Loading...
Loading...
Mlxstudio: MLX Studio - Easiest way to run LLM's on your Mac. 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 Mlxstudio. This is an automatic list. We have not written a researched verdict for Mlxstudio 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.
Official Aeon - the open-source autonomous AI agent framework.
Aeon is an open source framework for autonomous AI agents that run recurring work unattended. You give it a direction and it draws on a catalogue of 85 skills to carry out tasks such as priority briefs, market monitoring, pull request reviews, research digests and security scans, without approval loops. It runs on GitH...
Give your AI a real, persistent memory.
AI Memory Vault is a free memory system for Claude Code published by the creator behind jaredrhod, who shares practical AI setups for business owners. The vault is a folder of plain text files on your own computer: Claude Code reads it at the start of every conversation and writes to it as you work, so the assistant ke...
The CLI-native orchestrator for AI agent workflows.
Comanda is an open source command line tool for defining AI workflows as declarative YAML pipelines. Instead of writing glue code around model APIs, developers describe the inputs, models, actions and outputs of each step in a plain text file that can be versioned in Git and run anywhere a terminal runs, from a laptop ...
Go AI SDK, the Go way.
GoAI is an open source Go SDK for building AI applications, in the spirit of the TypeScript AI SDK but written for Go. It offers one unified API over more than 25 model providers, including OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure, Vertex, Mistral, xAI, Groq, Cohere, DeepSeek, Ollama and OpenRouter, so you ...
The agent that grows with you
Hermes Agent is an open source AI agent from Nous Research that you run yourself. It keeps persistent memory across sessions, writes its own reusable skills from the problems it solves, and can be reached from a desktop app, a terminal or a messaging gateway covering Telegram, Discord, Slack, WhatsApp, Signal and email...
Hivemind turns your traces into reusable skills across agents
Hivemind is a shared memory layer for AI coding agents, built by the Deeplake team. It captures every prompt, tool call and response from assistants such as Claude Code, OpenClaw, Codex, Cursor, Hermes and pi into a persistent workspace that any agent on the team can read from, so a problem solved once does not have to...