Loading...
Loading...
Nautilus Compass: Reliability layer for multi-agent setups — keep agents coordinating without an orchestrator. It is listed under Development & Code on AI Registry as a free tool.
The tools below are approved listings in the same category, ordered by how closely their tags match Nautilus Compass. This is an automatic list. We have not written a researched verdict for Nautilus Compass yet, so treat it as a shortlist and check each vendor's pricing page before switching.
Built from each tool's listing. Vendors can update their own listing after claiming it.
AI builder operating system.
basemode, whose command line tool is called base, is a shared memory layer for coding agents that places the right context in front of an agent at the moment it works, without the agent having to search or make a tool call. It holds a team's rules, decisions, notes and a map of the codebase in a graph, and injects the ...
Sno Station — your Claude Code and Codex working as one squad on your own machine.
Sno Station is open source software that runs on a developer's own machine and turns the AI coding agents they already use into a single working squad. It supports Claude Code, Codex and OpenClaw, and gives them one shared memory, a mailbox they use to wake each other up, and a set of skill files they follow and revise...
AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x
AG2 is an open source Python framework for building, orchestrating and scaling multi agent AI systems, created by the original creators of AutoGen. It lets developers define teams of specialized agents that converse, use tools and hand work to each other, and it sits at the core of a wider commercial platform the compa...
Minimal kernel to make any AI coding agent stateful.
Agent Kernel is a minimal way to make any AI coding agent stateful, using three markdown files and a git repository instead of a framework or database. You clone the repository, start a coding agent inside it and talk to it; the agent reads the kernel, recognizes that it is new, asks who it should be, and from then on ...
Sandbox your local AI agents so they can read/write only what they need
Agent Safehouse is a macOS native sandbox for local AI coding agents. It wraps an agent process in kernel level enforcement through the operating system's sandbox facility, so an agent running with its permission prompts switched off still cannot write outside the project directory or read sensitive files. A destructiv...
Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task.
Agentlas is a desktop and cloud workspace for putting a team of specialist AI agents on a single goal. Users turn a brief into tasks, give each agent a role, context and a clear handoff, and review the combined output, then keep the method for reuse. Hephaestus, the component listed here as Agentlas OS, is its open age...