MCP Servers

langchain-perplexity v1.2.0 introduces PerplexityEmbeddings support and overhauls the integration with the official Perplexity SDK and Search API. The release includes content-block-centric streaming improvements, dependency updates (langsmith, pillow, pytest), security patches (CVE-2026-4539 via pygments), and standardized integration testing across partners. Multiple maintenance updates ensure compatibility with langchain-core 1.2.21+ and improve code quality through type checking and documentation enhancements.

OpenClaw v2026.4.27 introduces major enhancements across Codex Computer Use setup, new provider integrations (DeepInfra, Tencent Yuanbao, QQBot), and a shift toward manifest-first plugin metadata architecture. Key improvements include GPU passthrough for Docker sandboxes, authenticated node presence tracking for iOS/Android, outbound proxy routing, and comprehensive reliability fixes across Telegram, Slack, and gateway startup. The release emphasizes reducing boot overhead through manifest-driven plugin discovery and model catalogs.

crewAI v1.14.4a1 is a pre-release update focusing on bug fixes and documentation improvements. Key fixes address LLM chat failures, message state management in executors, trained-agent file handling, multimodal input support, and JSON serialization issues. The release includes new documentation for sandbox tools (E2B, Daytona), Vertex AI setup, and You.com MCP integration, plus security updates to litellm.

OpenAI Agents Python v0.14.8 is a maintenance release that fixes two critical issues: preserving MCP re-export import errors and properly delimiting sandbox prompt instruction sections. The release includes documentation improvements and welcomes a new contributor to the project.

Claude Code v2.1.122 introduces Bedrock service tier selection via environment variable, PR URL resume functionality across multiple Git platforms, improved MCP server management with duplicate detection, and numerous bug fixes. Key improvements include OpenTelemetry enhancements for better observability, fixes for session branching, model configuration, and terminal/voice mode stability. The release addresses issues with structured outputs, token counting, image resizing, and various UI/UX problems.

langchain-anthropic version 1.4.2 is released with critical fixes and new features. Key updates include restoration of `cache_control` functionality on non-direct subclasses, bumped minimum core versions for compatibility, and implementation of content-block-centric streaming (v2). The release also includes CI improvements and standardized integration test invocation across partners.

Claude Code v2.1.121 introduces significant usability and performance improvements, including a new `alwaysLoad` MCP option for tool availability, enhanced plugin management with pruning, and improved terminal UI with scrollable dialogs and better URL handling. The release addresses critical memory leaks affecting image processing and session history, fixes OAuth and authentication issues across multiple platforms, and adds support for Workload Identity Federation and custom redirect URIs. Multiple terminal rendering bugs are resolved, and performance optimizations reduce file descriptor usage and startup time.

OpenClaw v2026.4.26 introduces major enhancements to real-time communication, plugin architecture, and migration tooling. Key additions include a generic browser real-time transport contract, Cerebras provider integration, asymmetric embedding support for memory search, and bundled importers for Claude and Hermes configurations. The release also includes numerous stability fixes for gateway operations, plugin discovery, and device token handling.

OpenClaw v2026.4.25 delivers major upgrades across voice synthesis, plugin architecture, observability, and browser automation. TTS now supports multiple providers (Azure Speech, Xiaomi, ElevenLabs v3, etc.) with chat-scoped controls and per-agent overrides. Plugin startup paths move to a cold persisted registry for deterministic operations and reduced manifest scanning. OpenTelemetry coverage expands across model calls, token usage, and tool loops with bounded attributes. Browser automation gains safer tab URLs, iframe-aware snapshots, and improved CDP readiness. Control UI adds PWA/Web Push support and enhanced setup flows.

OpenClaw v2026.4.25-beta.2 delivers major upgrades across text-to-speech (TTS) with new providers and chat-scoped controls, plugin architecture optimization through cold persisted registry, comprehensive OpenTelemetry observability expansion, safer browser automation with CDP improvements, and hardened installation/update processes across all platforms. The release includes PWA/Web Push support in the control UI, per-agent and per-account TTS overrides, and deterministic plugin discovery that eliminates broad manifest scans.

OpenClaw v2026.4.25-beta.3 introduces major upgrades to text-to-speech (TTS) with new providers and chat-scoped controls, migrates plugin management to a cold persisted registry for faster startup, expands OpenTelemetry observability across model calls and tool loops, enhances browser automation safety with iframe-aware snapshots, and hardens installation/update processes across multiple platforms. The release also adds PWA/Web Push support to the control UI and includes new CLI tools for setup and diagnostics.

OpenClaw v2026.4.25-beta.4 introduces major upgrades to text-to-speech (TTS) with new providers and chat-scoped controls, migrates plugin startup paths to a cold persisted registry for faster performance, expands OpenTelemetry observability across model calls and tool loops, hardens browser automation with safer URLs and iframe awareness, and strengthens installation/update processes across multiple platforms. The release also adds PWA/Web Push support to the control UI and includes new CLI tools for plugin management and diagnostics.

OpenClaw v2026.4.25-beta.1 introduces major upgrades to text-to-speech (TTS) with multi-provider support and per-agent overrides, migrates plugin management to a cold persisted registry for faster startup, expands OpenTelemetry observability across model calls and tool execution, enhances browser automation safety with iframe-aware snapshots and CDP tuning, and hardens installation/update processes across multiple platforms. The release also adds PWA/Web Push support to the control UI and includes new provider integrations (Azure Speech, Xiaomi, Volcengine, ElevenLabs v3) alongside improved CLI tooling and diagnostics.

OpenClaw v2026.4.24 introduces Google Meet as a bundled participant plugin with real-time voice capabilities, adds DeepSeek V4 models to the default catalog, and enhances browser automation with coordinate clicks and improved action budgets. The release significantly lightens plugin and model infrastructure at startup through static catalogs and lazy dependencies, while implementing breaking changes to plugin SDK tool-result transforms that require migration to the new `registerAgentToolResultMiddleware` API.

OpenClaw v2026.4.24-beta.3 introduces Google Meet as a bundled participant plugin with real-time voice capabilities, adds DeepSeek V4 models to the default catalog, and enhances browser automation with coordinate clicks and improved tab recovery. The release includes significant infrastructure improvements for lighter startup times through static model catalogs and lazy provider dependencies, plus numerous bug fixes across Telegram, browser automation, MCP, sessions, and gateway restart handling.

OpenClaw v2026.4.24-beta.4 introduces Google Meet as a bundled participant plugin with real-time voice capabilities, adds DeepSeek V4 models to the default catalog, and significantly improves browser automation, plugin infrastructure, and session management. The release includes 20+ bug fixes addressing packaged installs, heartbeat scheduling, Telegram polling, browser navigation, and MCP runtime management. Key improvements focus on startup performance through lazy loading and manifest-backed catalogs, plus enhanced stability for multi-platform deployments.

OpenClaw v2026.4.24-beta.5 introduces Google Meet as a bundled participant plugin with real-time voice capabilities, adds DeepSeek V4 models to the default catalog, and enhances browser automation with coordinate clicks and improved tab recovery. The release includes significant infrastructure improvements for lighter startup times through static model catalogs and lazy provider dependencies, plus numerous bug fixes across Telegram, browser automation, MCP runtime management, and session handling.

OpenClaw v2026.4.24-beta.1 introduces Google Meet as a bundled participant plugin with real-time voice capabilities, adds DeepSeek V4 models to the default catalog, and implements WebRTC-backed realtime voice loops across Talk, Voice Call, and Google Meet. The release includes browser automation improvements (coordinate clicks, longer action budgets, per-profile headless overrides), lighter plugin/model infrastructure at startup, and breaking changes to plugin SDK tool-result transforms requiring migration to `registerAgentToolResultMiddleware`.

crewAI v1.14.3 introduces lifecycle events for checkpoint operations, adds support for e2b and Bedrock V4, and enhances sandbox capabilities with Daytona tools. The release includes significant bug fixes for checkpoint serialization, execution tracking, and streaming tool calls, plus a ~29% cold start optimization. Security patches for lxml and python-dotenv dependencies are also included.

LangChain Core v1.3.2 introduces content-block-centric streaming (v2), a new streaming architecture that improves how content blocks are handled during streaming operations. This release builds on v1.3.1 with enhanced streaming capabilities for better performance and developer experience. The update focuses on refining the core streaming mechanisms used throughout the LangChain framework.