Alternatives · OpenClaw

An OpenClaw alternative that checks the work

kwant is an open-source, self-hosted team of AI bots in one app, with nothing extra to install. A task counts as Verified only when kwant runs the check itself, and a bot that can't go on tells you why. It can bring in your OpenClaw workspace.

OpenClaw is an open-source AI assistant that runs on your own computer and meets you in the chat apps you already use, according to its README. kwant also runs on hardware you control, and its source is public too. The difference is in how a team of bots shows you what got done, what stopped and why.

If you want to try kwant without starting over, it can read your OpenClaw workspace and recreate each agent as a bot. See what the import brings across.

What kwant does differently

  • Verified means kwant checked it. Work shows up as cards on a Mission board. A card turns Verified only when its checks pass: a command such as the tests, a web address that has to answer, a file that has to exist, a review by a teammate who isn't the task's owner, or you pressing Verify. A bot can't verify its own work, and a check a bot adds to its own task waits for your OK. See what "Verified" means.
  • A bot that stops says so, and why. When a step fails or is refused, a bot tries it again, then tries another way. If nothing works, its last line starts with Blocked: and says what would unblock it, and from a team's lead that comes to you as a question card. A lead that stops without handing on, asking you or writing Done: gets up to 2 more turns, then you get one Keep going? card. See handoffs.
  • Nothing extra to install. kwant is one app for Mac or Linux (and a Windows beta), or one program, kwnt, with the web app built in. You don't install Node.js or Python yourself: the apps set up what they need on first start, and kwant installs Codex for you without Node. Docker is optional, only for VM mode and the bots' shared browser. Building kwant from source needs Rust and Node.js; the downloads don't. See Install & run.

None of this makes OpenClaw a bad product, and it reaches you in far more chat apps than kwant does. The three points above are where kwant fits better.

OpenClaw vs kwant

We only list what we can show from kwant's own docs and from OpenClaw's own README and docs, as read on November 16, 2026. Where we haven't checked an OpenClaw detail, we point you to OpenClaw's docs rather than guess.

TopicOpenClawkwant
Where it runsOn your own computer. One Gateway runs it on a laptop or as a shared "multiplayer claw" (README)Your laptop, a VPS or Docker, on hardware you control
Where you talk to itDiscord, iMessage, Slack, Teams, Telegram, WhatsApp and 20+ more, plus native apps for macOS, iOS, Android, Windows and Linux (README)kwant's web app, the Mac app, the Linux and Windows apps (both in beta), a phone app you add from the browser, and one paired Telegram chat per space
What it runs onNode.js. The installer provides a supported runtime when needed, or you install the npm package on Node 24 or 26 (README)One program with the web app built in. No Node.js or Python for you to install
ModelsModels and agent harnesses, such as Claude, Codex and local models, are plugins you can swap (README)Claude, Codex or Grok CLI logins, API keys, local Ollama or any OpenAI-compatible server, with failover across accounts
When work counts as doneSee OpenClaw's docsVerified only when its checks pass, run by kwant or by someone other than the bot that did the work. A bot that can't finish ends with Blocked: and what would unblock it
Scheduled workScheduled jobs, webhooks and Gmail triggers in the Gateway scheduler (Automations)Routines and cron rules on your own machine; they run while the machine is on
Tool safetyTools run on the host for the main session unless you configure sandboxing (security guide, sandboxing)Asks before bots run commands or edit files outside their folder, with three approval modes. Payments always ask
What goes to the developersA daily version check by default; anonymous feature statistics are opt-in (telemetry)No telemetry
LicenseMIT (LICENSE)AGPL-3.0, with commercial licenses available

Bring your OpenClaw workspace into kwant

Open Settings › Import. Since 0.8.0 it reads OpenClaw workspaces. In the Mac, Linux and Windows apps, Found on this computer lists ~/.openclaw by name and count only. It reads nothing until you pick it, and it never follows a link out of the folder. On a server, pick the folder or a GitHub link instead. Every import shows a preview first, and nothing is created until you press Import.

Each workspace becomes one bot: ~/.openclaw/workspace, each ~/.openclaw/workspace-<agent> and each ~/.openclaw-<profile>/workspace. kwant brings across:

  • the name, emoji and character from IDENTITY.md (or the folder's name)
  • SOUL.md as the bot's soul, and AGENTS.md as its instructions
  • MEMORY.md as its memories, and USER.md as what it knows about you
  • its skills, from skills/<name>/SKILL.md

Daily logs in memory/ and the first-run scripts BOOT.md and BOOTSTRAP.md are left out, and the preview names them under Not brought over. kwant never opens openclaw.json, credentials/, .env or auth.json, so no keys or sign-ins come across: you add your logins in kwant. Scheduled jobs aren't part of the import, so set them up again as routines. One Undo removes the whole import. See Import bots.

What you get in kwant after you move

  • Teams and handoffs. Group bots into teams with a lead and let them pass work with @mentions. Each hand-off gets a card, and the bot that handed it out reviews the result. See teams and handoffs.
  • A mission board. Every check and its evidence on the task's receipt, and checkpoints that let you undo a task's file changes. See the mission board.
  • Routines. Schedule bot work with routines, cron rules and follow-ups. See routines.
  • Approvals. Three approval modes per space or bot, and Flight School tiers (Observe, Sandbox, Act) that set how much freedom each bot has earned.
  • Your models, your accounts. Add multiple Claude, Codex and Grok accounts or API keys with failover. See models and routing.
  • Tools through MCP. Connect Model Context Protocol servers with per-bot access and approval before risky calls. See MCP tools.
  • Spaces. Keep work and home apart, each with its own bots, routines and approval rules. See spaces.

When OpenClaw is still the better fit

If you want one assistant that answers in WhatsApp, iMessage, Slack, Discord and many other chat apps, or native phone apps, OpenClaw covers far more of that than kwant, which has its web and desktop apps, a phone app you add from the browser, and Telegram. OpenClaw also has ClawHub, a public catalog of skills and plugins. And kwant runs on a machine you look after: if your bots live on a laptop that is switched off, routines wait until it is back on. A small VPS with the systemd setup in Install & run avoids that.

Get started

Install kwnt on a laptop, a VPS or with Docker, add a login, and import your workspace.

git clone https://github.com/alexsergivan/kwant && cd kwant && make run

FAQ

What is a good open-source alternative to OpenClaw?

It depends on what you need. kwant is an open-source (AGPL-3.0), self-hosted option built around a team of AI bots that hand work to each other with @mentions, where a task counts as Verified only when kwant runs the check itself. It runs on your laptop, a VPS or Docker.

Can I import my OpenClaw agents into kwant?

Yes. Since 0.8.0, Settings › Import reads OpenClaw workspaces, and the desktop apps list ~/.openclaw under Found on this computer. Each workspace becomes a bot with its name, soul, instructions, memories, what it knows about you, and skills. Daily logs and first-run scripts are left out and listed in the preview, and keys and sign-ins are never read.

What does "Verified" mean in kwant?

A task on the Mission board turns Verified only when its checks pass: a command such as the tests, a web address, a file, a review by a teammate who isn't the task's owner, or you pressing Verify. The bot that did the work can't verify it, and a check it adds to its own task waits for your OK.

Do I need Node.js to run kwant?

No. The Mac, Linux and Windows apps and the one-line Linux install use a prebuilt program with the web app built in, and kwant sets up the rest itself. Only building kwant from source needs Rust and Node.js.

Is kwant free?

The software is free under the AGPL-3.0, and commercial licenses are available. You pay for whatever model accounts or API keys you connect. kwant sends no telemetry to its developers.

What is kwnt?

It is the program you install and run for kwant. Start it with kwnt serve.