Organizes your inbox, sends emails, manages your calendar, checks you in for flights - all from WhatsApp, Telegram, or any chat app you already use. Your agent, your machine, your rules.
OpenClaw is a free, open-source personal AI assistant that runs on your computer or server and actually does things - reads your email, manages your calendar, browses the web, writes code, runs commands - all from the messaging apps you already use. It started as a weekend hack in Austria and became the fastest-growing repository in GitHub history, now stewarded by the non-profit OpenClaw Foundation.
One Gateway process runs on your machine and bridges everything: your chat apps on one side, an AI agent with tools, memory, and skills on the other. Message it from anywhere; it thinks with the model you chose and acts with the permissions you granted.
No dashboards to learn. After onboarding, you message your agent like a person. Real use cases from the community:
Getting started, channels, config, and every capability.
GitHubMIT-licensed. Star it, fork it, hack it, contribute.
ExamplesReal workflows the community built and shared.
DemoThe Discord is the showroom - watch agents at work.
Latest updateControl UI overhaul, new models, stronger workflows.
Product notes with docs-level depth. The lobster ships fast.
The lobster grows up: OpenClaw is now a non-profit with a full-time team, paid maintainers, and world-class partners - including OpenAI, NVIDIA, Microsoft, and GitHub - on a mission to bring personal AI to everyone. Peter Steinberger keeps the technical helm; the project stays MIT, open, and independent. Watch cofounders Peter Steinberger and Dave Morin fireside at GitHub HQ above.
A revamped Control UI, conversational onboarding, GPT-5.6 / Claude Sonnet 5 / Tencent Hy3 / Muse Spark 1.1 support, ClawRouter, and stronger Codex workflows.
release Jun 30, 2026 Β· MobileNative apps with chat, Talk mode, and remote action approvals - paired to your own Gateway, so your data stays yours.
apps Jun 1, 2026 Β· SecurityEvery ClawHub skill now ships with a Skill Card and is scanned by SkillSpector for hidden instructions and agentic risks.
securityWindows, macOS, Linux, Docker, or a VPS - every OpenClaw installation path, from a one-line install to a fully self-hosted server setup.
Native app with controls for the gateway, chat, setup, and node features. First run may prompt for an administrator password for Homebrew.
The Windows Hub runs OpenClaw with tray, setup, chat, and node mode - natively contained via Microsoft Execution Containers, straight from the Build 2026 keynote.
Install OpenClaw on Linux with the one-liner below - it handles Node.js and every dependency for you. Ideal for servers, homelabs, and a Raspberry Pi 5.
The fastest way to install OpenClaw on macOS and Linux. Installs Node.js and everything else, then run openclaw onboard.
Already have Node.js 22+? Install OpenClaw globally via npm and onboard from any terminal on any OS.
Run the Gateway in a container for clean isolation on servers, NAS boxes (TrueNAS, Portainer), and homelabs. Follow the Docker guide in the docs.
The hackable install: clone, pnpm install, and run from source. Best for contributors and plugin developers.
Want a 24/7 assistant that answers even when your laptop sleeps? Run OpenClaw on a small VPS or any always-on machine you own. It's the same install - just on a server.
min spec: 2 vCPU Β· 4 GB RAM Β· Node.js 22+ Β· ~$4β10/mocurl -fsSL https://openclaw.ai/install.sh | bash sets up Node.js and OpenClaw in one go.openclaw onboard walks you through model providers and credentials conversationally.openclaw update. Pair the iOS/Android app for approvals on the move.Mac, Windows, or Linux. Bring hosted, subscription-backed, gateway, or fully local models. State lives with you, not a vendor cloud.
WhatsApp, Telegram, Discord, Slack, Signal, iMessage, and more - in DMs and group chats alike.
Remembers your preferences, projects, and people from one conversation to the next. Context that persists 24/7.
Browses the web, fills forms, and extracts data from any site - checked in for your flight before you land at the gate.
Read and write files, run shell commands, execute scripts. Full access or sandboxed - always your choice.
Extend with community skills from ClawHub or build your own. It can even write its own - and hot-reload them.
Tools are callable actions, skills teach repeatable workflows, and plugins add runtime capabilities like providers and channels. Together they turn a chat agent into a workflow automation engine - and OpenClaw can even write its own.
Inbox triage, smart replies, bulk unsubscribing, and a morning brief of what actually matters. Users report clearing 10,000-email backlogs on autopilot.
triage Β· draft Β· unsubscribe Β· briefTimeblock tasks, resolve conflicts, get briefed before meetings, and get pinged when it's time to leave based on live traffic.
timeblock Β· conflicts Β· pre-meeting briefsDelegate to Claude Code or Codex from any chat: run autonomous fix-the-tests loops, steer sessions from your phone, and attach to running work with openclaw attach.
Create and triage issues from chat, watch webhooks (a Sentry error can become a fix and an open PR), and preview issue status inline in the Control UI.
issues Β· PRs Β· webhook-triggered fixesConnect CRMs like HubSpot via plugins or MCP: look up contacts, track deals, log activity, research prospects, and draft outreach - with you approving what goes out.
contacts Β· deals Β· research Β· outreach draftsCron jobs, heartbeats, reminders, and background tasks: expense reports, invoices, meeting-notes reviews, ad optimization, content pipelines - one user says "it's running my company."
cron Β· webhooks Β· background tasksThousands of community skills and plugins, one command away - or ask your agent to install one mid-conversation.
"install the todoist skill" β doneDescribe the workflow in chat and OpenClaw writes the skill itself, hot-reloads it, and starts using it - no editor required.
"build a skill for my uni assignments" β builtThe Skill Workshop turns completed agent work into reusable skills - you review, revise, and approve proposals before they change how your agents operate.
review β revise β applyThe result: a productivity assistant that compounds - every workflow you teach it once, it runs forever. Skills docs β
OpenClaw is free, open-source software - no license fee, no seats, no subscription. What you pay for is where it runs and which AI model powers it. Here's the honest breakdown.
| Model | Good for | per 1M tokens (in / out) |
|---|---|---|
| Claude Haiku Β· Anthropic | heartbeats, routing, quick tasks | $1 / $5 |
| Claude Sonnet Β· Anthropic | the best default for most work | $3 / $15 |
| Claude Opus Β· Anthropic | genuinely hard reasoning only | $5 / $25 |
| GPT-5 Nano / Mini Β· OpenAI | cheap high-volume chat | fractions of a cent per msg |
| GPT-OSS-120B Β· open-weight | best value tool-calling | $0.04 / $0.10 |
| Local models Β· Ollama etc. | zero-API setups | $0 |
# A typical OpenClaw task uses 2,000β8,000 tokens across 3β8 model calls. Rates shift - check your provider's current pricing. You can also sign in with a Claude or ChatGPT subscription instead of paying per token.
No. OpenClaw has no paid plans and no official cloud - it's a free, MIT-licensed OpenClaw Foundation project. Any "OpenClaw cloud pricing" you see comes from independent third-party hosts, not the project itself.
$0 on hardware you already own, or roughly $4β10/month for a small VPS (2 vCPU / 4 GB RAM is enough). Add your model spend on top, plus a couple of hours of setup and occasional maintenance.
Light use runs under $1β5/month; moderate personal use around $10β30; heavy automation $50β150+. Model choice matters more than server size - route routine tasks to cheap models and reserve premium ones for hard reasoning. Alternatively, connect an existing Claude or ChatGPT subscription.
Leaving the heartbeat (the periodic "anything to do?" wake-up) pinned to a premium model. Point it at a cheap model or lower its cadence, and an idle agent costs cents instead of dollars per day.
OpenClaw separates model choice, authentication, and execution runtime. Connect with an API key, sign in with a subscription you already pay for, route through a gateway, or run models fully local - and switch anytime with one config change.
Claude connected to your tools - bring an Anthropic API key or sign in with a Claude subscription. Sonnet is the community's default workhorse; Opus for hard reasoning.
Claude API key Β· Claude Max sign-inOpenAI API plus ChatGPT/Codex sign-in and native Codex execution. GPT-5.6 is the default for new setups as of v2026.7.1.
OpenAI API key Β· ChatGPT sign-inGoogle's models over native transport - Flash-class models are a community favorite for cheap heartbeats and high-volume routing.
Gemini API key Β· free tier availableDeepSeek, Qwen, GLM, Grok, MiniMax, Kimi, and other direct model APIs - plus any OpenAI-compatible endpoint or unified gateway like OpenRouter.
direct APIs Β· OpenAI-compatible endpointsRun models on your own hardware with Ollama or any compatible local endpoint. Zero API bill, full privacy - the fully-local lobster.
Ollama Β· local endpoints Β· $0/moThe bundled router plugin (new in v2026.7.1): credential-scoped model discovery, multi-provider transports, and managed budget reporting across all usage surfaces.
smart routing Β· quotas Β· budgets# Illustrative - see the model configuration docs for exact keys, aliases, and per-agent overrides. openclaw doctor preserves your model tuning across updates.
There's no single best model - the winning setup routes each job to the cheapest model that does it well. A sensible policy cuts the model bill 40β70%:
API keys stay on your machine in your own config - OpenClaw is the harness, not a middleman.
29 chat channels plus tools for email, calendar, code, and the open web. Every channel installs in one command or during onboarding - run several at once and OpenClaw routes each conversation automatically.
Your agent inside WhatsApp - DMs, group chats, and rich media. Setup is install-on-demand with QR pairing.
via WhatsApp Web Β· QR pairingThe fastest channel to set up - just a bot token, no plugin install. Chats, groups, topics, commands, and live progress.
via Bot API Β· fastest setupServers, channels, DMs, commands, and voice sessions. A favorite home base for multi-agent fleets.
via bot Β· servers & DMsYour agent where your team works - threads, cards, reactions, relay mode, and app events over WebSocket.
via Slack app Β· workspacesEnterprise conversations through Bot Framework: Teams DMs, group chats, and channels with allowlist-first security defaults.
via Bot Framework Β· official pluginPrivacy-focused messaging with your agent, powered by signal-cli - private chats on your own infrastructure.
via signal-cli Β· privacy-firstNative Messages integration on a signed-in Mac - replies, tapbacks, effects, attachments, and group management.
via imsg / BlueBubbles bridge Β· macOSSpaces and direct messages through a Google Chat app - bring your agent into your Workspace conversations.
via Chat API webhook Β· official pluginRead, draft, send, and manage email. Triage the inbox, unsubscribe from noise, and surface what actually matters in your morning brief.
read Β· draft Β· triage Β· unsubscribeCalendar automation from chat: check your day, resolve conflicts, schedule meetings, timeblock tasks, and get briefed before every call.
events Β· conflicts Β· briefings Β· remindersWork across issues and pull requests, kick off Claude Code or Codex sessions from your phone, and let the agent open PRs from webhook-triggered fixes.
issues Β· PRs Β· coding-agent workflowsA real browser under agent control: browse, click, fill forms, and extract data from any site - flight check-ins and web errands included.
browse Β· fill forms Β· extract data+ Matrix, Mattermost, IRC, LINE, Feishu, QQ, Nextcloud Talk, SMS, Voice Call, Twitch, and more - browse the full directory β
OpenClaw is powerful software - it can read files, run commands, send messages, and act on schedules. That's the point, and it's also why security is a shared responsibility: OpenClaw ships safe defaults, and you decide what it can touch. Treat it like privileged software, not a harmless chatbot.
Your context, memory, skills, and state live on your machine - not a vendor cloud. There's no hosted service in the loop, no telemetry harvesting your conversations, nothing to leak from someone else's server.
self-hosted Β· your hardware Β· your dataRun the agent with full access or sandboxed - your choice. On Windows, OpenClaw runs inside Microsoft Execution Containers; on servers, Docker gives clean isolation. Unsafe runtimes are stopped before they can touch state databases.
execution containers Β· docker Β· scoped runtimesChannels default to pairing and allowlists: unknown senders are ignored until you approve them, groups are blocked unless allowlisted, and sensitive node capabilities (like browser proxying) require admin-level approval.
allowlists Β· DM pairing Β· operator rolesCommunity skills are a supply chain, and OpenClaw treats them like one: every ClawHub skill ships a Skill Card documenting what it does and where it came from, and is scanned by SkillSpector for hidden instructions and agentic risks.
skill cards Β· SkillSpector Β· NVIDIA collabAPI keys and channel credentials live in your local config with masked prompts during onboarding - OpenClaw is the harness, not a middleman. Keep secrets out of version control and rotate anything you paste into a chat.
local config Β· masked prompts Β· your keysRemote action approvals on the iOS and Android apps, explicit approval binding during setup, and spend caps mean the agent asks before consequential actions - you stay the operator.
action approvals Β· spend caps Β· audit your logsThe hardening steps that matter most, whether you run it on a laptop or host it on a server. Ten minutes of discipline now saves a bad week later.
defaults are safe Β· these keep them that wayallowFrom: ["*"] to production, and require mentions in groups.openclaw update for security fixes.Security posture evolves fast in agentic AI - read the current guidance in the security docs β and the security blog posts β.
"Best alternative" depends on what you're actually replacing. Most tools people compare with OpenClaw solve a different problem - here's a fair map of the landscape, grouped by what each is for.
ChatGPT and Claude are polished hosted assistants you visit. OpenClaw is a self-hosted agent that lives in your chat apps 24/7 with persistent memory and system access. Not really rivals: many users plug their ChatGPT or Claude subscription in as OpenClaw's brain.
different layer - OpenClaw is the harness, they're the modelsClaude Cowork (Anthropic's agentic desktop app) and Manus are managed agent products - smoother onboarding, vendor-run, vendor-priced. OpenClaw trades that polish for open source, full self-hosting, any model, and 29 chat channels.
managed convenience vs open controlThese are developer frameworks for building agents - libraries, not products. OpenClaw is a ready-to-run assistant out of the box. If you want to ship your own agent system, use a framework; if you want an assistant today, run OpenClaw.
build-your-own vs ready-to-runTrigger-action platforms excel at deterministic pipelines: when X happens, do Y, every time. OpenClaw handles open-ended, conversational work that doesn't fit a flowchart. They pair well - plenty of setups have OpenClaw triggering n8n flows and vice versa.
deterministic pipelines vs open-ended agencyHosted AI-assistant platforms with per-seat or usage pricing, built for teams that want zero infrastructure. OpenClaw is free and self-hosted: you own the data and the bill, but also the setup and maintenance.
subscription SaaS vs free self-hostedThe nearest true alternatives: other personal agent harnesses. Hermes is an alternative stack (some users run both - their agents even chat), and NanoClaw is a security-focused fork-alike with stricter human-in-the-loop defaults.
same category - pick your philosophy| OpenClaw | Hosted assistants (ChatGPT, Claude, Manus, Lindy) | Frameworks (AutoGPT, CrewAI, LangChain) | Workflow tools (n8n, Zapier, Make) | |
|---|---|---|---|---|
| Open source | β MIT | mostly β | β mostly | varies |
| Self-hosted / local data | β always | β vendor cloud | β you build it | n8n β Β· others β |
| Lives in your chat apps | β 29 channels | own app / limited | if you build it | β triggers only |
| Model choice | β any, incl. local | vendor's models | β any | limited |
| Ready to use today | β product | β product | β library | β product |
| Software cost | $0 | subscription | $0 + dev time | free tier β paid |
# Simplified by necessity - each column groups distinct products. The honest takeaway: OpenClaw's edge is open, self-hosted, chat-native agency; managed products' edge is polish and zero maintenance. Choose for your constraints, not the hype.
The honest cost-benefit: the software is free, but you invest setup time, a small hosting bill, model costs, and the discipline to run privileged software safely. Here's who comes out ahead - and who doesn't.
For the right person, emphatically yes. If you're technical, privacy-minded, or simply curious, OpenClaw delivers something no hosted product does: a personal agent you fully own, for roughly $0β40/month and an evening of setup. Half a million systems and the loudest word-of-mouth in AI - "iPhone moment," "it's running my company" - didn't happen by accident. Start small: one channel, one low-risk workflow, spend caps on. If the magic lands, expand. If it doesn't, you've lost an evening and a few dollars - the software itself never costs a cent.
The fastest-growing project in GitHub history - a weekend hack that became the most-starred software repo in under five months, built by one creator, dozens of maintainers, and thousands of contributors.
- as told at the Y Combinator community celebrationUsers describe daily briefings, inbox triage, calendar juggling, expense reports, deploy fixes over voice notes, and multi-agent fleets running across several machines - all steered from a phone chat.
- community showcase threadsβIt's running my company.β
- @therno, one of thousands of daily shoutoutsThe one-liner installs Node.js and everything else for you. Switch channels later with a single command.