Skills & Tools

OpenClaw v2026.5.12-beta.2 releases critical fixes and enhancements across authentication, provider streams, memory management, and UI/UX. Key improvements include auth-profile-backed media tools availability, subagent session visualization, error handling in auto-reply, and provider stream reliability. The release also upgrades to pnpm 11, adds per-agent tool policies, expands Slack/Gemini/Fal provider support, and strengthens TypeScript/linting standards.

OpenClaw v2026.5.12-beta.1 is a maintenance and feature release addressing security, UI/UX, and provider integrations. Key improvements include memory-wiki admin scope requirements, subagent session hierarchy visualization, Gemini 3 model normalization, enhanced tool policies, and expanded Slack/iMessage channel support. The release also upgrades build infrastructure to pnpm 11 and refines plugin SDK public APIs.

Claude Code v2.1.139 introduces significant new features including an agent view for managing multiple sessions, a `/goal` command for multi-turn task completion, and enhanced MCP server support with environment variables. The release includes numerous UX improvements like transcript navigation shortcuts, plugin token cost estimation, and fixes for critical issues such as credential deadlocks, memory leaks in MCP servers, and terminal interaction bugs.

OpenClaw v2026.5.10-beta.4 introduces significant enhancements across CI/CD, runtime detection, provider integrations, and agent capabilities. Key improvements include Fly Machines container environment detection, expanded Fal provider image editing support, stricter build tooling (oxlint, Vitest, TypeScript), and enhanced Slack integration with link/media unfurling controls. The release also upgrades to pnpm 11, adds per-agent message tool overrides, improves Discord voice diagnostics, and deprecates legacy Plugin SDK subpaths while exposing active model metadata.

OpenClaw v2026.5.10-beta.5 introduces significant improvements across CI/CD, runtime detection, provider integrations, and agent capabilities. Key updates include Fly Machines container detection, enhanced Fal provider image editing, stricter build tooling (oxlint, Vitest, TypeScript), pnpm 11 upgrade, and expanded agent-to-agent communication limits. The release also adds Slack thread management improvements, Discord voice diagnostics, plugin SDK deprecations, and QA automation enhancements for Telegram and Mantis.

OpenClaw v2026.5.10-beta.2 introduces significant enhancements across QA automation, voice capabilities, and provider compatibility. Key additions include Telegram live PR evidence automation with Crabbox integration, realtime voice diagnostics for Discord, and improved CLI onboarding. The release includes 30+ dependency updates and numerous bug fixes addressing session management, model compatibility, and gateway stability.

OpenClaw v2026.5.10-beta.1 introduces significant enhancements to QA automation, real-time voice diagnostics, and gateway security. Key additions include Telegram live PR evidence automation with Crabbox integration, Discord voice diagnostics, and private skill archive uploads. The release also includes numerous bug fixes across CLI, agent routing, model compatibility, and chat delivery systems, plus dependency updates for improved performance and security.

Google ADK Python v1.33.0 introduces BufferableSessionService, configurable environment tool truncation limits, and enhanced LlmResponse with function call/response accessors. The release includes 11 bug fixes addressing session state management, video event filtering, authentication error handling, and async event loop blocking. Code refactoring improves workflow metrics computation and removes deprecated input/output type attributes from ADK metrics.

Claude Code v2.1.133 introduces enhanced worktree configuration with `worktree.baseRef` settings, improved sandbox path management for Linux/WSL, and critical fixes for parallel sessions, proxy handling, and effort level synchronization. The release addresses memory efficiency, credential management, and cross-session consistency issues while improving focus mode behavior and MCP OAuth flow support.

This guide teaches how to build a grade-and-revise loop using Outcomes in Claude Managed Agents, where a writer agent drafts a cited research brief and a stateless grader independently verifies every URL, quote, and claim against a detailed rubric. The grader provides structured feedback that drives revisions until the brief passes, eliminating manual review cycles. Key techniques include writing specific, actionable rubrics that force concrete evidence, using span.outcome_evaluation_* events to track the loop, and understanding when Outcomes is the right tool for quality assurance.

This cookbook demonstrates building a multiagent coordinator system using Claude Managed Agents to automate sales-proposal generation. A coordinator agent orchestrates three specialist subagents—a web-search researcher, a case-study librarian, and a rules-based pricing modeler—each with scoped toolsets and specific responsibilities. The pattern shows how to structure heterogeneous teams, use per-role tool scoping, and leverage thread_created/thread_message_received events for agent coordination to assemble tailored sales proposals.

OpenAI Agents Python SDK v0.16.0 introduces significant updates including a default model change from gpt-4.1 to gpt-5.4-mini, new configuration options for disabling max_turns limits, SDK-side tool execution concurrency control, and server-prefixed MCP tool naming to prevent conflicts. The release also includes stability fixes for tool call output indexes and security improvements for symlink handling. These changes enhance performance and provide greater flexibility for agent configuration while maintaining backward compatibility through explicit model specification.

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.