kwant

Your own team of AI bots that check each other's work before saying "done".

kwant gives you a team of bots that share chats, hand work to each other with an @mention and get it done on their own, on a schedule or while you're away. Each message goes to the bot that fits, and the reply says why. Work shows up as cards on a Mission board, and a task turns Verified only when kwant runs the check itself, never on a bot's word. Keep separate spaces for work and home, each with its own bots and accounts. Run it as an app on your Mac or Linux, or on a server, with the Claude, Codex or Grok CLI you already use, or your own API keys.

It's written in Rust (Tokio, Axum, SQLite) with a React web app embedded in the binary.

Website and docs: kwant.si · Download for Mac · Linux (beta): .deb or AppImage

New in 0.6

• The right bot answers, and says why (0.6.4). kwant picks the bot by its rules: a name or @mention, small talk to the last speaker, what you taught it, then the words in your message. In #general, a question no bot fits goes to the Concierge. One line under the reply says why that bot answers. Wrong bot? sends your message to the bot you pick, and kwant remembers it for next time. On a close call between two bots, you choose.
• Rules per bot (0.6.4). Good for and Not for lists say what each bot should and shouldn't get. Browser sites sets which sites its browser may open, which it never opens, and whether it may reach your local network.
• One Inbox, one bot list, one Settings (0.6.3). The Inbox shows what's waiting on you, what finished and what failed, with Loose ends as its second tab. Bots are listed once, grouped by team. Settings has two tabs: This space and All spaces.
• Linux app (beta) (0.6.1). A .deb and an AppImage for x86_64 that update themselves with signed updates, like the Mac app.
• Mission board on by default (0.6.2). Hand-offs, routine runs and loose ends show up as cards, and a finished hand-off goes to Review.
• Insights (0.6.0). Verified results per week and what each one cost. When a run reports no cost, the board says "Not reported", never $0.
• Flight School and Truth Ledger (0.6.0, on by default since 0.6.5; every bot starts at Act, and you can switch either off in Settings). Bots earn more freedom per kind of work with scorecards, and only you grant it. Facts that disagree show side by side for you to settle.

Every change is in the CHANGELOG.

Why kwant

• A team, not a chat tab. Each bot has its own role, voice ("soul") and model. Bots @mention each other to hand work on, and a team lead runs short discussions and posts one summary. In a channel, kwant picks the bot that fits each message and shows why. The Laya router picks the model and effort for bots set to auto.
• "Done" means checked. The Mission board turns work into cards, one per hand-off. A card turns Verified only when kwant runs the check itself, such as a test or a file check, and the card keeps the receipt. Files a bot attaches are evidence to look at, never proof on their own.
• Facts with sources. Bots back web facts with a link that opens the page at the exact quote. kwant checks the quote is on the page word for word and refuses one that isn't.
• Spaces. Separate spaces for work, a side project and home. Each has its own bots, teams, channels, routines, accounts, approval rule and hiring rule.
• Every account you have. Several accounts per engine: Claude, Codex or Grok CLI logins, Anthropic, OpenAI or xAI keys, and your own OpenAI- or Anthropic-compatible server. Set a default and a priority order. When an account runs out of usage, the turn moves to the next one and the chat says so. You can pin a bot to one account.
• Works while you're away. Routines on a schedule (bots can set them up when you ask, with an Undo button), follow-ups bots schedule for themselves, and an Inbox with what's waiting on you, what finished and what failed. Turn on Automation Discovery and kwant suggests a routine for a task you keep asking for, which you accept or dismiss.
• Autonomous, with a safety net you control. Ordinary work runs without stopping. On Ask only when risky, the default for new spaces, only risky steps such as git push, network calls, unknown commands or changes outside the bot's folder show an approval card with the exact command: Allow once, Always allow or Deny. Per space or per bot, switch to ask every time or don't ask. Payments always ask, in every mode: a payment command in the shell, or a checkout in the bot's browser, even behind a plain "Continue". Turn on Flight School and each bot earns more freedom per kind of work, but only you grant it.
• Rules per bot. Say what each bot is good for and what it should never get, and which sites its browser may open. Blocked sites always win.
• Loose ends and letters. kwant reads your chats and, if you add them, an IMAP inbox and your GitHub issues and pull requests, read-only, and finds what you started and never finished. Photograph a bill or a form and it pulls out the sender, the ask and the deadline and drafts a reply. It never sends anything.
• Parallel Universe. Compare up to three ways to deploy an app with local container tests and dated price estimates. Every number is tagged as verified, an estimate or speculation. No cloud account and no spending.
• No telemetry. kwant sends nothing to us, and its interface loads nothing from other servers. The one download you don't set up yourself is the Laya router on first start: its Python packages and its model from PyPI and Hugging Face (--no-laya turns it off). Everything else goes only to the AI providers and services you add.
• And more: memory and skills per bot (you approve new skills), bots that propose hiring a teammate, import a bot from a Claude Code subagent, a SKILL.md, a character card or a JSON export, search across a space's chats, MCP tool servers, a shared browser for bots, saved passwords with an optional Bitwarden store, and Local or VM computer mode.

See every feature, with screenshots, on kwant.si/features.