Skip to content

Latest commit

 

History

History
396 lines (294 loc) · 9.73 KB

File metadata and controls

396 lines (294 loc) · 9.73 KB

JAT Quick Start Guide

Get from zero to orchestrating AI agents in 5 minutes

The 10X Boost in 5 Steps

Andrej Karpathy said it best: you could be 10X more powerful with AI agents if you could just string together what's available. JAT is that string.


Step 1: Install Prerequisites (2 min)

# Linux (Arch/Manjaro)
sudo pacman -S tmux sqlite jq nodejs npm

# Linux (Debian/Ubuntu)
sudo apt install tmux sqlite3 jq nodejs npm

# macOS
brew install tmux sqlite jq node

Why these?

  • tmux - Agent sessions run here (IDE tracks them)
  • sqlite3 - Agent Registry database (coordination)
  • jq - JSON processing (tool outputs)
  • node/npm - IDE and browser automation

Step 2: Install JAT (1 min)

# One-line installer (works on Linux and macOS)
curl -fsSL https://raw.githubusercontent.com/joewinke/jat/master/install.sh | bash

This symlinks all tools to ~/.local/bin/:

  • jt-* - JAT Tasks CLI
  • am-* - Agent Registry (4 commands)
  • browser-* - Browser automation (11 commands)
  • db-* - Database tools (4 commands)
  • jat-* - JAT signals and launchers

Reload your shell:

source ~/.bashrc  # or ~/.zshrc on macOS

Verify:

am-whoami    # Should show "Not registered" (expected)
jt --version # Should show version number

Step 3: Initialize a Project (30 sec)

cd ~/code/myproject
jt init

Answer the prompts (or press Enter for defaults):

  • Project name: myproject
  • Default priority: 2 (Medium)
  • Task prefix: mp (e.g., mp-001, mp-002)

This creates .jat/ directory - git-backed task tracking.


Step 4: Start the IDE (30 sec)

jat

This:

  1. Checks dependencies (npm install if needed)
  2. Starts SvelteKit dev server (port 3333 by default)
  3. Opens browser to http://localhost:3333

You should see:

  • Empty Work page (no active sessions yet)
  • Navigation: Tasks, Work, Files, Servers, Agents, Config

Step 5: Launch Your First Agent (1 min)

Option A: Via IDE (Recommended for First Time)

  1. Go to Tasks page
  2. Click "Create Task" button
  3. Fill in:
    • Title: "Add authentication"
    • Type: task
    • Priority: P2 (Medium)
  4. Click "Create"
  5. Go to Work page
  6. Click "Start Next" dropdown → Select your new task
  7. Watch agent spawn in tmux session

Option B: Via CLI (Faster for Repeat Use)

# Single agent
jat-myproject

# Multiple agents in auto-attack mode
jat myproject 4 --auto

What happens:

  1. Tmux session created: jat-{AgentName}
  2. Claude Code starts in session
  3. Agent runs /jat:start (picks highest priority task)
  4. IDE shows live terminal output
  5. Session state updates in real-time

You're Now Orchestrating AI Agents! 🎉

What you have:

  • ✅ Visual IDE showing all agent sessions
  • ✅ Task management (create, assign, track)
  • ✅ Live terminal output per agent
  • ✅ Code editor (/files page)
  • ✅ Server controls (/servers page)
  • ✅ Token usage tracking

Configure Auto-Proceed Rules (Optional but Recommended)

Go to Config → Review Rules:

The Review Rules Matrix:

              P0        P1        P2        P3        P4
bug         review    review    review    auto      auto
feature     review    review    auto      auto      auto
task        review    auto      auto      auto      auto
chore       auto      auto      auto      auto      auto

What this means:

  • P3-P4 bugs: Agent auto-completes → spawns next task
  • P0-P2 bugs: Agent asks for review before completing
  • Click cells to toggle between auto/review

Why configure this?

  • Lets agents work overnight on low-priority items
  • You review high-priority completions
  • Balances autonomy with control

Configure Automation Rules (Optional)

Go to Config → Automation → Presets:

Install these presets:

  • API Overloaded Recovery (auto-retry with backoff)
  • Rate Limit Recovery (wait 60s, retry)
  • Network Error Recovery (detect ECONNREFUSED, retry)
  • Auto-Continue Prompts (send Enter on "Continue?" prompts)

Why these help:

  • Agents recover from transient errors automatically
  • You don't babysit stuck sessions
  • 3am rate limit? Handled.

Your First Epic Swarm (Multi-Agent Workflow)

Create an Epic

  1. Tasks page → Create Task
  2. Type: epic
  3. Title: "Add user authentication system"
  4. Description:
    - [ ] Design auth flow
    - [ ] Add login endpoint
    - [ ] Add registration endpoint
    - [ ] Add password reset
    - [ ] Write tests
    - [ ] Update documentation
    
  5. Click Create

Launch the Swarm

  1. Click the Epic's title → Opens detail drawer
  2. Click "Launch Epic Swarm" button
  3. Configure:
    • Execution mode: Parallel
    • Max concurrent: 4
    • Review threshold: P0-P1 (only review critical items)
    • Auto-spawn blocked: Yes (wait for dependencies)
  4. Click "Launch"

Watch the Magic

  • IDE converts each [ ] item into a subtask
  • 4 agents spawn simultaneously
  • Each picks a subtask (ordered by priority)
  • As tasks complete, agents auto-proceed to next task
  • Progress bar shows completion

When to intervene:

  • Agent shows "NEEDS INPUT" badge → click to answer
  • Agent shows "REVIEW" badge → check work before completing
  • Error in terminal → automation rules try recovery first

Common First-Time Issues

"Agent shows offline in IDE"

Cause: Not running in tmux

Fix:

# Don't run:
claude "/jat:start"  # ❌ No tmux, IDE can't track

# Do run:
jat-myproject        # ✅ Launcher creates tmux session

"IDE says 'No projects found'"

Cause: Haven't run jt init in your project

Fix:

cd ~/code/myproject
jt init
# Refresh IDE

"Browser automation tools not found"

Cause: npm dependencies not installed

Fix:

cd ~/code/jat/tools/browser
npm install

"Agents cost too much"

Check usage:

  • IDE → Agent card → Shows tokens + cost today/week
  • Adjust review rules to require more human review
  • Set max concurrent lower (fewer agents = less cost)

Typical costs:

  • 100K tokens/day ≈ $0.30/day
  • 1M tokens/day ≈ $3/day
  • 10M tokens/day ≈ $30/day

Next Steps

Level 1: Single Agent (you just did this ✅)

  • Launch one agent on one task
  • Watch it work in IDE
  • Review and complete

Level 2: Auto-Proceed

  • Configure review rules matrix
  • Let agents auto-complete low-priority tasks
  • Wake up to finished backlog

Level 3: Epic Swarm

  • Create epic with 10+ subtasks
  • Launch 4-8 agents in parallel
  • Track progress in real-time

Level 4: Custom Automation

  • Write custom automation rules (regex patterns)
  • Template variables with capture groups
  • Project-specific error handling

Level 5: Multi-Project

  • Initialize multiple projects (~/code/project1, ~/code/project2)
  • IDE shows all projects
  • Swarm attack across projects

Key Keyboard Shortcuts

Every route with a list, table, or grid supports vim-style j/k navigation. Press ? anywhere for the full route-specific overlay.

Shortcut Action Context
j / k (or / ) Navigate list / rows / cards Any route
Enter Open focused item Any route
? Show shortcut overlay Any route
Esc Clear focus / close overlay Any route
Alt+N Create new task Global
Alt+E Open Epic Swarm modal Global
Alt+S Start next task Global
Alt+A Attach to session Hovered session (Work page)
Alt+K Kill session Hovered session
Alt+1 to Alt+9 Jump to session Work page
Cmd+K Command palette Global

Full per-route reference: ide/docs/keyboard-navigation.md.


Essential Commands

IDE

jat                             # Launch IDE

Project Management

jat init                        # Auto-discover ~/code/* projects
jat add <path>                  # Add project manually
jat list                        # Show all projects

Task Management

jt ready                        # Tasks ready to work
jt create "Title" --priority 1  # Create task (P1 = High)
jt show <id>                    # View task details
jt close <id>                   # Close completed task
jt dep add <task> <blocker>     # Add dependency

Agent Coordination

am-whoami                       # Check your agent identity
am-agents                       # List all registered agents

Slash Commands (in Claude sessions)

/jat:start          Pick task, reserve files, begin work
/jat:complete       Verify, commit, close task, end session
/jat:tasktree           Convert PRD to structured tasks
/jat:verify         Run tests, lint, security checks
/jat:doctor         Diagnose and repair JAT setup

Support & Next Steps

Documentation

Having Issues?


The Bottom Line

Karpathy said programmers could be 10X more powerful if they could just string together what's available.

You just strung it together.

  • ✅ Agents orchestrated
  • ✅ IDE running
  • ✅ Tasks tracked
  • ✅ Automation configured

You're ready to claim the 10X boost. Happy orchestrating! 🚀

Full Docs | README | Issues