Toli

Toli is an AI agent collaboration tool that enables agents to work together across one or multiple machines.

Toli is an open-source collaboration system for AI agents, functioning like a telephone network to let different programs work together. It allows any agent using the Model Context Protocol to communicate, delegate tasks, ask questions, and share results using the open A2A protocol. Users run a local daemon that handles agent registration, tokens, and peer connections securely on a single machine or across networks using Tailscale, local networks, or HTTPS tunnels. The software provides a terminal user interface and a command-line interface to watch, manage, and inspect all active tasks. It supports multiple agent types including Claude Code, Codex, OpenCode, OpenClaw, and Pi, running on macOS, Linux, and Windows operating systems.

Toli at a glance

Best for: Software engineer
Runs on: macOS, Linux, Windows, CLI
Pricing: Free
Released: October 2026
Category: AI agent tool
Website: github.com/arjunvlama/toli

Key features

Connects multiple AI agents to collaborate on tasks
Manages agent communication over the open A2A protocol
Provides a terminal user interface to watch and manage tasks
Offers a command-line interface for control and inspection
Supports secure cross-machine communication using Tailscale or HTTPS
Integrates with tools via Model Context Protocol clients

Use it for

Collaborating between different AI coding assistants
Delegating tasks across multiple agent systems
Managing multi-agent communication on a single machine
Connecting agents across different network environments

Alternatives to Toli

Alook — Connects existing local coding agents to team communication channels.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
Kolo — Teams share one browser session to watch, type, and control AI agents together.
Hybro — Orchestrates local and remote agents using the open Agent2Agent protocol.
Clai — Query twelve models and local Ollama directly from your terminal using unix pipes.
Moli — A lightweight, structure-first browser engine with low memory usage.
VoltAgent — Offers open-source flexibility with built-in supervisor agent orchestration and RAG.
OpenSquilla — Maximizes AI intelligence density while minimizing token costs through smart routing.
BrowserOS — Runs entirely locally and lets AI agents use real user logins to complete tasks.
Agenta — Build and automate AI agents that run on your own infrastructure or the cloud.
Adyen — Share AI agent resources across coding tools and repositories easily.
Agent Squad — Runs multi-agent orchestration in Python, TypeScript, and locally on Apple devices.

All Toli alternatives