Loading...
Loading...
Magpie: Every agent's model. One place. 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 Magpie. This is an automatic list. We have not written a researched verdict for Magpie 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.
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...
Your personal AI agent platform — self-hosted, BYO Claude/Codex subscription
OtoDock describes itself as an agentic company operating system. It turns Claude Code and Codex into a team of agents that run on the customer's own server, working through the customer's existing Anthropic and OpenAI subscriptions. Local models through Ollama, llama.cpp, LM Studio or vLLM are also supported, and the e...
Multi-LLM orchestration framework
PuzldAI is a multi LLM orchestration framework that wraps existing command line AI tools, including Claude, Gemini, Codex, Ollama and Mistral. Because it drives those installed CLIs, the documentation states that no separate API keys are required by PuzldAI itself. It is used from a terminal interface or through comman...
Native macOS app to monitor AI usage limits and watch your coding sessions live
TokenEater is a native macOS menu bar app with widgets that track Claude and OpenAI Codex usage limits in real time. It shows the live five hour session window and the weekly window, so a developer can see how much capacity remains and when it resets, for Claude (Pro, Max or Team) and for Codex with a ChatGPT sign in. ...
wanman is an open-source agent matrix runtime inspired by Japanese one-man trains.
wanman is an open-source agent matrix runtime inspired by Japanese one-man trains. It lets human users step back into an observer role while local agent runtimes coordinate autonomous multi-agent workflows, task execution, and artifacts.
10x - Up to 20x faster AI coding with multi-step Superpowers.
10x is a terminal based AI coding agent that reads a whole codebase to plan, generate and verify code changes. It runs in the shell rather than as an IDE plugin, with full file system access for reading, writing and editing files, glob and grep search, and the ability to run commands, scripts and build tools while show...