A big one: a turn can now keep going when its model gives out, you can roll back what a turn did to your files, and bots can build up skills of their own.
Fallback models. When a model hits its usage limit, loses its login, is unavailable or runs out of context, the turn can continue on the next model in your list, API-key providers included. Set it up in Settings Models and agents Fallback models. It's off until you add a model, and you can pin a conversation to its own model.
Undo a turn's file changes. When a turn changes files, its answer shows the diffs, and "Undo changes of this turn" puts them back, whether the agent used its file tools or ran commands. You review each file first, can undo just one, and can redo. It works with or without Git.
Bots keep their own skills. A bot can save a procedure it learned as a skill and improve it over time. In the bot's Settings Skills you see each skill's history, restore a version, edit or lock it, or require your approval before a change takes effect.
One account rotation per provider. Claude and Codex accounts now share a single ordered rotation in Settings Accounts. An account you pick directly stays fixed and stops when it runs out instead of switching. The failover routes you already had become the new rotation.
Long conversations hold up better. Agents search past messages by what they're about, not only by exact words, and compaction keeps decisions, pending requests and exact identifiers in fixed sections, with the latest part of the conversation kept word for word.
Sturdier with local models. Ollama, LM Studio, llama.cpp and vLLM report the context window they actually run with, and malformed tool calls from any model are repaired before they fail.
Release notes: https://github.com/antonioducs/m...
Hey Product Hunt!
I built Maestrly because my AI coding workflow had turned into a mess of Claude Code sessions, Codex terminals, worktrees and forgotten tasks.
I wanted something closer to Cursor, but provider-independent: keep the subscriptions and tools I already use, while having one place to coordinate the work.
Maestrly runs locally and is free and open source (MIT). It is still early, so I would genuinely love feedback from people already juggling multiple coding agents.
Update, October 2026: a lot has changed since launch. Maestrly now puts Claude, ChatGPT/Codex, GitHub Copilot, Cursor, Google AI and Grok in the same conversation, Maestro coordinates a team of subagents, and code and plan reviews run before anything ships. You can also run bots with their own Linux desktop on your own server, follow them from the iOS and Android app, and install Codex and Claude Code plugins that work with every model. Release notes: https://github.com/antonioducs/m...
The parallel-agents-with-isolated-worktrees approach is exactly what heavy Claude Code/Codex users need. Do you let people point these agents at a custom Anthropic-compatible endpoint rather than only the official subscriptions, or is auth locked to the vendors' own accounts right now?
Thanks @tian_yi1 ! Auth isn’t locked to vendor accounts. Maestrly runs your locally installed Claude Code or Codex CLI, so if you’ve configured either one to use a custom API URL/provider, that same configuration works inside Maestrly.
You can also use Maestrly Chat with any BYOK provider and custom endpoint. So users can choose between their existing subscriptions, custom CLI endpoints, or their own API keys and providers through Maestrly Chat.