for open tickets, post updates to Linear, fetch metrics from Datadog or PagerDuty
• Communication — Send Slack messages, create GitHub issues, post comments on PRs
• CLI tools — Run linters, test suites, deployment scripts, or any command-line tooling in your stack
• REST APIs — Call internal or external APIs to fetch data, trigger webhooks, or sync state
• MCP servers — Connect to any MCP-compatible service for specialized capabilities (databases, cloud providers, monitoring systems)

Skills make teammates practical for real workflows — not just coding, but the coordination and communication around it.

Workspace orchestration

Through Agor’s MCP tools, teammates can:

• Create branches — Spin up new isolated work environments for specific tasks
• Spawn sessions — Delegate work to child sessions with focused prompts
• Manage boards — Organize branches across spatial canvases (guided by BOARD.md)
• Check on work — Review session status, read files, assess progress

This makes teammates natural orchestrators — they can break down complex tasks, distribute work across multiple branches, and synthesize results.

Learning and adaptation

As your teammate works with you, it naturally improves:

• Learns your coding patterns and preferences (stored in USER.md)
• Understands your repository structure and conventions
• Builds knowledge about your team’s workflows (daily memory)
• Adapts its communication style to match yours (refined in SOUL.md)

Creating a teammate

From the onboarding wizard

When you first log into Agor, choose “Set up your AI teammate”. The wizard will:

1. Clone the teammate framework repository 
2. Create a personal board
3. Set up a branch with your own branch
4. Configure API keys
5. Launch your first session (which runs BOOTSTRAP.md)

From Settings

Go to Settings > Teammates > Create AI teammate:

1. Enter a display name (e.g., “PR Reviewer”, “Command Center”)
2. Choose or create a board
3. Optionally customize the framework repo and branch
4. Click Create

From the CLI

During agor init, you’ll be prompted to set up a teammate. This queues the setup for the UI wizard on your next login.

Teammate vs. Agent

These terms mean different things in Agor:

A teammate uses an agent to do its work. When you create a session for your teammate, you choose which agent runs it (Claude Code is the default).

Think of it this way:

• “Start my teammate” = open a session on your persistent AI companion’s branch
• “Choose an agent” = pick which AI model/tool runs that session

Managing teammates

Settings > Teammates

The Teammates table in Settings shows all your teammates with:

• Display name and branch name
• Environment status (start/stop controls)
• Framework repository
• Branch and session count

BranchModal > Teammate tab

Click any teammate’s branch card to open its modal. The Teammate tab shows:

• Editable display name
• Framework repo and version
• Creation method (onboarding vs manual)

Boards

Teammates appear as branch cards on boards, distinguished by a robot icon and blue border. We recommend giving each teammate its own board for clarity.

Real-world examples

For real-world use cases and the story behind Agor Teammates, see our blog post: Introducing Agor Teammates.