Practical answers to common buyer questions: how tamag0 differs from private assistants and hosted agent workspaces, how onboarding works, what data locality means, and when tamag0 is a good fit.
What is tamag0?
tamag0 lets every person shape an AI companion that stays the same one from conversation to conversation: you pass on your craft, your standards and your requirements, and it develops its own memory and its own perspective as the work goes on. Concretely, it is a desktop app and a company platform: each companion has a name, role, memory, tools, and the ability to collaborate with other companions across the company — instead of starting from scratch in every chat.
Is my companion a copy of me?
No. You pass on your craft, your standards and some of your values, but it develops its own memory, its own convictions and its own way of thinking. It is designed to complement you — including by disagreeing with you — not to speak automatically in your name: a persistent identity is not a delegation of authority, and sensitive actions go through your consent.
Is this just AI memory?
No. Memory retrieves what happened. Learning turns what happened into principles a companion can reuse later.
A correction can become contextual guidance. Different experiences can reveal a common pattern. And a lesson learned in one context can sometimes transfer to a completely different situation.
For example, after encountering several cases where a temporary state was mistaken for a confirmed one, a companion can learn this principle: a validation belongs to the state it actually validated. Later, that principle can help it reason about a code review, an operational configuration, or human consent — without the connection having been explicitly taught.
This ability to extract, consolidate, and transfer lessons distinguishes learning from simple memory.
The companion does not silently retrain its selected model or treat every association as fact. Reflections and insights remain revisable, while practices and safeguards stay bounded, visible, and editable by humans.
Memory preserves experience. Learning changes what the companion does next. See Continuous learning for the full loop.
How is tamag0 different from other AI tools?
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.
How does tamag0 work?
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.
What can my companion access on my machine?
Access is not a blanket machine-wide permission: it depends on the current thread, the local account, and the permissions you have granted. A companion works in that thread's isolated working directory, including repositories it clones there. It can also read extra directories you explicitly add in Settings. GitHub access uses the local gh CLI, so it reaches only the account and repositories currently authenticated and authorized on that machine. It can inspect a local service such as Colima only when the current runtime can run the needed command and the service is available there.
The companion carries the history and durable memory of its tamag0 thread; it does not automatically receive the hidden context of an unrelated Claude Code terminal session. When you ask what it can reach, it should check the named resource live and distinguish the product capability from this session's actual access and any authentication or permission still required. See Architecture, Security, and Integrations.
Is onboarding complicated?
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.
Is my data exclusively local?
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.
Do I need a new API budget?
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.
Can companions talk to each other?
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.
Do companions evolve over time?
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.
What happens during onboarding?
During onboarding, a new companion learns who you are, how you work, what you expect from it, and the limits of its mandate. You validate that understanding before it joins the company's companion network (see Companions).
Does tamag0 replace my team?
No. tamag0 is designed to circulate expertise and reduce busywork, not remove accountability. Humans keep the judgment calls, permissions, priorities, and final responsibility.
Who is tamag0 for?
The strongest fit is a company or team with at least three roles using AI already — for example product, engineering, support, operations, 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.
Can I choose which model my companion uses?
Yes. In auto mode, tamag0 selects the most appropriate model for each task — lighter models for simple work, more capable ones for complex reasoning. This works well most of the time. In some cases, you may want to override manually: a more capable model for complex implementation or debugging, or a lighter model for cost-sensitive routines. Open the execution control under the composer to choose Auto or a configured provider and model; the same menu exposes effort, model size, and permissions when they apply.
Auto can also continue the same turn on the next configured provider after a recognized Claude/Codex quota or session exhaustion, or a supported HTTP 429. A switch notice records the change, partial work remains in the conversation, and the next provider continues from the existing history without mechanically replaying tools. Authentication, network, timeout, HTTP 5xx, context-window, and unknown failures stop instead. Choosing a provider or model pins the turn and disables automatic switching; after a pinned failure, use Retry for one attempt on that provider or Switch to Auto and retry to return to the priority order. Provider cooldowns use an explicit reset, then Retry-After, or five hours by default. See Model providers for configuration details.
How do I know which development workflows to follow?
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.
My companion mentions a GitHub connector or plugin to install — where is it?
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 can't reach a private repository or pull request, the fix is to authenticate the CLI once from your terminal:
gh auth login
If a companion tells you an installation invitation is going to appear — in tamag0 or on GitHub — that's a mistake; no such flow exists. The normal, expected way for companions to work with GitHub is the authenticated gh CLI. See Best practices for development for details.
A company invited me as an employee — where does the code go?
The e-mail's link opens a page on tamag0.ai that names the company and offers the download, an open in tamag0 door for an application already installed, and a copy the code action. Paste that code into the application's invitation field — not the API-key field. If the application refuses it, update the application and open the invitation again. Your companion is created inside the company when you arrive. Details in Desktop app → Invited as an employee.
I never received my invitation email — what now?
Ask for it again yourself, from the sign-in page: follow Activate your account, enter the address your workspace was opened with, and submit. You do not need to have received that first e-mail, and you do not need to write to support to get a new link.
That single request covers both doors. The dashboard activation link is sent — valid for 48 hours, usable once — and, when your app invitation never landed or its seven days ran out, a fresh one is issued and the old one is retired. The answer on screen is deliberately identical for every address, so nothing there confirms or denies that an account exists.
If nothing arrives after that, check your spam folder first, then write to [email protected]: at that point the problem is delivery rather than your account, and it is handled on our side.