OpenClaw (formerly Moltbot/ClawdBot) 2026.2.9

OpenClaw (formerly Moltbot/ClawdBot) 2026.2.9

OpenClaw (formerly Moltbot/Clawd Bot) is an open-source, self-hosted AI personal assistant that runs on your own devices or a cloud server.
(4.8)
Free
Download

Operating System

MacOS / Windows / Linux

Date Published

Tue Feb 10 2026

OpenClaw (formerly Moltbot/ClawdBot) 2026.2.9

OpenClaw, formerly known as Clawd Bot, stands out as one of the most exciting open-source personal AI assistants available in 2026. This powerful tool brings advanced AI capabilities directly into your daily messaging apps, letting you chat with a smart assistant that actually gets things done. Whether you want to manage emails, write code, or stay organized across platforms, OpenClaw delivers a seamless experience while keeping your data under your control.

What Is OpenClaw?

OpenClaw is an open-source, self-hosted AI personal assistant that runs on your own devices or a cloud server. Created by developer Peter Steinberger, it first gained massive attention under the name Clawd Bot before rebranding to OpenClaw on January 27, 2026. The name change came after Anthropic raised trademark concerns related to similarities with their Claude AI model. The shift to OpenClaw symbolizes growth and adaptation, much like a lobster molting its shell to grow bigger and stronger.

The project exploded in popularity thanks to its innovative approach. It integrates deeply with the messaging apps you already use every day, turning them into a gateway for interacting with advanced AI. With over 30,000 GitHub stars, a thriving Discord community of thousands, and contributions from hundreds of developers, OpenClaw has quickly become a favorite among tech enthusiasts and productivity seekers.

What's new in OpenClaw v2026.2.9?

OpenClaw v2026.2.9 Release Notes:
### Added

- iOS: alpha node app + setup-code onboarding. (#11756) Thanks @mbelinky.
- Channels: comprehensive BlueBubbles and channel cleanup. (#11093) Thanks @tyler6204.
- Plugins: device pairing + phone control plugins (Telegram `/pair`, iOS/Android node controls). (#11755) Thanks @mbelinky.
- Tools: add Grok (xAI) as a `web_search` provider. (#12419) Thanks @tmchow.
- Gateway: add agent management RPC methods for the web UI (`agents.create`, `agents.update`, `agents.delete`). (#11045) Thanks @advaitpaliwal.
- Web UI: show a Compaction divider in chat history. (#11341) Thanks @Takhoffman.
- Agents: include runtime shell in agent envelopes. (#1835) Thanks @Takhoffman.
- Paths: add `OPENCLAW_HOME` for overriding the home directory used by internal path resolution. (#12091) Thanks @sebslight.

### Fixes

- Telegram: harden quote parsing; preserve quote context; avoid QUOTE_TEXT_INVALID; avoid nested reply quote misclassification. (#12156) Thanks @rybnikov.
- Telegram: recover proactive sends when stale topic thread IDs are used by retrying without `message_thread_id`. (#11620)
- Telegram: render markdown spoilers with `` HTML tags. (#11543) Thanks @ezhikkk.
- Telegram: truncate command registration to 100 entries to avoid `BOT_COMMANDS_TOO_MUCH` failures on startup. (#12356) Thanks @arosstale.
- Telegram: match DM `allowFrom` against sender user id (fallback to chat id) and clarify pairing logs. (#12779) Thanks @liuxiaopai-ai.
- Onboarding: QuickStart now auto-installs shell completion (prompt only in Manual).
- Auth: strip embedded line breaks from pasted API keys and tokens before storing/resolving credentials.
- Web UI: make chat refresh smoothly scroll to the latest messages and suppress new-messages badge flash during manual refresh.
- Tools/web_search: include provider-specific settings in the web search cache key, and pass `inlineCitations` for Grok. (#12419) Thanks @tmchow.
- Tools/web_search: normalize direct Perplexity model IDs while keeping OpenRouter model IDs unchanged. (#12795) Thanks @cdorsey.
- Model failover: treat HTTP 400 errors as failover-eligible, enabling automatic model fallback. (#1879) Thanks @orenyomtov.
- Errors: prevent false positive context overflow detection when conversation mentions "context overflow" topic. (#2078) Thanks @sbking.
- Gateway: no more post-compaction amnesia; injected transcript writes now preserve Pi session `parentId` chain so agents can remember again. (#12283) Thanks @Takhoffman.
- Gateway: fix multi-agent sessions.usage discovery. (#11523) Thanks @Takhoffman.
- Agents: recover from context overflow caused by oversized tool results (pre-emptive capping + fallback truncation). (#11579) Thanks @tyler6204.
- Subagents/compaction: stabilize announce timing and preserve compaction metrics across retries. (#11664) Thanks @tyler6204.
- Cron: share isolated announce flow and harden scheduling/delivery reliability. (#11641) Thanks @tyler6204.
- Cron tool: recover flat params when LLM omits the `job` wrapper for add requests. (#12124) Thanks @tyler6204.
- Gateway/CLI: when `gateway.bind=lan`, use a LAN IP for probe URLs and Control UI links. (#11448) Thanks @AnonO6.
- Hooks: fix bundled hooks broken since 2026.2.2 (tsdown migration). (#9295) Thanks @patrickshao.
- Routing: refresh bindings per message by loading config at route resolution so binding changes apply without restart. (#11372) Thanks @juanpablodlc.
- Exec approvals: render forwarded commands in monospace for safer approval scanning. (#11937) Thanks @sebslight.
- Config: clamp `maxTokens` to `contextWindow` to prevent invalid model configs. (#5516) Thanks @lailoo.
- Thinking: allow xhigh for `github-copilot/gpt-5.2-codex` and `github-copilot/gpt-5.2`. (#11646) Thanks @LatencyTDH.
- Discord: support forum/media thread-create starter messages, wire `message thread create --message`, and harden routing. (#10062) Thanks @jarvis89757.
- Paths: structurally resolve `OPENCLAW_HOME`-derived home paths and fix Windows drive-letter handling in tool meta shortening. (#12125) Thanks @mcaxtr.
- Memory: set Voyage embeddings `input_type` for improved retrieval. (#10818) Thanks @mcinteerj.
- Memory/QMD: reuse default model cache across agents instead of re-downloading per agent. (#12114) Thanks @tyler6204.
- Media understanding: recognize `.caf` audio attachments for transcription. (#10982) Thanks @succ985.
- State dir: honor `OPENCLAW_STATE_DIR` for default device identity and canvas storage paths. (#4824) Thanks @kossoy.

Key Features of OpenClaw

OpenClaw goes far beyond simple chat responses. It acts as an active agent that can handle real tasks, remember context across sessions, and even reach out to you proactively.

Here are some of its standout features:

  • Multi-channel support: Connects to WhatsApp, Telegram, Discord, Slack, Signal, iMessage, Microsoft Teams, Matrix, Google Chat, and more. You get one unified conversation that persists no matter which app you use.

  • Proactive assistance: Unlike passive chatbots, OpenClaw can send you messages first with reminders, alerts, morning briefings, or updates when something important happens.

  • Persistent memory: It remembers everything from past interactions, so you never have to repeat context when picking up unfinished work.

  • Powerful integrations: Links to tools for email management (like Gmail triage, drafting replies, or unsubscribing), code editing in IDEs, calendar handling, and custom skills you can build or download.

  • Voice and text input: Send voice notes on supported apps for transcription and processing, with more audio features in development.

  • Self-hosted privacy: Run it locally on your Mac, Linux machine, or a cloud droplet. Your data stays with you instead of feeding into big cloud AI services.

  • Easy onboarding: The CLI wizard (openclaw onboard) guides you through setup, including daemon installation for always-on access.

Developers love using it for coding tasks, where it can fix tests, generate full-stack features, or compile research notes. Everyday users appreciate inbox zero automation, smart replies, and consolidated messaging from multiple platforms.

How to Get Started with OpenClaw

One-liner

curl -fsSL https://openclaw.ai/install.sh | bash

npm

npm i -g openclaw
openclaw onboard

pnpm

pnpm add -g openclaw
openclaw onboard

Download DMG file for macOS

Many run it on a home machine for privacy or on a cheap cloud server for 24/7 access. Once live, add OpenClaw as a contact in WhatsApp or invite the bot to your Discord server, then start chatting.

OpenClaw represents the next step in personal AI. It combines large language model smarts with real-world action, persistent context, and deep system access in a way few tools do. You get an assistant that lives in your existing apps, handles routine tasks autonomously, and evolves with community contributions.

If you value privacy, customization, and true productivity boosts, OpenClaw deserves a spot in your workflow. Head to the official site at https://openclaw.ai/, check the docs at https://docs.openclaw.ai/, or join the active Discord to see what others are building. The future of personal AI assistants looks a lot like OpenClaw, and it's already here for anyone ready to self-host it.

Loading...