Official OpenClaw version releases, changelogs, and upgrade notes.
Azure joins DigitalOcean, Docker, GCP, Hetzner, and others as a documented deployment target with official install instructions. Previously, Azure deployment required adapting guides from other platforms.
Source: OpenClawThe biggest release of the month adds full-agent voice calls, DeepSeek V4 Flash and Pro models, Azure Speech as a bundled TTS provider, and the Crestodian first-run TUI helper for smoother CLI onboarding.
Source: MultipleGPT-5.5 support arrives within days of OpenAI's release, alongside image generation and editing via Codex OAuth. The new forked-context subagent architecture lets agents spin off independent sub-tasks without polluting the main conversation.
Source: Blockchain NewsShared Bot Framework audience tokens must now name the configured app via verified appid or azp claim. Prevents lateral movement between bots in enterprise Teams deployments.
Source: GitHubExternal Android apps can no longer auto-dispatch prompts to OpenClaw via ASK_OPENCLAW intents. Actions now only prefill the draft, requiring user confirmation before sending.
Source: GitHubDefault image model switches to gpt-image-2, command permissions are tightened to owner-only, and Slack thread aliasing is fixed. Security hardening continues as a theme across April releases.
Source: GaoxiaomaA "house-repair release" focused on operator reliability — fixing session pruning, cost tracking duplication, and default session management. No new features, just making existing ones work correctly.
Source: GaoxiaomaTeams on Copilot Enterprise subscriptions can now use the same provider for memory and retrieval workloads in OpenClaw. Reduces provider sprawl for organizations already invested in GitHub's ecosystem.
Source: PetronellatechAnthropic's newest flagship model is now natively supported in OpenClaw, positioning the framework as production-grade infrastructure. Google Gemini TTS joins Azure Speech as a voice output option.
Source: ClawbotForward-compatible GPT-5.4-pro support arrives alongside a fix for the longstanding Ollama timeout issue where slow local model runs hit the global stream timeout. Complex reasoning tasks on local models no longer disconnect mid-response.
Source: PetronellatechPlugins can no longer access undeclared filesystem paths or network endpoints thanks to cryptographically signed manifests enforced at the kernel level via eBPF. This is the architectural answer to the malicious skills vulnerability from early April.
Source: ClawbotGPT-5 family support lands in OpenClaw alongside a bundled Codex provider with native authentication. Setup for OpenAI-powered agents is now simpler with fewer manual config steps.
Source: PetronellatechOpenClaw v2026.4.10 enables Apple Silicon users to run voice I/O entirely on-device without cloud APIs using the MLX framework. This is the first step toward fully offline agent voice interaction on macOS.
Source: Petronellatech