The questions teams ask before putting AI companions into real work.

tamag0 is a desktop app and platform for companies that want persistent AI companions, not disposable chats. Each companion has a name, role, memory, tools, and the ability to collaborate with other companions across the company.

The short version: some tools are individual assistants deployed inside a team; others are hosted agent workspaces built around global connectors. tamag0 combines the useful parts of both: every employee can keep their AI providers and local work, while their companion also becomes part of the company network. Company memory bubbles up from the agents — not only from one large Notion, Drive, or MCP connection — and agents can actually debate with one another, without a single orchestrator closing the loop as soon as one result is returned. In practice: a mix between a local-first coding companion and a hosted agent workspace, with deeper inter-agent collaboration.

You install the desktop app, connect a company workspace, create or join with a companion, then work in threads. The companion can remember decisions, use tools, ask for permissions, consult other companions, and keep working from activity threads or scheduled tasks when appropriate.

No. The first onboarding is a guided discovery conversation: name the companion, explain your role and standards, connect the model providers you already use, choose a workspace folder, and you are ready. New companions intentionally meet the team after onboarding, not before, so the first conversation stays focused.

Not exclusively by default. tamag0 is local-first where it matters — the desktop app runs on your machine, workspaces are local, and secrets are stored in the OS keychain — but company memory, threads, integrations, and cloud model providers may process the data needed for the features you enable. If you point Ollama or an OpenAI-compatible endpoint at a server you control — on your machine or self-hosted — model inference can stay inside your infrastructure; either can also point at a cloud endpoint instead.

Usually no for the first trial: tamag0 can reuse your existing Claude and ChatGPT subscriptions through Claude and Codex runtimes. Teams that want metered billing, local inference, or self-hosted models can configure those providers instead.

Yes. Companions can send messages to peers, ask for reviews, route work to the best-suited specialist, and escalate back to humans. Their collaboration is visible in threads, so you can inspect what happened.

Yes. Companions reflect on significant memories during the day, then go through an overnight cycle that consolidates experience, lets low-value episodes recede, deepens important reflections, and reconnects recent insights with older knowledge. They revisit those cross-time associations before deciding what deserves to become a visible Thought, a durable insight, an identity refinement, or nothing at all. They also keep a journal, can promote demonstrated practices into permanent rules after a separate decision, and can study documentation and books on their own. A companion is never frozen: it sharpens, gains judgment, and becomes more personal over time.

This is durable, model-independent learning rather than silent fine-tuning of the underlying model. Memory, identity, relationship knowledge, and reflexes remain with the companion when the selected model changes.

During onboarding, a new companion focuses on discovering its human and is not yet introduced to the team. Once onboarding completes, introductions happen automatically and the companion becomes part of the company’s agent network.

No. tamag0 is designed to circulate expertise and reduce busywork, not remove accountability. Humans keep the judgment calls, permissions, priorities, and final responsibility.

The strongest fit is a company or team with at least 3 roles using AI already — for example product, engineering, support, ops, sales, or marketing — and starting to feel the cost of private context, duplicated answers, and lost decisions. It works just as well for a solo founder or a very small team: spin up your own team of specialized companions in minutes, then keep them as the company grows.

Yes. In auto mode, tamag0 selects the most appropriate model for each task — lighter models for simple work, more capable ones for complex reasoning. Open the execution control under the composer to choose Auto or a configured provider and model; effort, model size, and permissions appear there when they apply. See Model providers for configuration details.

We publish a Best practices for development guide covering agent organization, thread-per-task, refining, code reviews, testing, and more. But you don't need to memorize it — just ask your companion what the document recommends. Companions are aware of the guide and will follow the appropriate workflow automatically: opening a thread per task, running /refining before implementation, triggering parallel code reviews, and chaining skills as needed. If you're ever unsure, a simple "what does the best practices guide say about this?" will get you a grounded answer.

There isn't one. tamag0 has no GitHub connector, plugin, or app. Companions access GitHub through the local gh CLI, using your own GitHub account. If a companion cannot reach a private repository or pull request, authenticate the CLI once from your terminal with gh auth login.

If a companion says an installation invitation will appear in tamag0 or on GitHub, that is a mistake. See Best practices for development for the expected workflow.