Tool Use

crewAI v1.14.4 introduces enhanced persistence customization, expanded cloud provider support (Azure OpenAI, Vertex AI), and new research tools (Tavily, You.com MCP). The release includes 12 bug fixes addressing JSON handling, message preservation, credential forwarding, and multimodal input support. Documentation updates cover E2B and Daytona sandbox tools.

OpenClaw v2026.4.29-beta.2 introduces significant enhancements across messaging, memory, provider coverage, and reliability. Key additions include active-run steering for messaging, a people-aware wiki with provenance tracking, NVIDIA provider onboarding, and improved channel resilience across Slack, Telegram, Discord, and others. Security improvements include OpenGrep scanning and stricter tool-scope handling, while operational reliability focuses on slow-host startup diagnostics and session recovery.

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.

LangChain v1.2.16 release includes performance optimizations for agent state handling and streaming, new content-block-centric streaming in core, dependency updates, and documentation corrections. Key improvements focus on reducing overhead in tool dispatch, adding LRU caching for type resolution, and enhancing streaming metadata efficiency. The release also bumps related packages including Anthropic 1.4.2, OpenAI 1.2.1, and LangChain Core 1.3.0.

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.

langchain-tests version 1.1.7 is released with several improvements including a hotfix for minimum core version requirements, new content-block-centric streaming capabilities (v2), and dependency updates. Key updates include bumping langsmith from 0.6.3 to 0.7.31 and pytest to 9.0.3. This release focuses on stability, testing infrastructure improvements, and enhanced streaming functionality.

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 v2.1.123 is a patch release that fixes a critical OAuth authentication bug. When the experimental betas feature flag was disabled via the `CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1` environment variable, OAuth authentication would enter a 401 retry loop, preventing successful login. This fix resolves the authentication failure and allows users with experimental features disabled to authenticate properly.

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.

OpenAI Agents Python v0.14.7 release includes convenience properties for tool items (tool_name, call_id), improved memory consolidation with higher turn limits, GPT-5.5 model aliases, and critical security fixes for file validation and symlink handling. The release also removes unset fields from Responses API calls and tightens tar/zip member validation to enhance security and stability.

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.

This guide demonstrates how to build Claude Managed Agents with persistent memory capabilities that learn and retain user preferences across multiple sessions. Users create a memory store, configure a shopping agent with file access tools, and show how the agent automatically reads and updates customer preferences on repeat visits. The memory system uses a simple file-based approach mounted at /mnt/memory/ that both the agent and application can access via API.

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.