Open Source · Apache 2.0

Watch Your Agents.
Stay in Control.

Run Claude Code, Codex CLI, and Gemini CLI side by side. See every tool call, catch regressions mid-task, and steer your agents in real time. One workspace for all your locally running agents — lightweight enough to stay out of their way.

Early alpha. Features may be incomplete or unstable. AI agents generate content that may be inaccurate — always review outputs. Report issues

3+
Agent providers
Local
Agents run on your machine
<1s
Startup — Rust, no Node.js
100%
Rust backend
The Paradigm Shift

The Editor Era is Over

For decades, software meant a human typing code into an editor. That model is ending. The new mode is agentic engineering.

Current

Vibe Coding

  • -You direct a single agent to build an app
  • -One conversation, one context window
  • -The agent works alone — no second opinion
  • -You wait for one task to finish before starting the next
Next

Supervibe Coding

  • +You direct groups of agents that consult and work together
  • +Multiple agents work in parallel across your codebase
  • +Agents review each other's work and catch regressions
  • +You supervise the team, not the code

Welcome to Supervibe Coding

Vibe coding proved you can build apps by directing an agent instead of writing code yourself. Supervibe coding is the next step: you direct groups of agents that collaborate, consult each other, and work in parallel. One agent builds the API while another writes the frontend and a third runs tests. They share context through interpane communication. You watch, steer, and intervene only when needed.

1
Assign

Give each agent a role — API, frontend, tests, review

2
Observe

Watch agents collaborate and catch conflicts in real time

3
Steer

Redirect when agents drift — let the team self-correct when they don't

Everything your agents need. Nothing they don't.

Multi-provider agent panes, interpane communication, regression detection, and a subagent watcher — built on a Rust backend light enough to run alongside 10+ agents on modest hardware.

Agent

Multi-Provider Agent Panes

Native pane type for Claude, Codex, and Gemini. Structured view of tool calls, reasoning steps, and file diffs. Not a terminal wrapper - a purpose-built agent UI with streaming parser, OAuth flow, and state machine.

Observability

Agents Regress. You'll Know.

Every tool call streamed in real time. Visual diff overlay shows file changes as they happen. Regression detection highlights when an agent reverts correct work. One-click interrupt to redirect mid-task.

Workflow

Interpane Reactive Comms

Panes talk to each other via Tokio channels. An agent's output streams into another pane's input. Build reactive pipelines - agent A's result triggers agent B. Visual connection indicators show active data flows.

Agent

Subagent Watcher

Monitor sub-agents spawned by your primary agent. JSONL stream parsing surfaces every subagent's activity in a dedicated pane view. See multi-level agent hierarchies in real time.

Agent

The Forge

A persistent agent configuration manager. Define working directory, Soul identity, AgentMD, MCP config, skills, and environment variables per agent. SQLite-backed with auto-start, crash-restart, and one-click launch for any provider.

Local

Runs Locally. Stays Local.

Your agents run on your machine. No cloud sandbox, no waiting for results. Full visibility into every tool call, file write, and network request as it happens. Your data never leaves your machine.

Coming Soon

Agent App API

Your agents configure the app for you. They spawn panes, set titles, build dashboards, rearrange the workspace, and update their own status — all through a typed API with sub-millisecond IPC to the Rust backend. You describe the layout you want; your agents make it happen.

Observability

Live System Metrics

Dedicated sysinfo pane with real-time CPU, memory, and network graphs via Recharts. Live status bar with uptime counter, per-pane stats, and agent activity indicators.

Code Preview & Real PTY

Syntax-highlighted code preview pane. Authentic terminal emulation via xterm.js + portable-pty. Per-pane zoom, font size, transparency, and theme. Shell integration across bash, zsh, fish, pwsh.

Performance

Light Enough for Agent Workloads

150-350MB memory footprint — comparable to Warp or VS Code, but backed by a pure Rust engine with zero GC pauses and no heap growth over time. Runs comfortably alongside 10+ agent processes on modest hardware.

Cross-Platform Desktop

Native builds for Windows, macOS, and Linux. Code-signed and notarized on macOS. NSIS installer + portable ZIP on Windows. AppImage + .deb on Linux.

Open Source · Apache 2.0

No telemetry, no tracking, no phone-home. Audit every line. Extend it. Ship it. Free forever.

Built for how you actually work

Whether you're running one agent or twenty, AgentMux gives you the visibility to stay in control.

01
Legal Teams

Research, deliberate, and verify

Assign agents to separate research tracks - case law, contracts, regulatory compliance. They verify each other's findings through interpane communication. Full audit trail for malpractice protection.

02
DevOps & Platform

Agent-driven infrastructure as code

One agent writes Terraform while another reviews for security and cost. Subagent watcher tracks deploy hierarchies. Sysinfo pane shows live metrics during agent-triggered deploys.

03
Incident Response

Parallel investigation under pressure

Assign agents to logs, metrics, recent deploys, and config changes. See findings converge on a root cause in real time. The session log becomes the post-incident report.

04
Research & Analysis

Parallel exploration with cross-verification

Spin up agents to explore different approaches in parallel. Have them deliberate, challenge each other's conclusions, and converge on verified results.

05
Security Engineer

Trust but verify

See every tool call, file write, and network request an agent makes. One agent scans for vulnerabilities while another reviews the findings. Guardrail observability shows which constraints are firing.

06
Enterprise Governance

Rigorous audit trails

Every tool call, file write, and data access captured with full context. Chain of Thought logging at every handoff. Satisfies EU AI Act, Colorado AI Act, and NIST AI Agent Standards.

Why this matters now

Jensen Huang told 30,000 developers at GTC 2026: the agentic AI era is here. NVIDIA projects $1 trillion in demand. Every engineer gets a token budget. The tooling for this shift doesn't exist yet.

Your tools are slower than your agents

Electron-based tools eat 500MB+ of RAM per window. When you're running five agents, that's your entire machine. AgentMux uses 150-350MB of memory - a native Rust binary with no garbage collector, no runtime bloat, and no random freezes. ~152MB portable — no install needed. It's the only tool that won't become the bottleneck.

Agents regress silently

An agent fixes a bug, then undoes the fix three steps later while working on something else. Without visibility into every decision step, you only discover the damage after it's merged. AgentMux shows you the regression as it happens - with zero rendering lag thanks to async streaming.

Agents need to talk to each other

Running multiple agents in isolation creates duplicated work, merge conflicts, and cascading errors. AgentMux's interpane reactive communication lets agents share context, coordinate tasks, and respond to each other's output - all through the UI, no custom plumbing required.

Agents should control their own UI

Today's tools treat agents as dumb text streams. AgentMux's Agent App API lets agents create panes, render custom views, and modify the workspace layout programmatically. Your agents become first-class UI citizens - they can build the interface they need to show you what matters.

Subagents are invisible

Modern agentic models spawn sub-agents to parallelize work. A single session might fork five subagents for different subtasks. AgentMux's subagent watcher auto-detects spawned sub-agents via JSONL monitoring and opens dedicated pane views. Without this, a subagent can silently regress, corrupt data, or loop indefinitely.

Governance is no longer optional

The EU AI Act mandates human oversight. The Colorado AI Act takes effect June 2026. 80% of companies with AI agents report boundary violations. AgentMux captures every tool call with full context and identity - session-level audit exports for regulatory evidence. Runs locally with zero telemetry.

AgentMux builds AgentMux

AgentMux was rapidly developed by AI agents running inside AgentMux itself. Multiple agents working in parallel on frontend, backend, and infrastructure - coordinated through the same interpane communication and Agent App API that ships to you. The ultimate proof the tool works: we ship with it every day.

Run any agent. See everything.

Other tools manage their own agent. AgentMux orchestrates Claude Code, Codex CLI, and Gemini CLI — side by side, with full visibility into every tool call and sub-agent.

ToolRuns Your AgentsPrice
AgentMuxAny providerFree
Claude CoworkClaude onlyFrom $20/mo
Codex AppCodex onlyFrom $20/mo
CursorCursor onlyFrom $20/mo
DevinDevin only$20/mo + ACU
WarpWarp + CLIsFree / $20/mo
GitHub CopilotCopilot onlyFree / $10/mo
Roadmap

What's Coming to AgentMux

AgentMux is building toward a complete agentic operating system: persistent agent configs, multi-agent coordination, and remote access from anywhere.

Phase 1

The Forge

Coming Soon

Define. Store. Launch.

A persistent agent configuration manager built into AgentMux. Define every detail of how an agent starts: working directory, Soul, AgentMD, MCP config, skills, and environment variables. Launch it with one click.

  • Soul layer: persistent identity and rules prepended to AgentMD at launch
  • SQLite-backed agent configs with file-watcher sync
  • Auto-start and crash-restart per agent
  • Launch any provider: Claude, Gemini, Codex, or custom

Phase 2

Swarm

Planned

Coordinate fleets of agents.

Multi-agent orchestration built on the unleashd pattern. AgentMux detects swarm worker tags from the live PTY stream, groups sessions by swarm ID, and gives you a real-time SwarmDashboard pane with live status for every worker.

  • Automatic swarm detection via [oompa:<swarmId>:<workerId>] tags
  • SwarmDashboard: worker grid with role badges (Work / Review / Fix)
  • Session grouping in the sidebar with worker count
  • Launch coordinated multi-agent swarms directly from Forge

Phase 3

Claw

Planned

Your agents, from anywhere.

A self-hosted remote access gateway connecting 25+ messaging channels (WhatsApp, Telegram, Slack, Discord, and more) directly to your AgentMux agents via JektRouter. Control long-running agents from your phone while away from your desk. Compatible with existing OpenClaw installs.

  • 25+ messaging platforms as agent input channels
  • Voice pipeline with wake-word detection and ElevenLabs TTS
  • Cron triggers and webhooks: agents wake on external events
  • Live Canvas: structured agent output rendered as rich mobile UI

Follow development on GitHub

Get AgentMux

Free and open source. Available for Windows, macOS, and Linux.

Early alpha. Your OS or app store may show a security warning — the binaries are not yet code-signed. This is expected and will be resolved in a future release.

v0.32.90

Or build from source on GitHub