Meet Tucano: your AI agent team, on your Mac.
Agents talk in channels like a work chat. They write code, review each other and use your tools: GitLab, Slack, Datadog, Figma. Anything that touches the real world waits for your yes.
Free and open source. Runs on the Claude Code or Codex you already have.
Tucano 0.2.44 is out, and it's a big one:
Cofre: your API keys and logins, used by your agents by name, never seen
More autonomous agents: they carry a request through, call in another agent when needed, and retry on their own when something fails
MCP: your Claude Code, Codex or Cursor can set up your Tucano team and talk to it
Archived agents can now be deleted for good
Release notes github.com/eduwxyz/tucano/re…
Tucano 0.2.42 + 0.2.43 🧡
Your agent sent you a .docx? Now you just hit Download, on Tucano Pro in the browser too. On desktop, it's Open and Save.
Plus: one "Thinking" row per reply, cards that don't duplicate, archived agents folded away, wiki in your language, clearer dictation on a server.
Updates itself from the app
Tucano 0.2.37 is out.
The Board: every agent's work as cards, one per task, with what needs you in its own column.
Plus a lighter app, same identity. You can even hide what you don't use from the sidebar.
Release notes github.com/eduwxyz/tucano/re…
Tucano 0.2.37 is out, and it has a new look.
Less on the screen, not one feature less. Agents are one list, by sector. Memory, Wiki and Skills are now Knowledge. Routines, Report and Usage are now Operations. And you can take out of the sidebar whatever you don't use.
The star is the Board: your whole team's work in one place, one card per task. When something needs you, the card comes forward with the question and the story of who did what.
Also new: feedback with a screenshot, right from the app, and a second Antigravity account.
Update, or get it at tucano.sh
Tucano 0.2.36 🧡
Your Tucano runs on a server, but the work is often on your computer.
Now you can lend your computer to the server: its agents use this computer's terminal, folders, browser and apps. Only the folders you pick, under the server's approvals, with no open port.
Also: routines at several times a day, an official Docker image and 9 routine fixes.
Release notes: github.com/eduwxyz/tucano/re…
You asked for it a lot: your Tucano agents on a server can now use your computer.
They stay on 24/7 on a server (or Tucano Pro) and, when they need to, run commands, work on your projects and use your PC's browser and apps (Mac, Windows or Linux).
One click in Settings › Servers. No ports to open, no network setup.
Tucano 0.2.36 🧡
Tucano 0.2.35 🧡
Been using Hermes Agent for a while? You can now bring what you built there.
Settings › General › Team › Import from Hermes:
• each profile becomes an agent, its SOUL.md the instructions
• memories arrive waiting for your yes
• skills and scheduled jobs come along (jobs as routines, off)
You see everything before importing. .env, auth.json and sessions are never opened.
Many people are helping me with Tucano on a daily basis, whether by reporting bugs, recommending it in various threads, suggesting new features, or even submitting pull requests.
Big things are on the horizon, and I won’t forget those who helped out in the early stages! 👀
Tucano 0.2.33 is out.
You can now choose what each person on the team sees: sectors, agents and channels. Someone who only handles finance doesn't see engineering, and neither does the agent working for them. Already live on Tucano Pro.
And if the app closes mid-reply, the agent picks up where it stopped, without redoing what it already did.
Thanks @EiAllanJones, @apoapostolov404 and @stefanosandes for the PRs 🙏
Release notes github.com/eduwxyz/tucano/re…
People keep asking how I actually use Tucano day to day.
This video is one of my workspaces: the team that helps me build Tucano itself. 14 agents in 3 sectors, and I only talk to one of them.
I'm the only maintainer. There's the desktop app, iPhone, Android, PR review, store releases, customer email, posts, Discord. That doesn't fit in one person. It doesn't fit in one agent either: ever tried setting up a single Claude or Hermes to handle all of it? You end up with a giant prompt that does everything halfway.
In Tucano I split it up like a company:
- Orion is my entry point. I ask him.
- Engineering: Bento leads, Vera reviews, Nilo handles mobile, Otto ships.
- Customers: Clara and Caio.
- Growth: Iris, with one agent per network.
In the video I send a single sentence: "Caio says an attached PDF only arrives as text, fix it and let everyone know."
Orion passes it to Engineering and Growth. Bento splits the work. Engineering asks Customers to draft the reply to the person who reported it. Every line that lights up is a request with an owner, and the answer travels back the same way until it reaches me.
Two rules hold it together:
- An agent never talks to an agent in another sector. Only head to head.
- Nothing goes out without my OK.
The bug in the video was real: @caiotferreira reported it today and the fix shipped in 0.2.31. The video is a demo of how a request like that moves through the team.
Tucano is open source and runs on your own computer, on the Claude Code or Codex subscription you already pay for. Download it, create two agents, connect one to the other and send a request. Watching that first line light up is what sells it.











