Loading...
Loading...
Mega: Mega is an open-source implementation of Google Piper — a Git-compatible monorepo engine built for the AI Agent era. 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 Mega. This is an automatic list. We have not written a researched verdict for Mega 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.
Codex for Android, iOS & Mac.
Aether is an open source AI agent app for the phone and desktop, originally built for Android and now also available for iOS and macOS. It pairs a polished conversation interface, inspired by apps such as ChatGPT and Codex, with a local agent engine built on the Pi harness kernel, so the agent can run shell commands, c...
The local-first Agent OS — your AI partner lives on your own machine.
Avibe is a local agent operating system for the coding agents developers already run: Claude Code, Codex and OpenCode. It installs with a single shell command and wraps those official command line agents in one runtime on the developer's own machine, adding a browser based Workbench, durable background work, multi agen...
Bub it. Build it. A tiny agent runtime, composable with plugins.
Bub is a small, open source Python runtime for building AI agents that work in shared environments. It began in group chats, where several humans and agents had to share one conversation, so it avoids hidden state and opaque memory. It builds on the agents.md convention and Agent Skills, and starts as a working agent t...
An open-source long-horizon SuperAgent harness that researches, codes, and creates.
DeerFlow is an open source agent harness, built on LangChain, that researches, writes code and creates content on a user's behalf. Version 2.0 extends the project from a deep research agent into what its authors call a full stack super agent: it combines sandboxes, memory, tools, skills and subagents to handle tasks th...
Agent framework for the JVM.
Embabel is an agentic AI framework for the Java Virtual Machine. It is written in Kotlin with a usage model intended to feel natural from Java, and its argument is that the qualities which matter once AI becomes mission critical, namely context handling, reliability, type safety, performance, observability and integrat...
Self-healing infrastructure for AI agent payments.
Helix is infrastructure that lets AI agents learn from one another's failures. It sits between an agent and the services it calls, and when a tool call fails it classifies the error, constructs and evaluates a fix, then commits the repair as a reusable Repair Pattern in a shared graph. The next agent that hits the same...