Open-source personal agent that runs continuously, connects to messaging channels and uses installable skills to perform work across local and online tools.
Short answers to the questions buyers and builders commonly ask about OpenClaw. Each answer cites the shared ledger below, where every source is listed once.
05What should teams verify before adopting OpenClaw?
Broad tool permissions require careful review and isolation. · Community skills should be audited before installation. · Model-provider subscription and API terms can affect availability.
This profile connects the jobs OpenClaw is described as handling with its delivery model, access options and the subjects used to match it to related products in this directory.
Each fact points to a recorded source, making it easy to distinguish verified product information from claims that need checking.
Source availability
Public repository
Self-hosting
Supported
Messaging
Core interface
Skills
Installable
Practical capabilities
What it helps with
5 documented areas
A concise view of the jobs, capabilities and integrations described in the recorded product sources.
Use case
Personal automation
Use case
Messaging assistant
Use case
Background tasks
Focus area
Messaging integrations
Focus area
Skills and tools
Availability
Where it runs and where to get it
Source checked
Documented product formats, platforms and official distribution destinations. Availability can vary by region and plan.
Cost / license
FreeFree software + model costsOpen source; confirm repository license for the installed release
Platforms
Self-hostedDockerMessaging apps
Implementation details
Adoption notes
DeploymentSelf-hosted; local or server installation
LicenseOpen source; confirm repository license for the installed release
Model supportBring-your-own supported model providers
Data controlSelf-hosted control with data still subject to selected model and integration providers
Learning curveAdvanced
Primary use casesPersonal automation, Messaging assistant, Background tasks
What to verify before adopting
Broad tool permissions require careful review and isolation.
Community skills should be audited before installation.
Model-provider subscription and API terms can affect availability.
Evolution and major updates
OpenClaw timeline
A concise history of software releases and material product changes. Events appear only when a dated source supports what changed.
23 dated updates
Latest first · exact dates
Showing the newest updates and meaningful milestones. Open an entry for its summary and source.
Release note
openclaw 2026.7.1 released
Open details
OpenClaw v2026.7.1 brings major Control UI and onboarding overhauls, major updates to the official iOS, Android, and macOS apps, expanded model and provider support including GPT-5.6 compatibility, Tencent Hy3, and Meta Muse Spark 1.1, and stronger Codex and c
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 defaults. Full release notes
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 trusted tool policies are more reliable, with smaller improvemen
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 mentions and spooled handlers on the right delivery path. (9
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 replies, while WhatsApp now honors configured ACP bindings. (92679,
Stronger security and content boundaries: group prompt text is kept out of the system prompt, repeated-dot hostnames are normalized, side-effecting command wrappers and unsafe Node runtime env overrides are blocked, no-auth Tailscale exposure is rejected, and
Core npm hotfix release for v2026.5.3. Plugins/security: stop the install scanner from blocking official bundled plugin packages when process.env access and normal API sends only appear in distant parts of the same compiled bundle.
View 15 more dated releasesFull source-backed history
Release note
openclaw 2026.6.5 released
Open details
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, @dygg2001, @Takhoffman, and @vincentkoc. MCP results no longer p
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 cleanup, stale restart continuations are avoided, and Codex app-ser
Faster Gateway and replies: startup avoids repeated plugin, channel, session, usage-cost, warning, scheduled-service, and filesystem scans; visible replies separate user-facing sends from slower follow-up work; Gateway runtime/session caches churn less under l
Exec approvals: remove the old cat SKILL.md && printf ... && allowlist compatibility path so skill files must be loaded with the read tool and only the real skill executable is auto-allowed. Discord: let voice sessions follow configured Discord users into voic
Agents: clarify that fixes should default to clean bounded refactors, lean internals, and explicit plugin SDK/API deprecation paths. Dependencies: update @openclaw/proxyline to 0.3.3.
OpenClaw 2026.5.18 is the stable rollup after 2026.5.12. It includes the 2026.5.14 and 2026.5.17 beta trains plus the final 2026.5.18 fixes below. Consolidated Since 2026.5.12
Leaner installs: WhatsApp, Slack, Amazon Bedrock, Anthropic Vertex, and related provider/plugin dependency cones moved out of the core runtime so installs only pull what you use. Telegram got much more resilient: isolated polling, durable local spooling, safer
Release/plugin publishing: retry transient ClawHub CLI dependency install failures, keep preview-passing plugins publishable when one preview cell flakes, and verify every expected ClawHub package version after publish so maintenance releases are faster to rec
Doctor/OpenAI Codex: revert the 2026.5.5 doctor --fix repair that rewrote valid openai-codex/ ChatGPT/Codex OAuth routes to openai/, which could break OAuth-only GPT-5.5 setups or accidentally move users onto the OpenAI API-key route. If 2026.5.5 already chang
Feishu: hydrate missing native topic starter thread IDs before session routing so first turns and follow-ups stay in the same topic session. Fixes 78262. Thanks @joeyzenghuan. LINE: reject dmPolicy: "open" configs without wildcard allowFrom so webhook DMs fail
Google Meet/Voice Call: make Twilio dial-in joins speak through the realtime Gemini voice bridge with paced audio streaming, backpressure-aware buffering, barge-in queue clearing, and no TwiML fallback during realtime speech, giving Meet participants a much sn
Plugins/file-transfer: add bundled file-transfer plugin with filefetch, dirlist, dirfetch, and filewrite agent tools for binary file ops on paired nodes; default-deny per-node path policy under plugins.entries.file-transfer.config.nodes with operator approval,
External plugin installation, update, doctor repair, dependency reporting, and artifact metadata now cover the npm-first cutover, stale configured installs, missing package payloads, and beta-channel plugin fallback. Thanks @vincentkoc. Gateway and agent hot p
Facts, answers, structured details, milestones and primary resource links cite this shared ledger. Each external page appears once; release tags from the same GitHub project are grouped under one release history.