← Registry
Harness Official

OpenClaw

Your own personal AI assistant for any OS and platform — installs via npm and runs as an always-on gateway daemon.

Install

via Positronick CLI

$positronick harness install openclaw --run

Official

$npm install -g openclaw@latest

OpenClaw is an open-source personal AI assistant that runs on any operating system and platform, installed globally through npm. Its onboarding sets up a Gateway daemon (a launchd or systemd user service) so the assistant stays running and reachable in the background, and a Control UI plus a skills ecosystem round out the experience. Reach for OpenClaw when you want a persistent, locally-run AI assistant you fully control rather than a hosted service.

Releases · 9

2026.7.1 Latest

openclaw

New models and providers: add Featherless, Claude Sonnet 5 and Mythos 5, Meta Muse Spark 1.1, and ClawRouter; make GPT-5.6 the new-setup default with /think ultra for Sol and Terra plus max for Luna,…

GitHub ↗
2026.6.11 Release

openclaw

We heard the feedback. v2026.6.11 focuses on the rough edges that make OpenClaw feel less dependable, with fixes for misplaced replies, stuck sends, reconnects, model setup failures, and safer admin…

GitHub ↗
2026.6.10 Release

openclaw

Automatic fast mode starts short conversations quickly, then returns longer or fallback work to normal mode without losing visible state. Provider routing, channel progress, session identity, and…

GitHub ↗
2026.6.9 Release

openclaw

Richer Telegram delivery: Telegram now sends rich HTML, preserves rich markdown and sticker paths, renders progress drafts and command output more faithfully, normalizes HTML tables safely, and keeps…

GitHub ↗
2026.6.8 Release

openclaw

Richer channel delivery: Telegram and WhatsApp are less brittle: Telegram renders structured text with tables, lists, expandable blockquotes, preserved intentional line breaks, and CLI-backed…

GitHub ↗
2026.6.6 Release

openclaw

Tighter security boundaries: transcript, sandbox, MCP, browser, channel, and exec-approval paths now fail closed around unsafe access, timed-out approvals, and malformed boundary input. (#91529,…

GitHub ↗
2026.6.5 Release

openclaw

Safer channel output: QQBot strips model reasoning and thinking scaffolding before native delivery, so users see the final answer rather than raw internal markup. (#89913, #90132) Thanks @openperf,…

GitHub ↗
2026.6.1 Release

openclaw

Resilient agent and Codex runs: interrupted tool calls, stale session bindings, compaction handoffs, auth-profile failover, reasoning-tag cleanup, yielded subagents, and generated-media delivery all…

GitHub ↗
2026.5.28 Release

openclaw

Agent and Codex runtime recovery is steadier: subagents keep cwd/workspace separation, hook context stays prompt-local, session locks release on timeout abort while live OpenClaw locks survive…

GitHub ↗

Showing 9 of 9 releases