Skills & Tools

Claude Code v2.1.129 introduces plugin URL fetching, improved output synchronization, and auto-update capabilities for package managers. The release includes refinements to model discovery, history search behavior, and skill overrides, along with numerous bug fixes addressing UI regressions, cache handling, OAuth issues, and policy enforcement. Key improvements enhance terminal compatibility, conversation management, and enterprise security features.

langchain-fireworks version 1.3.1 is a patch release that addresses three key issues: requiring explicit API key configuration in FireworksEmbeddings, fixing a release versioning issue, and correcting how ToolMessage text content blocks are processed by removing non-wire protocol keys. This update ensures proper authentication handling and improves compatibility with the Fireworks API.

This cookbook demonstrates building a vulnerability-discovery agent using the Claude Agent SDK that automatically threat-models C source code, hunts memory-safety bugs using built-in file tools (Read, Grep, Glob), and generates structured security reports. The agent operates in a multi-turn session with a bootstrap threat-modeling phase, an interview phase for owner input, and automated vulnerability finding and triage loops. The approach reduces false positives compared to traditional static analyzers by using Claude's reasoning to identify high-confidence memory-safety issues in a read-only sandbox environment.

OpenClaw v2026.5.4-beta.1 introduces a bundled file-transfer plugin for binary file operations, enhances Google Meet/Voice Call integration with Twilio's realtime Gemini voice bridge, and delivers significant performance improvements across the gateway startup, plugin loading, and UI rendering. The release includes numerous UX refinements for chat controls, streaming progress visualization, and agent command steering, plus expanded QA/testing capabilities for Discord and Slack integrations.

OpenClaw v2026.5.3 introduces a bundled file-transfer plugin with secure binary file operations, hardens plugin installation workflows, and optimizes Gateway startup performance through lazy-loading. The release improves channel reliability across Discord, WhatsApp, Telegram, and other platforms, adds new agent steering commands, and fixes critical issues in realtime transcription, plugin updates, and systemd secret management.

OpenClaw v2026.5.3-beta.3 introduces a bundled file-transfer plugin with secure binary file operations, hardens plugin installation workflows, and optimizes Gateway performance through lazy-loading. Major improvements include enhanced channel support (WhatsApp, Discord, Telegram), improved agent runtime reliability, and numerous fixes for edge cases in streaming, transcription, and configuration management. The release emphasizes security (default-deny policies, symlink traversal protection), performance (startup optimization, hot-path trimming), and operational robustness (doctor command enhancements, state recovery).

OpenClaw v2026.5.3-beta.2 introduces a bundled file-transfer plugin with secure binary file operations, hardens plugin installation and updates, and improves gateway performance through lazy-loading. The release enhances channel reliability across Discord, WhatsApp, Telegram, and other platforms, while fixing critical issues in agent runtime, memory status reporting, and macOS upgrades. Key improvements focus on security (path policies, symlink traversal), performance (startup optimization), and reliability (streamed replies, session recovery).

crewAI v1.14.5a1 introduces the `restore_from_state_id` kickoff parameter for state management and enhances the ExaSearchTool with highlights while renaming it from EXASearchTool. Bug fixes address missing crewai pin sites in the release flow and ensure proper skills loading events for traces. This alpha release includes documentation updates and contributions from five team members.

Google ADK Python v1.32.0 introduces significant enhancements to agent development capabilities, including native OpenTelemetry metrics, Anthropic thinking blocks support, improved authentication mechanisms (2LO/3LO via GcpAuthProvider), and express mode deployment. The release addresses critical security vulnerabilities (RCE via YAML, SSRF), fixes parallel tool execution issues, and improves analytics with BigQuery LLM cache metadata logging and credential isolation to prevent race conditions.

Claude Code v2.1.126 introduces gateway model listing, project purge functionality, improved OAuth authentication for WSL/SSH/containers, and numerous bug fixes. Key improvements include permission bypass options, better shell detection on Windows, security fixes for managed settings, and stability enhancements for streaming, image handling, and remote sessions. The release also refines telemetry events, fixes UI issues, and resolves edge cases in tool availability and clipboard handling.

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.

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.

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-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 v2026.4.24 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.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`.

OpenClaw v2026.4.23-beta.6 introduces significant enhancements to image generation across multiple providers (OpenAI, OpenRouter), adds optional forked context for subagents, implements per-call timeout support for generation tools, and includes configurable local embedding context sizes. The release also delivers numerous fixes for Codex harness routing, media handling, provider authentication, and UI persistence, improving reliability across chat platforms including Slack, Telegram, WhatsApp, and WebChat.

OpenClaw v2026.4.23 introduces significant enhancements to image generation across multiple providers (OpenAI, OpenRouter), adds optional forked context for subagents, implements per-call timeout support for generation tools, and includes configurable local embedding context sizes. The release also fixes numerous issues related to Codex harness routing, media handling, provider authentication, and streaming behavior across multiple platforms including WhatsApp, Slack, and Telegram.