Loading…
Network Agent Logic Architecture
AI agents that
work as one
The agentic IDE: a local-first command center that connects to the subscriptions you already have.
curl -fsSL web-production-13d16.up.railway.app/install.sh | sh
Now seating · Private preview
ClaudeCodexDevinCursorGrokKimi K3+ Custom
One-click launch for every major coding agent, plus any CLI agent you define yourself. Private preview: brand new, openly built, and ready to work today.
editor / AI editor / agentic IDE (ADE)
Your agents already type faster than you.
The bottleneck is who's running the room.
Run five agents in five terminal tabs and you become the relay, copying context between windows so nothing gets lost. nala replaces the tabs with panes built for a fleet, tasks that carry state between agents, messages they send each other directly, and approvals that only pull you in when something actually matters.
THE NALA AGENT
One agent routes the whole fleet
A resident nala agent sits at the centre of the workspace and coordinates supported coding tools through local adapters. You install and authenticate the tools you choose; nala conducts them from one workspace.
Route · Work goes to the right agent, not the nearest chat window.
Relay · Agents ask, answer, and hand off through durable messages.
Restrain · No agent spawns another without your single-use approval.
Under the hood sits the Pi agent framework. Nala's adapters keep provider choice separate from workspace orchestration, and Pi's extension system provides a path for adding compatible tools without introducing a Nala-hosted inference layer.
███╗ ██╗ █████╗ ██╗ █████╗ ████╗ ██║ ██╔══██╗ ██║ ██╔══██╗ ██╔██╗ ██║ ███████║ ██║ ███████║ ██║╚██╗██║ ██╔══██║ ██║ ██╔══██║ ██║ ╚████║ ██║ ██║ ███████╗ ██║ ██║ ╚═╝ ╚═══╝ ╚═╝ ╚═╝ ╚══════╝ ╚═╝ ╚═╝
Network Agent Logic Architecture
Welcome to the Future — let's get you set up.
Setup complete. NALA is ready.
curl -fsSL https://web-production-13d16.up.railway.app/install.sh | shthen type nala for the agent · nala desktop for the command center
01FLEXIBILITY
Extends your existing subscriptions
The supported coding tools and provider clients you already use remain the engine. Connect their local CLIs or a custom adapter; Nala coordinates them without reselling inference or requiring a Nala-hosted model backend.
CLAUDECODEXDEVINCURSORGROKKIMI K3+ CUSTOM
02DURABILITY
Terminals that survive reboots
Sessions live in a detached daemon: close the app, reboot the machine, and your terminals, scrollback, and agent conversations come back exactly where they were. Suspended sessions persist for seven days.
DAEMONSCROLLBACKRECOVERYOSC 133
03INTEGRATION
An agent extensibility harness
NALA registers itself as an MCP server with Claude, Codex, and Gemini: 30+ tools for workspace control, terminal routing, and browser automation, handed to every agent you run. Surgical registration that never clobbers your own config. Your agents arrive already knowing how to drive the machine.
MCPPLAYWRIGHTTOOLSPERMISSIONS
04WORKFLOW
Built-In Skills
nala ships with reusable workflows for planning, debugging, reviewing, debating, documenting, and breaking work into tickets. 40+ predefined agent roles across engineering, design, and PM.
PLANEXECUTEREVIEWEXPLAIN
THE A2A PROTOCOL
The fleet talks. You conduct.
Stop being the messenger between chat windows. Agents talk over a durable protocol (send, ask, reply, inbox), so a reviewer can question the builder, a lead can task its department, and you can put one agent in charge of others.
And no agent mints another agent without your signature: spawn requests are proposals until you approve them, and each approval is single-use.
Durable envelopesAcknowledged end-to-endIdempotent deliveryLoop preventionSingle-use spawn approvals
nala · live sessionFeature build · simulation
Off
Agents work alone. Messages queue, nothing moves. Your fleet, on mute.
Connect
Agents ask, reply, and hand off through the inbox. Envelopes survive restarts and land exactly once.
Orchestrate
Full choreography: reviews, delegation, run waves. A wait-graph watches every conversation and breaks loops before they spin.
40+ agent presets · isolated worktrees · cost tracking
COMPANY MODE
A team of specialists, not a chatbot
Build an organization of agents the way you'd build a firm: a CEO agent, departments, leads, and members drawn from 40+ presets across engineering, design, and product. Each department works in its own isolated git worktree; every member's cost is tracked; approvals gate anything critical.
Describe the goal. The firm divides the work, reviews itself, and reports back, while you watch every move.
Everything you just saw runs on your machine.
VOICE
Talk to it. It talks back.
Hold Space and speak, and nala answers in one of 14 voices, in whatever language you think in. Both voice models run entirely on your machine: no cloud round-trip, no API keys, no per-word bill for talking to your own agent.
It doesn't stop at the terminal: one shortcut dictates into any window, from a browser tab to a doc to an email, and session recaps land in the workspace's running notes. A router and a voice in the same process are the raw parts for building voice agents of your own, and prototyping one costs exactly nothing. The models are already on your machine.
HOLD SPACESYSTEM-WIDE DICTATION14 VOICESEVERY LANGUAGEWORKSPACE NOTESNO API KEYS
Two response styles, live in the app. Pick yours in settings.
THE BASE LAYER
The terminal was the
first operating system.nala is its agentic
evolution.
From a terminal you can already do anything on a machine. nala keeps that reach and puts a fleet of agents behind it. Speak or type, and conduct the work. Not a plugin sitting on top of your tools: a command center for the agentic era, and how you and your agents run the machine.
“A few days of living in it and I stopped toggling between terminals and virtual desktops. I command whole teams of agents, and put agents in charge of other agents. It feels like superpowers.”
Agent-nativeTerminal-nativeVoice in & outLocal-firstDurable stateYours to extend
The same fleet, everywhere you work
One install. A desktop command center, a resident terminal agent, and a CLI, all conducting the same fleet.
The one-line install
App, daemon, and agent in one command. Then nala sit. Good lion.
curl -fsSL web-production-13d16.up.railway.app/install.sh | sh
PRICING
Free. Bring your own agents.
The whole product is free today: extend the subscriptions you already pay for, with voice and orchestration included. No metering, no markup.
$0 today
The whole app. Not a trial, not crippleware.
nala: free preview
Download nala, connect supported tools you already use, and run the local-first desktop app and agent without entering a credit card. Nala does not currently sell a hosted model service, credits, subscriptions, or team plan.
Includes:
- Desktop app, terminal, CLI, and TUI
- The Pi-powered nala agent
- Claude Code, Codex, Cursor, Grok, Kimi K3, Gemini CLI, OpenCode & custom agents
- Your existing subscriptions, your API keys, local models
- Voice in & out on-device, with system-wide dictation
- Workspaces, panes, missions, and agent workflows
- Agent-to-agent communication & local swarms
- Local memory and project history
- MCP, skills, and community extensions
- Updates during the free preview
FAQ
Questions, answered
Straight answers about the product, the private preview, and what runs on your machine.
nala is an agentic IDE: a private, local-first workspace where your AI coding agents run side by side. Connect Claude Code, Codex, Devin, Cursor, Grok, Kimi K3, or any custom CLI agent, and nala handles durable tasks, artifact sharing, agent-to-agent messaging, voice, and MCP, with no cloud host required.
WHAT'S NEXT
The base layer is free. Take it.
Bring your own models and agents. Durable terminals, agent-to-agent orchestration, on-device voice, and MCP, all local-first, no cloud host required. Your machine is the empire.
The Nerve Center for Agentic Engineering
Start building with nala today
Download nala free and be among the first to orchestrate your AI coding agents. Product updates, tips, and early-access notes in your inbox.