Independent·self-funded·MIT licensed

Every hour of agent work, logged and provable.

xNAUT runs your AI coding agents and records what they did. Every command, timestamped and chained into a SHA‑256 Merkle tree, exported as a report your client can verify — without sending a byte to the cloud.

brew install --cask 48nauts-operator/tap/xnaut
Download for macOS git clone 48Nauts/xNaut

Free & open source · MIT · latest release · Apple Silicon, Intel & Windows x64 · macOS 13+

WORK SESSION — 2026-08-06 VERIFIED
Claude Code3 h 12 m
Codex0 h 51 m
Docker1 h 04 m
cargo · tests0 h 47 m
Total billable5 h 54 m
merkle root a94f…c21e
Edit one line of this session and the root changes. That is the whole idea.
1,080downloads across every release
70releases shipped, and counting
21 MBto download, not 500 MB of Electron
0bytes required to leave your machine

THE APP

Thirteen agents. One deck.

The Observatory lists every agent and every sandbox currently running, with the command to attach to any of them. Plan consumption sits across the top, because agents cost money and a number you cannot see is a number that surprises you.

The xNAUT Observatory: a dark interface listing thirteen running agents, each a named terminal session with an attach command, above a multi-agent swarm summary, with plan usage meters across the top.
Real session, not a mockup. Every row is a live terminal you can attach to.

01 — NAUTFLOW

The work has a shape. So does the tool.

An idea becomes a shipped change through fifteen stages and eight roles. xNAUT holds all of it — the documents, the tickets, the agents doing the work, and a Validator that refuses to let a build start on a broken chain of reasoning.

  1. 01

    Discover

    Analyst

    Idea · Concept · Business case

  2. 02

    Define

    PM · Architect · Security

    Product requirements · Architecture · Data model · API design · Security review

  3. 03

    Plan

    Planner · PM

    Development plan · Sprint stories · Executable tickets

  4. 04

    Deliver

    Builder · Reviewer

    Build · Test and review · Release · Engram learning

GATE

The Validator sits between Plan and Deliver. It reads the whole document chain and checks contract coverage, stage completeness, cross-stage consistency, testability and build readiness. A FAIL blocks the build — and it writes an acceptance script that runs against the thing you actually built, not against its own opinion of it.

02 — FEATURES

Everything the work touches, in one place.

Every feature exists because running Claude Code, Codex, and friends in a plain terminal means losing track of who is doing what, where.

Agent Runner

Launch claude, codex, gemini or any CLI agent from a user-editable registry. Live status pills — working, done, blocked — with real-time hook pushes. Click a pill, jump to its tab.

git worktree add ⎇

Worktree Manager

One modal to spin up isolated worktrees with a recipe where push and status both just behave — then drop any agent straight into the new tree.

+ added  - removed

Diff Viewer with AI notes

Side-by-side diffs where agents leave inline annotations — summary, rationale, confidence — anchored to the exact hunk. Notes update live as agents write them.

xnaut ·   bucky · ○

Project Workspaces

Each project is a workspace with its own tabs, terminals and zellij session. Switch projects, get your exact context back — nothing bleeds between them.

⌥B browser · ⌥M markdown

More than terminals

Split any pane with a sandboxed browser, a markdown editor with Mermaid, a file tree or a code editor. Docs and previews live beside the shell, not in another app.

Themes with an AI twist

Twelve built-in themes with full ANSI palettes — Catppuccin, Tokyo Night, Nord, Dracula — plus a generator: describe a vibe, get a matching theme for the whole app.

triggeragentgate ✓deliver

Visual Loop Designer

Draw agent workflows as nodes — triggers, agents, approval gates, bounded retries — with versioning, validation, cost limits and model governance. Or just describe it: the LoopBuilder agent drafts the loop and repairs validator feedback itself.

[[naut-flow-concept]]  ← 12 backlinks

Integrated Doc Vault

An Obsidian-style vault inside the terminal — wikilinks, backlinks, tags, search and templates for work and personal notes. The Vault Librarian agent searches, files and writes notes on request.

Knowledge Graph orb

Your vault's wikilinks and your codebase's imports, rendered as a force-directed orb — 2D or a slow-rotating 3D nebula. Switch between notes and code with one selector, all scanned locally in Rust.

Agents don't just run in xNAUT — they drive it

A built-in MCP server on localhost turns the terminal into a tool your agents call. Claude Code, Codex or any MCP client can list projects, create and update tickets with conflict-safe revisions, and read or write project docs in the vault. Per-session bearer token, copy-ready connection object in Project Settings.

{
  "xnaut": {
    "type": "http",
    "url": "http://127.0.0.1:<port>/mcp",
    "headers": { "Authorization": "Bearer <session-token>" }
  }
}
// tools: projects · tickets · vault docs — all local

03 — PROOF OF WORK

Every billable hour, hash-chained.

The Work Session Logger records every command with timestamps and duration, chains them into a SHA-256 Merkle tree, and exports a client-ready HTML report. A QR code on the report recomputes the root, so a report that has been edited stops matching the record it came from.

WORK SESSION — 2026-07-11 VERIFIED
Claude Code3 h 12 m
Docker1 h 04 m
cargo · tests0 h 47 m
Total billable5 h 03 m
merkle root a94f…c21e ▦ scan to verify

04 — LOCAL-FIRST AI

Your model, your machine, your choice.

Explain Screen, AI chat and theme generation run against Ollama or LM Studio on localhost by default. Cloud providers are there when you want them — behind a privacy monitor that flags leaked keys and PII before a prompt leaves the app.

Ollama local LM Studio local AntBot local Anthropic OpenAI OpenRouter Perplexity

05 — HOW IT STACKS UP

Bragging rights, itemized.

Everyone's open source now. Nobody else fits a terminal, an agent fleet, and a notary into a 21 MB download.

xNAUTWarpCursorGhostty
PriceFree · MIT$20/mo credits$20/moFree · MIT
Ships as21 MB native appapp + cloudVS Code forknative binary
Full power, no accountAI needs account
AI fully on localhost✓ Ollama · LM Studiocloud creditscloud modelsno AI
Any CLI agent, live statusits own agentsits own agents
Visual agent-loop designer✓ nodes + gatescloud (Oz)
MCP server for agents✓ docs · ticketsclient only
Hash-chained proof of billable work✓ Merkle + QR
Prompt privacy guard✓ keys · PII

Ghostty is a great terminal. Warp is a great subscription. Cursor is a great IDE.

xNAUT is the whole bridge crew — in a 21 MB download, for free.

Snapshot July 2026. Warp: AGPL client, $20/mo Build plan for AI credits. Cursor: proprietary, $20/mo Pro; 3.x runs parallel/cloud agents — its own, not yours. Ghostty: MIT, no AI by design.

06 — FAQ

Frequently asked questions.

Everything you need to know about xNAUT, your agents, and the ∅ funding model.

What is xNAUT?

The workspace where agent work happens and gets recorded. One 21 MB native app holds the terminals your agents run in, their live status, git worktrees, diffs with AI annotations, project docs, the plan they are working through — and a hash-chained log of every hour of it. Instead of four separate tools and a spreadsheet for the invoice.

Is it really free? What's the catch?

MIT-licensed, no paid tier, no account, no trial that expires. The catch is there is no catch — we're backed by ∅ Nobody, so there's no investor to monetize you for. If you use cloud AI providers, you pay them directly; local models cost nothing.

Does anything leave my machine?

Only what you point somewhere: prompts go to the AI provider you configure (localhost Ollama/LM Studio by default), and the app checks GitHub Releases for updates. The app has no telemetry and no analytics — there is no backend of ours to send anything to. (This website uses self-hosted, cookieless privacy-respecting analytics; the app sends nothing.) The privacy monitor even flags API keys and PII before a prompt leaves the app.

Which coding agents work with it?

Any CLI agent. Claude Code, Codex, Gemini, Grok, OpenCode come preconfigured; anything else drops into the registry at ~/.config/xnaut/agents.toml. Live status pills work for all of them.

Do I need API keys or a cloud subscription for the AI features?

No. Explain Screen, chat and theme generation run against Ollama or LM Studio on localhost out of the box. Cloud providers (Anthropic, OpenAI, OpenRouter, Perplexity) are optional and use your own keys, stored locally.

How is a terminal with all this only a 21 MB download?

Rust + Tauri v2. The UI renders in your OS's built-in webview instead of shipping a bundled Chromium, so the whole app is a ~21 MB download where Electron apps ship hundreds of megabytes.

What exactly does "proof of work" prove?

Every command is recorded with timestamp and duration and chained into a SHA-256 Merkle tree. The exported report (HTML with a QR verification code) recomputes the root, so a report that has been edited stops matching its record. It proves the report matches the log it came from, not the quality of the work. The chain is computed on your own machine with no outside signature over it, so it is not evidence against whoever holds the log.

Is xNAUT a Warp or Cursor alternative?

They solve a different problem. Warp is a terminal you subscribe to; Cursor is an editor. xNAUT is where agent work gets planned, run and recorded — it replaces Warp's terminal without the account, the credits or the cloud, and it sits beside Cursor rather than against it: Cursor for editing, xNAUT for running the fleet and proving the hours. Neither of them can hand you a signed record of what the agents did. See the comparison above for specifics.

Does it run on Windows and Linux?

macOS 13 Ventura or newer (Apple Silicon + Intel) is the primary platform; the app declares that floor and older Macs refuse to launch it. Windows x64 installers (.msi / .exe) ship with every release — treat them as early: the core terminal works, but workspace features that rely on zellij are macOS-first. No Linux builds yet.

Can my agents control xNAUT itself?

Yes — that's the MCP server. Any MCP client can list projects, create and update tickets (revision-safe), and read or write project docs in the vault, all over localhost with a per-session token.

How often does it ship?

Fast — twenty-five releases so far, the latest on 2 August 2026. xNAUT tells you in-app when a new version lands, and everything that changed is on the releases page.

$ brew install --cask 48nauts-operator/tap/xnaut

Ship with a crew of agents. Keep the helm.

Download xNAUT Star on GitHub