According to @openclaw, 2026.5.22 cuts /models to ~5ms, streamlines gateway startup, locks npm deps, and hardens Windows installs for faster, safer ops.

According to @openclaw, Discord voice now follows users, plaintext secret checks land, model status clarifies behavior, and Windows install fixes ship.

According to xai, OpenClaw now uses Grok via X subscriptions to chat, generate images and videos, and search X posts.

According to @openclaw, the 2026.5.18 release adds Grok OAuth fixes, Android Realtime Talk Mode, Telegram media delivery fixes, and browser dialog handling.

According to TheRundownAI, OpenClaw used a home camera to verify Nat Friedman drank water, showing AI agents enforcing real-world actions.

According to @openclaw, fs-safe, Proxyline, ClawHub trust evidence, and smarter approvals harden agent security for auditable guardrails.

According to @openclaw, the 2026.5.12 release adds Codex login default, runtime fallbacks, stalled-stream recovery, and faster startup for lean installs.

According to PixVerse... Panel covered Qwen and Ant LingGuang LLM strategies and OpenClaw perspectives at MU Shanghai, highlighting business use cases.

According to openclaw, the 2026.5.6 update refines OAuth safety and stabilizes plugin and web fetches for smoother AI agent integrations.

According to @openclaw, Grok 4.3 support, sturdier plugins, slimmer agent paths, and messaging fixes boost uptime with TTS, realtime, search polish.

According to openclaw, the 2026.4.29 release adds safer exec, owner controls, NVIDIA provider catalogs, faster startup, and agent‑native group chat.

According to @openclaw, the 2026.4.27 release adds DeepInfra, better file attachments, operator proxy routing, stricter model selection, and reliability.

According to @openclaw, the latest release improves Ollama local models, migrates Claude and Hermes setups, and enables one‑command Matrix E2EE.

According to OpenClaw on X (formerly Twitter), the 2026.4.24 release enables voice calls to reach the full agent, adds DeepSeek V4 Flash and Pro models, upgrades browser automation with coordinate clicks and improved recovery, and ships fixes across Telegram, Slack, MCP, sessions, and TTS (source: OpenClaw). According to OpenClaw, full-agent voice routing reduces handoff friction and enables end-to-end conversational task execution, which can lower support costs and improve lead qualification for contact centers and SaaS workflows (source: OpenClaw). As reported by OpenClaw, integrating DeepSeek V4 Flash and Pro expands inference options for cost-performance tuning, allowing businesses to route lightweight tasks to Flash and complex reasoning to Pro to optimize latency and spend (source: OpenClaw). According to OpenClaw, coordinate-level click support and better recovery increase browser RPA reliability for tasks like checkout automation, KYC capture, and internal dashboard ops, improving success rates in unattended runs (source: OpenClaw). As reported by OpenClaw, client fixes for Telegram, Slack, MCP, sessions, and TTS strengthen multi-channel deployment, supporting faster pilots in enterprise messaging and voice IVR replacements (source: OpenClaw).

According to @deepseek_ai on X, the DeepSeek-V4-Pro API is discounted by 75% until May 5, 2026, 15:59 UTC, and developers can unlock a 1M token context by setting the model to deepseek-v4-pro[1m] in Claude Code, while OpenCode should be updated to v1.14.24+ and OpenClaw to v2026.4.24+ for compatibility. As reported by DeepSeek’s official post, the promotion lowers inference costs for long-context applications like code assistants, RAG pipelines, and multi-document analysis, creating near-term savings for teams scaling token-intensive workloads. According to the same source, the integration guidance indicates active ecosystem support, reducing upgrade friction and accelerating enterprise adoption of long-context AI in developer tooling.

According to DeepSeek on X (Twitter), DeepSeek V4 is now natively integrated with leading AI agents including Claude Code, OpenClaw, and OpenCode, and is already powering in-house agentic coding workflows at DeepSeek; the company also showcased a sample PDF generated by DeepSeek V4 Pro as evidence of its tool-use and document generation capabilities (source: DeepSeek). As reported by DeepSeek, these dedicated agent optimizations target seamless handoffs between code planning, tool invocation, and artifact generation, signaling practical gains for enterprise code automation, documentation pipelines, and agentic RAG workflows. According to DeepSeek, the integrations suggest lower orchestration overhead for businesses adopting multi-agent systems and faster time-to-value for developer productivity use cases such as code refactoring, unit-test synthesis, and spec-to-PDF generation.

According to OpenClaw on X, the 2026.4.22 release adds Tencent Hy3 to the supported model list, introduces Grok image and voice tools, debuts a local TUI with a new /models command, and enables auto-install plugins with diagnostics export for faster setup and troubleshooting (as reported by OpenClaw on X and the GitHub release notes). According to the GitHub release page, these upgrades expand multimodal capabilities, streamline on-device workflows, and reduce integration friction for teams deploying mixed-model stacks in production.

According to OpenClaw, the v2026.4.21 release adds support for OpenAI Image 2, introduces Docker end to end test coverage for channel dependencies, and includes an npm update repair for bundled plugins, with several low risk backports to improve stability (as reported on GitHub Releases and the OpenClaw Twitter post). According to GitHub Releases, OpenAI Image 2 integration enables higher quality image generation workflows inside OpenClaw, expanding content automation use cases for marketing assets and product mockups. According to the same source, Docker E2E coverage hardens CI reproducibility for dependency chains across channels, reducing breakage risk in multi environment deployments. As reported by GitHub, the npm repair targets bundled plugin update issues, cutting integration friction for third party extensions and improving time to upgrade. According to OpenClaw on Twitter, this is a small but practical release focused on maintainability and reliability, which can lower operational overhead for teams shipping AI assisted image pipelines.

According to The Rundown AI on X, entrepreneur Jesse Genet runs a homeschooling and household operation for four children under six using 11 OpenClaw agents deployed on dedicated Mac Minis, coordinated via Slack with Obsidian as the knowledge base and Claude Code to build and iterate agents; named agents include Claire (chief of staff), Sylvie (curriculum), Cole (code), Theo (content), and Finn (finances), with the system holding its own credit card and autonomously spinning up new agents (source: The Rundown AI post via a16z). As reported by The Rundown AI, Genet’s customized full Montessori curriculum cost about $8 in inference tokens, highlighting a low marginal cost for tailored education content and rapid agent orchestration even for non-developers who, per the post, had not used Terminal six months prior. According to the same source, the stack demonstrates practical business implications for AI agents in consumer household management and micro-operations—suggesting opportunities for agent-as-a-service offerings, verticalized family finance agents, curriculum marketplaces, and managed Mac Mini edge deployments integrated with enterprise-style tooling like Slack and credit-card-enabled automation.

According to @openclaw on Twitter, the 2026.4.14 update delivers smarter GPT-5.4 routing and recovery, Chrome/CDP improvements, subagents that no longer get stuck, fixes for Slack, Telegram, and Discord integrations, and various performance improvements (as reported by OpenClaw on X, April 14, 2026). From an AI operations perspective, smarter GPT-5.4 routing suggests dynamic model selection and failover that can reduce task latency and error cascades in multi-agent pipelines, while CDP enhancements likely increase browser automation stability for data extraction and RPA use cases (according to the OpenClaw release tweet). For businesses deploying agentic workflows in customer support, growth operations, and QA automation, these reliability upgrades can lower incident rates, cut retrials, and improve end-to-end success rates across chat channels and web automation surfaces (as reported by OpenClaw on X).