ClarkCant
GitHub

Open-source AI agent

Tell Clark
what you want.

ClarkCant works on your computer through a single conversation. Type it or say it. Clark handles the rest.

    A preview. Replies on this page are scripted; the real Clark runs on your own machine.

    Chapter one

    Clark couldn't.

    Clark Cant was our first AI agent, named as a joke on Clark Kent. In the beginning he could barely do anything. Every step ran into a guardrail: a refusal, a confirmation, a permission he didn't have.

    Honestly? He was almost useless.

    Chapter two

    Then Clark could.

    The guardrails didn't vanish. They moved into the system underneath: work confined to the folders you allow, a visible trail of what he did, and a Stop button that always works. The wall of dialogs came down.

    Clark became a teammate, and helped us build more than one product.

    Chapter three

    ClarkCant Can.

    We kept the name as a reminder of where he started. ClarkCant is that teammate, opened up for everyone: one conversation, one voice, and an agent that gets on with what you asked.

    Talk, don't operate

    One conversation.
    Everything else is plumbing.

    Most agent tools hand you the machinery and wish you luck. ClarkCant keeps it where it belongs: underneath. You never need to learn how an agent works to get something done.

    Clark

    Move last week's screenshots into a folder and name them properly

    Done. 37 screenshots are in Screenshots / Week 38, named by what's in them.

    Tell Clark what you want…

    What you see.

    • SessionsClark keeps one conversation. You never pick a session.
    • Context windowsWhat to remember and what to drop is his problem.
    • Models & routingChoose one if you care. Otherwise, don't.
    • Skills & toolsFound and used when the task needs them.
    • SubagentsIf work splits, it comes back into the same thread.
    • MCP serversConnected through chat, not config files.
    • Hooks & workflowsBehaviour you describe, not wiring you draw.
    • Runtimes & nodesYour laptop, your server. Same conversation.
    • PoliciesPick how bold Clark is, once. Change it by asking.
    • Audit trailEvery action written down, there when you look.

    What Clark handles.

    Rich replies

    Sometimes the best answer
    isn't text.

    When a list, a chart or a tiny app says it better, Clark draws one right inside the reply. No new window, no new app to learn. Go on, use these.

    Split a $186 dinner five ways, with tip

    Which of these three laptops should I get?

    Give me a 25-minute focus timer

    Find the contract I signed in March

    Examples built for this page to show the idea, with made-up data. In ClarkCant, widgets and mini-apps render inside the conversation, and every tool Clark uses appears as a widget you can open to see exactly what it did.

    Voice

    Voice is the
    same Clark.

    Not a separate assistant with a separate memory. Speak and it lands in the same conversation, with the same context and the same abilities. Start typing, finish talking, or the other way round.

    1. Draft a reply to Linh about moving Friday's meeting
    2. Drafted. Want me to suggest Monday at 10?
    3. “Make it Tuesday, and a bit warmer.”
    4. Updated. Tuesday, and friendlier.

    Uses your microphone only to move the Orb. Nothing is recorded or sent anywhere.

    What we hold ourselves to

    AI should make computers
    easier, not more complicated.

    1. Conversation is the app.

      No dashboard to learn, no sidebar of modes. Asking, seeing results, changing settings: it all happens in one place.

    2. Talk, don't operate.

      Say the outcome you want. Finding the right tab, tool or command is Clark's job.

    3. Voice is the same Clark.

      One agent, one memory, whether you type or speak.

    4. Sometimes the best answer isn't text.

      Tables, charts and small apps appear right in the reply, when they help.

    5. Power underneath. Not in your face.

      Details stay out of the way until you ask for them or something needs you.

    6. Don't make people learn the architecture.

      Nobody should need to understand sessions, runtimes or servers to finish a task.

    7. Honest, always.

      No fake progress bars, no “done” that isn't. If Clark doesn't know, he says so.

    The app today

    This is all
    you see.

    The real ClarkCant app, not a mockup. The Orb, one question and one place to type or talk. Everything else waits underneath until you need it.

    The ClarkCant app in dark mode: the glowing Orb in the centre, the question “Bạn đang nghĩ gì?”, a suggestion to reopen the latest session, and the message box below it.
    Dark
    The same ClarkCant screen in light mode, with the Orb, the question and the message box.
    Light

    Open source · Apache-2.0

    Yours to run, read
    and make better.

    ClarkCant runs on your own machine or server. The code is open, the roadmap is public, and it's meant to be approachable even if you've never touched an agent before.

    Early days v0.2.1 · bootstrap, not a release

    We'd rather tell you where things stand than impress you. The foundations are in and tested; parts of the experience are still being built.

    Working today

    • One conversation. Replies stream in, tool calls show as widgets, / picks a skill and @ points at a file, project or service.
    • Runs where you want. A headless runtime on your own machine or server, with read-only search across your files.
    • Answers you can use. Tables, charts, a calendar, maps, diagrams, timelines, a Kanban board, forms, code and diffs, audio, documents and media, drawn inside the reply.
    • An inbox you act on. Open, snooze, undo or ask about a notification, typed or spoken. Approvals stay yours.
    • Work that keeps going. Background tasks, reminders and triggers, website tasks on your own model, and GitHub issues taken to a draft pull request.
    • Control you can see. An execution policy checked before every effect, an audit trail of every action, and Stop. When Clark can't tell whether something happened, he says so.
    • Make it yours. Six Orb styles and theme packages, changed in Settings or just by asking.
    • Built to build on. REST, MCP, WebSocket and a CLI on one token, plus a widget authoring loop, reference apps and packages that bring their own sandboxed service (docs).

    Not yet

    • The full desktop app
    • Live sign-in to services like Google Calendar
    • Installing capabilities end to end from chat
    • Native computer control on macOS and Linux
    • The clarkcant CLI on npm (run it from the repo for now)
    Read the full, honest ledger →

    Try it from source

    Needs Node.js 22.19+. The installer clones the repo, then walks you through the model, your key and where Clark runs: on this machine or in Docker.

    # macOS / Linux
curl -fsSL https://raw.githubusercontent.com/digitopvn/clarkcant/main/tools/install.sh | sh
    # Windows PowerShell
irm https://raw.githubusercontent.com/digitopvn/clarkcant/main/tools/install.ps1 | iex

    Docker, VPS with HTTPS and manual setup →

    Star on GitHub Share an idea

    With gratitude

    Standing on Pi.

    ClarkCant is inspired heavily by the philosophy and work behind the Pi agent ecosystem, and its agent core is built on the Pi coding agent SDK. Small, understandable, yours. Thank you to Pi's authors and community.

    ClarkCant Can.

    You don't need to learn how the agent works.
    Just tell Clark what you want.

    Tell Clark