Starnet

Starnet is a local-first desktop agent orchestrator that runs autonomous AI workers within a visual pixel-art interface to manage workflows and perform tasks.

StarNet is a local-first desktop application that allows users to create and manage autonomous AI agents within a visual pixel-art station interface. The software operates by mapping visual layout directly to agent workflows, with each room representing a capability-scoped team. It performs real model calls and tool operations, using a Node-based sidecar to manage local persistence of agent memory, transcripts, and spend records. Users connect external models via OpenRouter, Anthropic, OpenAI, or Google accounts, or run local models via Ollama. The system supports integration with messaging platforms like Telegram, Discord, and Slack, and utilizes Model Context Protocol connectors to expand agent capabilities. Distinct from simulations, the interface projects live runtime state where all actions, budgets, and deliverables are verifiable.

Starnet at a glance

Best for: Software engineer
Runs on: Windows, macOS, open source
Pricing: Free and open source; Bring Your Own Key for cloud models or run locally via Ollama.
Released: June 2026
Category: AI agent tool
Website: github.com/androoAGI/starnet

Key features

Individual agent workspaces with distinct personas and bounded permissions
Integration with Telegram, Discord, Slack, Signal, and Matrix for remote management
Local-first architecture storing memory, transcripts, and budgets on disk
Support for OpenRouter, Anthropic, OpenAI, Google, and Ollama providers
Automated multi-step recipes, reusable skills, and cron-based scheduling
Model Context Protocol support for external tool connectors
Verified deliverables deposited into a local outbox

Use it for

Managing multi-agent workflows using visual spatial layouts
Automating long-running background tasks with adjustable constraints
Executing multi-step recipes on defined cron schedules
Interacting with autonomous agents remotely via messaging apps

Alternatives to Starnet

VoltAgent — Offers open-source flexibility with built-in supervisor agent orchestration and RAG.
Rakazo — Complete ownership of data, models, and execution environment.
Raven — Provides a persistent, self-evolving environment for all-domain agent collaboration.
Agenta — Build and automate AI agents that run on your own infrastructure or the cloud.
Agent Executor — Declarative runtime for scaling stateful agent workloads with isolation.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
AgentDock — It coordinates multi-device workflows and provides secure environment access.
Agensh — Scales to 1,024 self-organizing agents without a central orchestrator.
CodePilot — Consolidates multiple AI agents and local model connections in one workspace.
MyAgent — It features built-in permission controls, long-term memory, and skill self-evolution.
Astron Agent — Builds production-grade AI agents with zero-code prompting and visual workflows.
Alook — Connects existing local coding agents to team communication channels.

All Starnet alternatives