The missing control plane for AI coding agents

Agent Visualization • Zero-Lag Input Overlay • Mobile-First UI • Respawn Controller • Multi-Session Dashboard

---

Quick Start - Installation

curl -fsSL https://raw.githubusercontent.com/Ark0N/Codeman/master/install.sh | bash

This installs Node.js and tmux if missing, clones Codeman to ~/.codeman/app, and builds it. You'll need at least one AI coding CLI installed — Claude Code or OpenCode (or both). After install:

codeman web
# Open http://localhost:3000 — press Ctrl+Enter to start your first session

Update to latest version:

curl -fsSL https://raw.githubusercontent.com/Ark0N/Codeman/master/install.sh | bash -s update

Run as a background service

Linux (systemd):

mkdir -p ~/.config/systemd/user && printf '[Unit]\nDescription=Codeman Web Server\nAfter=network.target\n\n[Service]\nType=simple\nExecStart=%s %s/dist/index.js web\nRestart=always\nRestartSec=10\n\n[Install]\nWantedBy=default.target\n' "$(which node)" "$HOME/.codeman/app" > ~/.config/systemd/user/codeman-web.service && systemctl --user daemon-reload && systemctl --user enable --now codeman-web && loginctl enable-linger $USER

macOS (launchd):

mkdir -p ~/Library/LaunchAgents && printf '<?xml version="1.0" encoding="UTF-8"?>\n<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">\n<plist version="1.0"><dict><key>Label</key><string>com.codeman.web</string><key>ProgramArguments</key><array><string>%s</string><string>%s/dist/index.js</string><string>web</string></array><key>RunAtLoad</key><true/><key>KeepAlive</key><true/><key>StandardOutPath</key><string>/tmp/codeman.log</string><key>StandardErrorPath</key><string>/tmp/codeman.log</string></dict></plist>\n' "$(which node)" "$HOME/.codeman/app" > ~/Library/LaunchAgents/com.codeman.web.plist && launchctl load ~/Library/LaunchAgents/com.codeman.web.plist

Windows (WSL)

wsl bash -c "curl -fsSL https://raw.githubusercontent.com/Ark0N/Codeman/master/install.sh | bash"

Codeman requires tmux, so Windows users need WSL. If you don't have WSL yet: run wsl --install in an admin PowerShell, reboot, open Ubuntu, then install your preferred AI coding CLI inside WSL (Claude Code or OpenCode). After installing, http://localhost:3000 is accessible from your Windows browser.

---

Mobile-Optimized Web UI

The most responsive AI coding agent experience on any phone. Full xterm.js terminal with local echo, swipe navigation, and a touch-optimized interface designed for real remote work.

	Terminal Apps	Codeman Mobile
	200-300ms input lag over remote	Local echo — instant feedback
	Tiny text, no context	Full xterm.js terminal
	No session management	Swipe between sessions
	No notifications	Push alerts for approvals and idle
	Manual reconnect	tmux persistence
	No agent visibility	Background agents in real-time
	Copy-paste slash commands	One-tap /init

• Swipe navigation — left/right on the terminal to switch sessions (80px threshold, 300ms)
• Keyboard accessory bar — /init, /clear, /compact quick-action buttons above the virtual keyboard. Destructive commands (/clear, /compact) require a double-press to confirm — first tap arms the button, second tap executes — so you never fire one by accident on a bumpy commute
• Smart keyboard handling — toolbar and terminal shift up when keyboard opens (uses visualViewport API with 100px threshold for iOS address bar drift)
• Safe area support — respects iPhone notch and home indicator via env(safe-area-inset-*)
• 44px touch targets — all buttons meet iOS Human Interface Guidelines minimum sizes
• Bottom sheet case picker — slide-up modal replaces the desktop dropdown
• Native momentum scrolling — -webkit-overflow-scrolling: touch for buttery scroll

codeman web --https
# Open on your phone: https://<your-ip>:3000

localhost works over plain HTTP. Use --https when accessing from another device, or use Tailscale (recommended) — it provides a private network so you can access http://<tailscale-ip>:3000 from your phone without TLS certificates.

---

Live Agent Visualization

Watch background agents work in real-time. Codeman monitors agent activity and displays each agent in a draggable floating window with animated Matrix-style connection lines back to the parent session.

• Floating terminal windows — draggable, resizable panels for each agent with a live activity log showing every tool call, file read, and progress update as it happens
• Connection lines — animated green lines linking parent sessions to their child agents, updating in real-time as agents spawn and complete
• Status & model badges — green (active), yellow (idle), blue (completed) indicators with Haiku/Sonnet/Opus model color coding
• Auto-behavior — windows auto-open on spawn, auto-minimize on completion, tab badge shows "AGENT" or "AGENTS (n)" count
• Nested agents — supports 3-level hierarchies (lead session -> teammate agents -> sub-subagents)

---

Zero-Lag Input Overlay

When accessing your coding agent remotely (VPN, Tailscale, SSH tunnel), every keystroke normally takes 200-300ms to round-trip. Codeman implements a Mosh-inspired local echo system that makes typing feel instant regardless of latency.

A pixel-perfect DOM overlay inside xterm.js renders keystrokes at 0ms. Background forwarding silently sends every character to the PTY in 50ms debounced batches, so Tab completion, Ctrl+R history search, and all shell features work normally. When the server echo arrives 200-300ms later, the overlay seamlessly disappears and the real terminal text takes over — the transition is invisible.

• Ink-proof architecture — lives as a <span> at z-index 7 inside .xterm-screen, completely immune to Ink's constant screen redraws (two previous attempts using terminal.write() failed because Ink corrupts injected buffer content)
• Font-matched rendering — reads fontFamily, fontSize, fontWeight, and letterSpacing from xterm.js computed styles so overlay text is visually indistinguishable from real terminal output
• Full editing — backspace, retype, paste (multi-char), cursor tracking, multi-line wrap when input exceeds terminal width
• Persistent across reconnects — unsent input survives page reloads via localStorage
• Enabled by default — works on both desktop and mobile, during idle and busy sessions

Extracted as a standalone library: xterm-zerolag-input — see Published Packages.

---

Respawn Controller

The core of autonomous work. When the agent goes idle, the Respawn Controller detects it, sends a continue prompt, cycles context management commands for fresh context, and resumes — running 24+ hours completely unattended.

WATCHING → IDLE DETECTED → SEND UPDATE → /clear → /init → CONTINUE → WATCHING

• Multi-layer idle detection — completion messages, AI-powered idle check, output silence, token stability
• Circuit breaker — prevents respawn thrashing when Claude is stuck (CLOSED -> HALF_OPEN -> OPEN states, tracks consecutive no-progress and repeated errors)
• Health scoring — 0-100 health score with component scores for cycle success, circuit breaker state, iteration progress, and stuck recovery
• Built-in presets — solo-work (3s idle, 60min), subagent-workflow (45s, 240min), team-lead (90s, 480min), ralph-todo (8s, 480min), overnight-autonomous (10s, 480min)

---

Multi-Session Dashboard

Run 20 parallel sessions with full visibility — real-time xterm.js terminals at 60fps, per-session token and cost tracking, tab-based navigation, and one-click management.

Persistent Sessions

Every session runs inside tmux — sessions survive server restarts, network drops, and machine sleep. Auto-recovery on startup with dual redundancy. Ghost session discovery finds orphaned tmux sessions. Managed sessions are environment-tagged so the agent won't kill its own session.

Smart Token Management

Threshold	Action	Result
110k tokens	Auto /compact	Context summarized, work continues
140k tokens	Auto /clear	Fresh start with /init

Notifications

Real-time desktop alerts when sessions need attention — permission_prompt and elicitation_dialog trigger critical red tab blinks, idle_prompt triggers yellow blinks. Click any notification to jump directly to the affected session. Hooks auto-configured per case directory.

Ralph / Todo Tracking

Auto-detects Ralph Loops, <promise> tags, TodoWrite progress (4/9 complete), and iteration counters ([5/50]) with real-time progress rings and elapsed time tracking.

Run Summary

Click the chart icon on any session tab to see a timeline of everything that happened — respawn cycles, token milestones, auto-compact triggers, idle/working transitions, hook events, errors, and more.

Zero-Flicker Terminal

Terminal-based AI agents (Claude Code's Ink, OpenCode's Bubble Tea) redraw the screen on every state change. Codeman implements a 6-layer anti-flicker pipeline for smooth 60fps output across all sessions:

PTY Output → 16ms Server Batch → DEC 2026 Wrap → SSE → Client rAF → xterm.js (60fps)

---

Remote Access — Cloudflare Tunnel

Access Codeman from your phone or any device outside your local network using a free Cloudflare quick tunnel — no port forwarding, no DNS, no static IP required.

Browser (phone/tablet) → Cloudflare Edge (HTTPS) → cloudflared → localhost:3000

Prerequisites: Install cloudflared and set CODEMAN_PASSWORD in your environment.

# Quick start
./scripts/tunnel.sh start      # Start tunnel, prints public URL
./scripts/tunnel.sh url        # Show current URL
./scripts/tunnel.sh stop       # Stop tunnel
./scripts/tunnel.sh status     # Service status + URL

The script auto-installs a systemd user service on first run. The tunnel URL is a randomly generated *.trycloudflare.com address that changes each time the tunnel restarts.

Persistent tunnel (survives reboots)

# Enable as a persistent service
systemctl --user enable codeman-tunnel
loginctl enable-linger $USER

# Or via the Codeman web UI: Settings → Tunnel → Toggle On

Authentication

1. First request → browser shows Basic Auth prompt (username: admin or CODEMAN_USERNAME)
2. On success → server issues a codeman_session cookie (24h TTL, auto-extends on activity)
3. Subsequent requests authenticate silently via cookie
4. 10 failed attempts per IP → 429 rate limit (15-minute decay)

Always set CODEMAN_PASSWORD before exposing via tunnel — without it, anyone with the URL has full access to your sessions.

---

SSH Alternative (sc)

If you prefer SSH (Termius, Blink, etc.), the sc command is a thumb-friendly session chooser:

sc              # Interactive chooser
sc 2            # Quick attach to session 2
sc -l           # List sessions

Single-digit selection (1-9), color-coded status, token counts, auto-refresh. Detach with Ctrl+A D.

---

Keyboard Shortcuts

Shortcut	Action
Ctrl+Enter	Quick-start session
Ctrl+W	Close session
Ctrl+Tab	Next session
Ctrl+K	Kill all sessions
Ctrl+L	Clear terminal
Ctrl+Shift+R	Restore terminal size
Ctrl/Cmd +/-	Font size
Escape	Close panels

---

API

Sessions

Method	Endpoint	Description
GET	/api/sessions	List all
POST	/api/quick-start	Create case + start session
DELETE	/api/sessions/:id	Delete session
POST	/api/sessions/:id/input	Send input

Respawn

Method	Endpoint	Description
POST	/api/sessions/:id/respawn/enable	Enable with config + timer
POST	/api/sessions/:id/respawn/stop	Stop controller
PUT	/api/sessions/:id/respawn/config	Update config

Ralph / Todo

Method	Endpoint	Description
GET	/api/sessions/:id/ralph-state	Get loop state + todos
POST	/api/sessions/:id/ralph-config	Configure tracking

Subagents

Method	Endpoint	Description
GET	/api/subagents	List all background agents
GET	/api/subagents/:id	Agent info and status
GET	/api/subagents/:id/transcript	Full activity transcript
DELETE	/api/subagents/:id	Kill agent process

System

Method	Endpoint	Description
GET	/api/events	SSE stream
GET	/api/status	Full app state
POST	/api/hook-event	Hook callbacks
GET	/api/sessions/:id/run-summary	Timeline + stats

---

Architecture

flowchart TB
    subgraph Codeman["CODEMAN"]
        subgraph Frontend["Frontend Layer"]
            UI["Web UI<br/><small>xterm.js + Agent Windows</small>"]
            API["REST API<br/><small>Fastify</small>"]
            SSE["SSE Events<br/><small>/api/events</small>"]
        end

        subgraph Core["Core Layer"]
            SM["Session Manager"]
            S1["Session (PTY)"]
            S2["Session (PTY)"]
            RC["Respawn Controller"]
        end

        subgraph Detection["Detection Layer"]
            RT["Ralph Tracker"]
            SW["Subagent Watcher<br/><small>~/.claude/projects/*/subagents</small>"]
        end

        subgraph Persistence["Persistence Layer"]
            SCR["Mux Manager<br/><small>(tmux)</small>"]
            SS["State Store<br/><small>state.json</small>"]
        end

        subgraph External["External"]
            CLI["AI CLI<br/><small>Claude Code / OpenCode</small>"]
            BG["Background Agents<br/><small>(Task tool)</small>"]
        end
    end

    UI <--> API
    API <--> SSE
    API --> SM
    SM --> S1
    SM --> S2
    SM --> RC
    SM --> SS
    S1 --> RT
    S1 --> SCR
    S2 --> SCR
    RC --> SCR
    SCR --> CLI
    SW --> BG
    SW --> SSE

Loading

---

Development

npm install
npx tsx src/index.ts web    # Dev mode
npm run build               # Production build
npm test                    # Run tests

See CLAUDE.md for full documentation.

---

Published Packages

xterm-zerolag-input

Instant keystroke feedback overlay for xterm.js. Eliminates perceived input latency over high-RTT connections by rendering typed characters immediately as a pixel-perfect DOM overlay. Zero dependencies, configurable prompt detection, full state machine with 78 tests.

npm install xterm-zerolag-input

Full documentation

---

License

MIT — see LICENSE

---

Track sessions. Visualize agents. Control respawn. Let it run while you sleep.