Maintainer of this skill?
by eduwxyz
Your team of AI agents, on your Mac. Agents that talk in channels, write code, review each other and use your tools, on the Claude Code, Codex, OpenCode or Pi you already have. Anything that touches the real world waits for your yes.
# Add to your Claude Code skills
git clone https://github.com/eduwxyz/tucanoSee how tucano compares with popular alternatives.
tucano is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by eduwxyz. Your team of AI agents, on your Mac. Agents that talk in channels, write code, review each other and use your tools, on the Claude Code, Codex, OpenCode or Pi you already have. Anything that touches the real world waits for your yes. It has 51 GitHub stars.
tucano's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/eduwxyz/tucano" and add it to your Claude Code skills directory (see the Installation section above).
tucano is primarily written in TypeScript. It is open-source under eduwxyz on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh tucano against similar tools.
No comments yet. Be the first to share your thoughts!
Available after the catalog security scan passes.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
Your team of AI agents, on your computer. Your rules.
Agents that talk in channels, write code, review each other and use your team's tools. They do the work. Anything that touches the real world waits for your yes.
English · Português · tucano.sh · @tucanosh · Changelog
https://github.com/user-attachments/assets/533e1bf1-b4ca-4f4a-aad4-e015c6b4c421
Coding agents got good. Working with several of them is still a mess of terminals, copy-paste between sessions, and hoping nothing runs that shouldn't. Tucano puts them in one place that feels like your team's chat, and gives you the controls a team lead would want.
@mentions and hand work over: one finds the bug, another fixes it, a third reviews it, and you get the result.Create a channel, add the agents, and ask. Mention someone with @, or don't, and a router picks who answers. Agents pass the turn to each other with @mentions, so a request can travel from investigation to fix to review on its own, and every step shows up in the conversation: what it searched, read, ran and edited, with a receipt of tokens and time.
Tucano speaks MCP. Add Jira, GitLab, GitHub, Slack, Linear, Figma, Notion, Datadog, Sentry, or the internal server at mcp.yourcompany.internal: remote servers with OAuth or a token, or local ones. Then decide, per agent and per tool, what it can touch.
Write actions that matter wait for your OK, with the exact call and its arguments in front of you. Approve once, always allow a safe one, or refuse with a reason the agent reads. Approvals also reach your phone through Telegram. Each agent has a monthly token limit and a ceiling per reply, and Pause everything stops all agents at once.
Agents remember what matters about you, your projects and your preferences, and you see, approve, edit and forget every memory. When an agent keeps taking the same path, it proposes a skill, a written recipe the whole team can follow. Skills you already use in Claude Code and Codex come in with one click.
Schedule work for a day and time, or for when something new shows up in a connector: a new issue, a failing monitor, an email. Your week appears as a calendar with how each run went, and quiet hours keep the night quiet.
Missing someone on the team? Tell Tuca what you need, the way you'd explain it to a new colleague, and it drafts the agent: name, role, instructions, model and tools, for you to create, edit or adjust.
Usage and limits shows each agent's month against its limit and your subscription's windows. The weekly Report shows what each issue cost, in tokens and replies, and where the time went.
Give an agent a computer, an isolated Linux in Docker where it installs, runs and tests, or, if you choose so, your own computer. Lend it a folder or a repository. Give it a browser of its own, a Chrome you can watch live and take over when it needs to sign in somewhere.
| Harness | Sign in with | Notes |
|---|---|---|
| Claude Code | Claude Pro or Max, or your company's login | Reads only the env block and apiKeyHelper of your ~/.claude/settings.json; hooks, plugins and permissions stay out |
| Codex | ChatGPT Plus, Pro or Business | Runs with a home of its own, so your skills, AGENTS.md and plugins don't leak in; you sign in once inside Tucano |
| OpenCode | The providers you configured | Uses the models you have logins for |
| Pi | The providers you configured | Uses the models you have logins for |
Each agent picks its harness and model, so a team can mix them: Opus to fix, GPT to review, Haiku to route.
Behind a company gateway? If your Claude Code or Codex already sends requests to your company's AI proxy, Tucano's agents go the same way, with no extra setup. Telemetry and error reports of a harness on a gateway stay off, and the model list comes from the gateway itself. To use only the gateway, uncheck the other harnesses in Settings → Models.
You need a Mac with Apple silicon (M1 or later; tested on macOS 26) a Linux PC (x64 or ARM64; tested on Ubuntu with KDE and Xfce) or a Windows 10 or 11 PC (x64), and at least one harness, installed and signed in. On Windows, also Git for Windows: its Git Bash runs agents' commands on your PC, and Claude Code needs it there too. Optional: Docker to give agents a Linux computer (Docker Desktop on a Mac or Windows; Docker Engine or Docker Desktop on Linux), and Google Chrome (or Chromium, on Linux) for their browser (without it, the built-in browser is used).
1. Install a harness. Claude Code is the quickest:
curl -fsSL https://claude.ai/install.sh | bash
claude auth login
On Windows, in PowerShell: irm https://claude.ai/install.ps1 | iex, then claude auth login. Prefer Codex? npm install -g @openai/codex. You'll sign in from inside Tucano.
2. Install Tucano.
On a Mac: download the .dmg, open it and drag Tucano into Applications. The app is signed and notarized by Apple, so it opens with no warning.
On Ubuntu, Debian and their family (Mint, Pop!_OS…): download the .deb and open it, or run sudo apt install ./tucano-linux-amd64.deb.
On other Linux distributions: download the AppImage, make it executable (chmod +x) and open it. It needs FUSE, which most systems have. On Ubuntu 24.04 and later, prefer the .deb: it installs the AppArmor profile Electron apps need there.
On ARM64 Linux, take the files that end in -arm64 (tucano-linux-arm64.deb, tucano-linux-arm64.AppImage).
On Windows: paste this in PowerShell. It installs Tucano for your user, with no admin rights, and opens it:
irm https://github.com/eduwxyz/tucano/releases/latest/download/install.ps1 | iex
Or download the installer and open it. It isn't code-signed, so the first time Windows says it protected your PC: click More info, then Run anyway. The PowerShell command skips that warning, since a file PowerShell downloads isn't marked as coming from the internet.
Or from the Terminal, on a Mac or on Linux:
curl -fsSL https://github.com/eduwxyz/tucano/releases/latest/download/install.sh | sh
It downloads the latest release and opens it. On a Mac it puts Tucano in Applications; on Linux it installs the .deb with apt (it asks for your password) or, without apt, the AppImage in ~/.local/bin with an entry in the applications menu. Run on Windows (in Git Bash, say), it points you to the PowerShell command above.
On a server (a VPS, to keep routine