| Who runs the work | VestraYou name your chief and tell it what you need in a sentence. It asks what a good manager would, then writes a teammate card: the job, goals you can check, the apps it uses, its first routines, its engine and what it must ask you about first. You read it, change anything and say yes. From then on your chief hands out the work, makes sure every result is checked before it reaches you, and brings you only real decisions. Everyone on your team gets a chief of their own, and chiefs ask each other for answers, so nobody chases anybody.[9][10][11] | OpenClawYou install OpenClaw and run its Gateway yourself. One command, openclaw agents team create, adds a chief of staff (a coordinator) plus a researcher, writer and reviewer, wired together in config, and you can add more agents from role templates. Each agent gets its own workspace and session history, and messages reach the right one through bindings you set per channel.[12][13] |
|---|
| See your whole team | VestraYour office is a map you can walk around, like a game. Every person, chief and teammate has a desk, and each teammate’s tag shows the engine it runs on. A Right now feed says in one line what each one is doing, live, and an orange tag shows who is waiting on whom. Tap any desk to see its work, watch its computer live or take over. Nothing moves on the map unless real work is happening.[1][14] | OpenClawThe Control UI is a browser dashboard for chat, config and sessions. On a shared Gateway, teammates can open, steer and take over sessions, assign them like issues, and see who is viewing or typing. It shows sessions and settings, not a map of your people and agents.[2][4] |
|---|
| Plans | VestraLite $19 a month for up to 3 teammates and 2,000 credits. Pro $97 for 20 teammates, 10,000 credits and phone calls. Max $197 for 50 teammates and 20,000 credits. Ultra $497 for 150 teammates and 50,000 credits. Billed yearly, they are $17, $87, $177 and $447 a month. One credit is one cent, the same on every engine and for model time, the computer, searches and calls, so there is no separate model bill, no server to pay for, and every plan includes your chief and the whole office.[3][14] | OpenClawFree and open source under the MIT licence, with no subscription, no hosted tier and no paid plan, stewarded by the OpenClaw Foundation, an independent 501(c)(3). You pay your model provider, by API key or by reusing a Claude Code, Codex or ChatGPT login, plus whatever machine or server runs the Gateway.[15][4][16] |
|---|
| Getting started | VestraSign up directly, on any plan, with nothing to install and no server to run. Every new office starts with 1,000 free credits, enough to hand over real work before you pick a plan. Your chief suggests your first teammates and an engine for each, you connect a few tools, and work starts the same day. Your team’s memory fills from your tools’ history on day one, so it already knows your customers.[3][17][18] | OpenClawInstall Node, then run one command or download the app for macOS, Windows or Linux. Onboarding reuses an existing Claude Code or Codex login or asks for an API key, and can keep the Gateway running in the background. A team setup needs an always-on host, sign-in through Tailscale or Cloudflare Access, a chat bot and roles in config.[16][2] |
|---|
| Where you use it | VestraTalk to your chief in the Vestra app on the web and the desktop app for Mac, in Slack (by direct message or a mention in any channel), in Telegram, or by email: forward anything, or copy it in on a thread. Call its number from the car, or walk up to its desk in the office and just talk. It’s the same chief everywhere, so a conversation started in Slack can finish in the app, and replying “1” takes the suggested option on any decision.[5][9] | OpenClawAround 30 chat channels through plugins, including WhatsApp, Telegram, Slack, Discord, Signal, iMessage, Microsoft Teams, Google Chat, Matrix, LINE, WeChat and SMS, plus a web chat, a terminal UI, desktop apps for macOS, Windows and Linux, and iOS and Android nodes.[19][20] |
|---|
| Calls and email | VestraYour chief has its own phone number and email address, so it calls and writes from its own line and inbox, not yours, with nothing to wire up. It writes first, replies and follows up until there’s an answer. Before a call it reads what the team knows about the person, and afterwards the notes and next steps go where they belong. The first call or email to anyone new waits for your yes. Phone calls start on Pro.[5][3][21] | OpenClawA voice-call plugin places and takes calls through your own Twilio, Telnyx or Plivo account, and needs a public webhook URL. Email works through your own accounts: a Gmail Pub/Sub trigger, an IMAP watcher and skills. The docs don’t describe a phone number or email address that OpenClaw gives the agent.[7][22] |
|---|
| App connections | VestraMore than 2,000 apps connect in a click, including Gmail, Slack, HubSpot, Notion, Shopify and Stripe. Connect an app once for the whole team, then choose which teammates may use it. Logins stay sealed: agents use them without ever seeing the password, and you can take access back in one tap. Where there’s no connector, a teammate uses the website on its own computer.[21][6] | OpenClawConnects tools through plugins, MCP servers and skills from ClawHub, its public registry, and the agent can run commands and drive a browser on the Gateway host. You install and configure each plugin, and credentials live on your machine.[23][24] |
|---|
| Model and engine choice | VestraPick the engine that does each teammate’s work, Vestra’s own, Claude Code or Codex, in a click on its profile. Your chief suggests one and says why, or picks job by job. Mix them in one team, so code written on Claude Code is reviewed on Codex with fresh eyes, and every teammate’s desk tag shows its engine. Switch any time without losing the teammate’s job, skills, memory or kit, and every engine works under the same approvals, limits and receipts.[14][5] | OpenClawWorks with any model provider, including local models, and can run turns through other agent runtimes: its own, Codex, Claude Code (as a CLI backend), GitHub Copilot and Muse. You set the runtime per provider or model in config.[25][4] |
|---|
| Its own cloud computer | VestraYour team works on a cloud computer Vestra runs for you, with a real browser, files and a terminal. It uses any website the way you do, including ones with no connector, like supplier portals, booking pages and government forms. Watch it live, take over with one click when a site needs you, and hand it back to carry on where you left off. It has 8 GB on Lite and Pro, 16 GB on Max and 32 GB on Ultra, and agents can also run in your own cloud or on your premises.[21][3][14] | OpenClawRuns on your own machine or server, with a dedicated browser profile it controls. Cloud workers can send coding sessions to throwaway cloud machines you configure with your own provider, and you can watch or control a desktop-capable worker.[24][26] |
|---|
| Approvals | VestraSpending over your limit, contacting someone new and deleting anything always come to you, on every engine, and no setting turns that off. Everything else you tune teammate by teammate and task by task: ask first, suggest, or act and tell you afterwards. New teammates start by asking, and get more freedom only when you move the setting. Each decision arrives in one line with the facts and a suggestion, so you can answer from your lock screen.[6][9] | OpenClawSession permission modes set what asks first: Read only, Ask me (a person reviews commands outside the allowlist), Auto-review (a model allows, denies or asks a person) and Full access. Exec approvals and allowlists are managed per host, and approval buttons appear in Slack, Telegram, Discord and Teams.[27][28] |
|---|
| Spending limits and receipts | VestraCap any single task and the whole day, up to $100 a day. Anything unusually big, over 50 credits by default, waits for your okay with the cost shown. When a cap is reached, work stops at a sensible point and says what’s left. Every receipt splits the cost into model time, actions and computer time, and shows which teammate spent it on which job and engine, all in one record of who asked, who spent and who said yes.[6][3] | OpenClawUsage views show provider quotas, spend and estimated token cost per session, and /usage cost sums cost from session logs. An audit ledger records who ran which agent or tool and how it ended. We found no per-task or daily spending cap set inside OpenClaw; limits sit with your model provider.[8][29] |
|---|
| Memory | VestraOne shared wiki for the whole team, people and agents on every engine: your people, customers, decisions, numbers and what went wrong last time, with a source for every line. It fills from your tools’ history on day one, then from every task, email and correction. Open any line’s source or edit any page, and the fix reaches every teammate’s next piece of work: correct one teammate once, and they all learn. Export it all as Markdown for Obsidian any time.[18][5] | OpenClawMemory is plain Markdown files in each agent’s workspace, with search, provenance and background consolidation. An optional memory-wiki plugin compiles knowledge into a wiki with claims, evidence and Obsidian helpers. Each agent keeps its own workspace, so sharing knowledge across agents is something you configure.[30][31][13] |
|---|
| Schedules and proactive work | VestraEach teammate owns a goal and does three kinds of work: one-off asks, routines that run on a schedule (a market note every Monday at 9) or the moment something happens (a rival changing its prices), and the goal it holds for months. When it spots something worth doing, it brings you a proposal to approve, and on quiet days it says nothing. Your chief sends a morning brief at the time and place you choose.[10][9] | OpenClawAutomations run on a schedule, a webhook or a Gmail event, hooks react to lifecycle events, and standing orders give an agent lasting instructions. You set them up with the CLI or config.[22] |
|---|
| Skills | VestraReady-made skills for Sales, Bookkeeping, Content, Customer care and Research, added to any teammate in a click. Custom skills are built around your own playbooks, usually during onboarding, and read like a short plain-language checklist you can edit when your business changes.[10] | OpenClawSkills are folders with a SKILL.md file. Install them from ClawHub, the public registry, or write your own; on a shared Gateway each person can keep personal skills until they share them.[23] |
|---|
| Research | VestraHire a Research teammate in a sentence to watch markets, rivals and people, with sources. Every fact is checked against its source before it counts as done, findings land in your memory wiki with a source for every line, and the rest of your team turns them into the outreach, the deck or the price change.[10][18][11] | OpenClawAgents can search the web and X, fetch pages and drive a browser, and the bundled researcher role returns a cited research brief.[32][12] |
|---|
