Flagship open-source project

NANO Agent Stack

Modular orchestration infrastructure for agent systems that need structure, auditability, and real operational topology.

NANO Agent Stack is an open-source ecosystem for modeling departments, hierarchies, skills, policies, memory boundaries, trace hooks, and human checkpoints as explicit infrastructure primitives.

Structure-first

Departments, managers, workers, skills, and policies stay explicit.

Auditability

Runs emit traces, review artifacts, and inspection layers.

Modular ecosystem

Core runtime plus skills, templates, observability, docs, and benchmarks.

Operational topology

Executive intent / orchestrator
Research Department Manager
Market Research Worker
Report Writer

Infrastructure seams

Skills
Policies
Memory
Trace hooks
Human checkpoints

Run artifacts

Markdown report
JSON trace
Visual inspector
What it is

An open-source ecosystem for modular multi-agent orchestration.

NANO is built for builders who need systems that can represent organizational structure and still remain inspectable, composable, and open-source friendly.

The problem

Most agent demos hide structure inside prompt chains and wrappers.

That makes them hard to audit, hard to extend, and hard to map onto real workflows. NANO instead models departments, managers, workers, skills, policies, traces, and approval boundaries as explicit runtime seams.

How it works

A hierarchy-first runtime for representing organizations as systems.

The design is intentionally narrow: routing, structure, policies, memory boundaries, and traces stay visible instead of disappearing into generic agent abstractions.

Orchestrator

Coordinates task execution, provider strategy, policy enforcement, and artifact generation.

Departments

Own operational domains like research, content, support, or internal operations.

Managers and workers

Managers decompose work, workers execute through skills and provider-assisted notes.

Skills, memory, and traces

Reusable capabilities, pluggable state boundaries, and execution chronology.

Architecture

From executive intent to department execution and traceable outputs.

NANO models the chain from intent to work packets to artifacts as a visible system. The goal is to make agentic execution feel more like infrastructure architecture than hidden automation.

Control layer

Orchestrator / executive intent

Defines workflow boundaries, enforces policy, chooses provider strategy, and preserves the overall execution trace.

Department layer

Managers coordinate departments

Research, content, support, or internal operations can each own tasks and route them to the right workers.

Execution layer

Workers invoke skills and emit outputs

Skills, tools, memory adapters, and trace hooks turn a workflow into inspectable operational infrastructure.

CEO / Orchestrator
Department Manager
Worker Agents
Skills / Outputs

Policies

Govern run size, approval gates, and fallback behavior.

Memory interfaces

Persist shared state without fusing storage into agent behavior.

Trace hooks

Preserve chronology, actor flow, and review checkpoints.

Use cases

Patterns designed for workflows that resemble teams, not toy prompts.

The current examples and templates focus on operational scenarios where structure, routing, and review boundaries matter.

Research workflows
Content operations
Support triage
Marketing systems
Internal operations assistants
Donations

Support NANO Agent Stack

If this project is useful to you, or if you want to support more open-source work around agent orchestration, observability, and developer-grade AI infrastructure, you can contribute directly.

Donate via PayPalpaypal.me/imraullopezpty
Demo flow

Input becomes a routed workflow, then a department execution chain.

A typical run starts with one intent, routes through a manager layer, fans out to workers and skills, and returns a reviewable artifact plus trace.

1. Input

A request enters the orchestrator with a desired output and policy boundaries.

2. Routing

The task is assigned to a department manager who owns the workflow domain.

3. Execution

Workers invoke skills and provider-assisted notes to complete specialized subwork.

4. Result

The run emits markdown, JSON trace data, checkpoints, and visual inspection artifacts.

Quick demo
npm install
npm run demo
npm run demo:content
npm run demo:support

Artifacts

latest-run.md
latest-run.json
latest-trace.md
latest-run-inspector.html
Quickstart

A small but real developer path from install to demo run.

The goal is not a fake landing page. The GitHub repo already includes a CLI, executable demos, tests, generated artifacts, and supporting satellite repositories.

Local run
npm install
npm run demo
npm run demo:content
npm run demo:support
Roadmap

A staged path from alpha runtime to broader public beta.

The roadmap stays narrow and honest: stronger providers, better templates, richer observability, and more durable memory adapters without pretending the stack is already production-complete.

v0.1 core runtime
skills and package-level extensibility
observability and trace exports
workflow templates and examples
public beta with stronger provider and memory boundaries
Why it matters

Agent systems become more trustworthy when their structure stays visible.

Builders need more than a single prompt wrapper. They need the ability to represent authority, decomposition, traceability, and human review as composable system parts. That is the space NANO is aiming at.

About the builder

Raul Lopez

Founder-engineer building AI infrastructure, open-source orchestration systems, and technical presentation layers that help serious engineering work travel further than GitHub alone.