v0.1.0 — Phase 1 Release

Nexus OS

The orches|

One CLI to create, supervise, and scale AI agents. Built in Rust. WASM-sandboxed. Erlang-style fault tolerance. Token-cost optimization that saves you money on every call.

View on GitHub
< 5min
Project setup time
~90%
Token cost savings
3
Supervisor strategies
WASM skill modules
Features

Everything you need to orchestrate AI agents

From lifecycle management to cost optimization, Nexus OS provides the primitives that production agent systems require.

Erlang-Style Supervisors

One-for-one, one-for-all, rest-for-one restart strategies. Agents self-heal with configurable restart windows and escalation policies.

naos deploy researcher --supervisor one-for-one --max-restarts 5

Sagas & Workflows

Multi-step orchestration with automatic compensation. If step 3 fails, steps 1 and 2 are automatically rolled back.

naos workflow run data-pipeline

Token-Cost Optimization

Per-agent budgets, automatic model downsizing, semantic caching, and prompt compression. Every call is routed to the cheapest capable handler.

naos cost set researcher --budget $10/day --alert-at 80%

WASM Skill Marketplace

Deterministic tasks run in WASM sandboxes at near-zero cost. Skills are portable, versioned, and composable.

naos marketplace install [email protected]

Causal Audit Trail

Every agent action is logged with Lamport timestamps, content hashes, and cost tracking. Full replay and fork capabilities.

naos audit tail --lines 50

Edge Deployment

Deploy agents to Cloudflare Workers for sub-50ms latency worldwide. Offline-first with automatic sync.

naos edge deploy researcher

CRDT State Management

Conflict-free replicated data types for agent memory. Merge without coordination. Fork and replay from any point.

naos state inspect researcher

Broker Routing Engine

Skill → WASM → LLM routing cascade. The broker picks the cheapest handler that can solve the task with high confidence.

naos broker route "parse JSON from API response"
Architecture

Three layers, one binary

Nexus OS organizes agent systems into three distinct layers. The Execution Layer runs code in WASM sandboxes. The Orchestration Layer manages supervisors, sagas, and workflows. The Intelligence Layer handles LLM routing and cost optimization.

Execution— WASM sandboxes, containers, edge runtimes
Orchestration— Supervisors, sagas, workflows, pools
Intelligence— Broker routing, cost control, model selection
Nexus OS Architecture — Three layers: Execution, Orchestration, Intelligence
naos CLI in action — init, create, status commands
CLI

One command to rule them all

The naos CLI is your single interface for the entire agent lifecycle. Initialize projects, create agents from templates, deploy with supervisors, track costs, and monitor everything from your terminal.

naos initScaffold a new project in < 5 minutes
naos createCreate agents from built-in templates
naos run / stopManage agent lifecycle
naos deployDeploy with supervisor strategies
naos dashboardLaunch the web dashboard
naos cost statusView real-time cost tracking
naos broker routeRoute tasks through the broker
naos edge deployDeploy agents to Cloudflare Edge
naos audit tailStream the causal audit trail
Dashboard

Real-time monitoring at localhost:4200

A built-in web dashboard served by the naos binary itself — no separate install needed. Server-rendered HTML with auto-refresh, terminal-aesthetic styling, and 5 JSON API endpoints.

Nexus OS Dashboard — Agent monitoring, cost tracking, supervisor tree, audit trail

11 Pages

/
Overview

Real-time summary of agents, supervisors, cost, trust, and recent activity

/agents
Agents

All agents with status, cost budget, and AXIS trust scores

/supervisors
Supervisors

Supervisor trees with child agent states and restart counts

/sagas
Sagas

Multi-step saga definitions with execution history and rollback status

/workflows
Workflows

Sequential data pipeline steps with execution tracking

/pools
Pools

Concurrent fan-out pools with member status and strategy

/cost
Cost

Budget tracking with progress bars and per-agent spend breakdown

/audit
Audit Log

Searchable, filterable log of every system event

/trust
AXIS Trust

Trust verification status for all registered agents

/broker
Broker

Routing stats, skill calls, WASM/LLM breakdown, and cost savings

/edge
Edge

Cloudflare Worker deployments, global latency, region distribution

naos dashboard
$ naos dashboard --open
⬡ Dashboard running at http://127.0.0.1:4200
Pages:
/ Overview
/agents Agent list and status
/supervisors Supervisor trees
/sagas Saga definitions
/workflows Workflow pipelines
/pools Pool status
/cost Budget tracking
/audit Audit log
/trust AXIS Trust status
/broker Broker routing stats
/edge Edge deployments
Press Ctrl+C to stop

JSON API Endpoints

/api/agents
Agents
/api/supervisors
Supervisors
/api/cost
Cost
/api/audit
Audit
/api/trust
Trust
/api/broker
Broker
/api/edge
Edge
Broker Routing

Route tasks to the cheapest capable handler

The broker evaluates every task against registered skills, WASM modules, and LLM providers. It picks the fastest, cheapest handler that meets the confidence threshold — saving up to 90% on token costs.

Routing Cascade

SKILL
Pattern-matched deterministic functions
Cost: ~$0.00Latency: ~5ms
WASM
Sandboxed WebAssembly modules
Cost: ~$0.00Latency: ~10ms
LLM
Language model API (last resort)
Cost: ~$0.01Latency: ~1s
Confidence Thresholds
90%Skill match
80%WASM match
70%LLM fallback
naos broker
$ naos broker route "summarize the quarterly report"
Routing decision:
Route: SKILL (summarize)
Confidence: 93%
Est. cost: $0.00
Est. latency: ~5ms
$ naos broker route "write me a poem about cats"
Routing decision:
Route: LLM (anthropic/claude-sonnet)
Confidence: 70%
Est. cost: $0.01
Est. latency: ~1000ms
$ naos broker stats
SKILL 7 calls $0.00 ~4ms
WASM 0 calls $0.00 -
LLM 8 calls $0.08 ~1,100ms
Savings: $0.07 (46%)
broker route
Dry-run routing
broker execute
Route & run
broker stats
Cost savings
broker config
View config
broker skills
List skills
Edge Deployment

Deploy agents to 300+ Cloudflare PoPs

One command pushes your agent to Cloudflare Workers with Durable Objects for persistent state. Sub-50ms latency worldwide, automatic scaling, and zero cold starts.

naos edge
$ naos edge deploy researcher
Deploying researcher to Cloudflare Edge...
\u2713 Compiled to WASM (48 KB)
\u2713 Generated Worker script
\u2713 Uploaded to Cloudflare
\u2713 Created Durable Object namespace
\u2713 Route configured: researcher.agents.nexus/*
Deployment complete!
URL: https://researcher.agents.nexus
Regions: 300+ Cloudflare PoPs
Latency: <50ms globally
$ naos edge status researcher
Agent: researcher
Status: \u25cf active
Requests: 12,847
Avg lat: 23ms
p99 lat: 89ms
Errors: 0.1%

Global Distribution

North America45%
Europe32%
Asia-Pacific18%
Other5%
edge login
Authenticate with Cloudflare
edge deploy
Push agent to Workers
edge list
View all deployments
edge status
Metrics & region stats
edge logs
Stream Worker logs
edge undeploy
Remove from edge
Architecture
Cloudflare Workers for compute
Durable Objects for persistent state
Custom routes per agent
Zero cold starts, auto-scaling
Configuration

Declarative YAML, zero boilerplate

Define your entire agent system in a single nexus.config.yaml. Agents, supervisors, cost budgets, broker routing, skills, and deployment targets — all in one place.

The config file supports agent templates (research, coding, data, custom), supervisor strategies with restart windows, per-agent cost budgets with automatic throttling, broker routing with skill/WASM/LLM cascade, and edge deployment targets.

nexus.config.yaml
project: my-agents
version: "1.0"

agents:
  researcher:
    template: research
    model: claude-sonnet
    capabilities:
      - resource: "web.*"
        actions: [read]
      - resource: "fs.output"
        actions: [write]

supervisor:
  strategy: one-for-one
  max_restarts: 5
  window: 300s

cost:
  researcher:
    budget: $10/day
    alert_at: 80%
    action: throttle

broker:
  routing:
    preferSkill: true
    llmAsLastResort: true
  thresholds:
    skill: 0.9
    wasm: 0.8

skills:
  - name: summarize
    patterns: [summarize, summary, tldr]
    handler: "fn:summarize_text"
    cost: "$0.0001"

edge:
  cloudflare:
    account_id: "${CF_ACCOUNT_ID}"
    zone_id: "your-zone-id"
  routes:
    researcher: "researcher.agents.nexus/*"
Pricing

Open source. Free forever.

Nexus OS is MIT licensed. The CLI, dashboard, and all orchestration primitives are free. You only pay for the LLM tokens your agents consume.

Core CLI

Free
  • Agent lifecycle management
  • Supervisor strategies
  • Sagas & workflows
  • Cost tracking
  • Audit trail
  • Dashboard

WASM Marketplace

Free
  • Install community skills
  • Publish your own skills
  • Version management
  • Deterministic execution
  • Near-zero cost per call

Edge Deployment

Pay-as-you-go
  • Cloudflare Workers
  • Sub-50ms latency
  • Offline-first sync
  • Auto-scaling
  • Your Cloudflare account
Get Started

From zero to running agents in 5 minutes

Install the CLI, initialize a project, create your first agent, and watch it run.

quickstart
# Install
$ cargo install --git https://github.com/leonidas-esquire/nexus-os.git
# Initialize a project
$ naos init my-agents
$ cd my-agents
# Create your first agent
$ naos create researcher --template research
# Run it
$ naos run researcher
# Check status
$ naos status
# Launch dashboard
$ naos dashboard
Dashboard: http://localhost:4200
Installation

Choose your install method

Nexus OS supports macOS and Linux on x86_64 and ARM architectures.

Via Cargo

Recommended

Install directly from GitHub with Cargo. Requires Rust toolchain.

Download Binary

No Rust needed

Download a pre-built binary from GitHub Releases for your platform.

From Source

Build locally

Clone the repository and build with Cargo for full control.

Verify your installation: naos --version