Multi-Agent Systems

OpenClaw v2026.5.12-beta.6 is a comprehensive bug-fix and security-hardening release addressing 50+ issues across messaging channels, agent sessions, gateway protocols, plugin management, and authentication. Key improvements include fixing iMessage media handling, agent-to-agent messaging reliability, OAuth token exchange for GitHub Copilot, plugin dependency management, and enforcing stricter security controls for device pairing and proxy access. The release prioritizes stability in multi-agent communication, transcript redaction consistency, and dependency isolation while maintaining backward compatibility.

OpenClaw v2026.5.12-beta.5 is a comprehensive bug-fix release addressing gateway protocol improvements, security hardening, plugin dependency management, channel integrations (WhatsApp, Telegram, Discord, WeCom), session transcript redaction, and agent execution reliability. Key fixes include OAuth token exchange for Copilot, device pairing approval requirements, media size enforcement across plugins, and LLM idle watchdog timeout escalation. The release improves stability across multiple integrations while strengthening security controls for trusted proxies, admin scopes, and sensitive data redaction.

OpenClaw v2026.5.12-beta.4 is a maintenance release addressing runtime issues, authentication flows, and provider integrations. Key fixes include resolving MODULE_NOT_FOUND errors in Codex migrations, improving WhatsApp/Telegram message handling, and normalizing Google Gemini model IDs. The release also enhances session management, adds per-agent tool policies, and improves error messaging across multiple channels and providers.

crewAI 1.14.5a5 is a pre-release update that deprecates CrewAgentExecutor in favor of AgentExecutor, improves Daytona sandbox tools, and addresses multiple security vulnerabilities in dependencies. The release includes bug fixes for HITL workflows, logging enhancements, and comprehensive documentation updates including migration guides for state restoration and crew-to-flow transitions.

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.

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.

crewAI releases version 1.14.5a4, a pre-release update that updates LLM listings and resolves a critical dependency issue by relocating the `textual` package to `crewai-cli` while adding `certifi` as a dependency. This patch addresses packaging conflicts and ensures proper CLI functionality. The release includes documentation updates to reflect the changelog and version information.

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.

LangChain v1.3.0a2 is an alpha release featuring improvements to stream events protocol (v3), ordered schema resolution, and agent middleware enhancements. The release includes performance optimizations, bug fixes across multiple integrations (OpenAI, Anthropic, Fireworks), and new features like HITL middleware respond decision and dynamic tool registration. Key updates involve dependency bumps, security patches, and refinements to the agent creation and model initialization systems.

crewAI v1.14.5a3 is a maintenance release focusing on bug fixes and architectural improvements. Key changes include correcting the status endpoint path structure, upgrading gitpython for security compliance, and extracting the CLI into a standalone package. This refactoring improves modularity while maintaining backward compatibility.

crewAI v1.14.5a2 is a bug fix release addressing critical issues in task output handling, token counting, async operations, and LLM configuration. Key improvements include fixing task output restoration in finally blocks, preserving outputs across async batch flushes, and preventing incorrect final answer returns from hooks and errors. The release also enhances the CrewAIRagAdapter with proper kwargs forwarding and improves BaseModel input handling.

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.

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.

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.

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.

Google ADK Python v2.0.0-beta.1 marks the transition to Beta phase with significant architectural improvements. Key additions include a full Workflow graph orchestration system with NodeRunner for execution isolation, explicit ReAct loop nodes for agent execution, and Human-in-the-loop resumption capabilities. The release also addresses a critical RCE vulnerability in YAML configuration handling and optimizes performance for single-turn LLM agents.

crewAI v1.14.3a2 introduces support for AWS Bedrock V4 and Daytona sandbox tools while expanding documentation with an AI-native 'Build with AI' page across multiple languages. The release includes critical bug fixes for event propagation, batch initialization, task serialization, and guardrail handling, plus a security update to python-dotenv. This alpha release enhances the platform's capabilities for AI agent development with improved infrastructure support and developer resources.

crewAI v1.14.3a1 introduces checkpoint and fork support for standalone agents, enhancing workflow management capabilities. The release includes critical bug fixes for Gemini streaming tool calls, checkpoint TUI redesign, and dry-run ordering. Documentation has been updated to reflect the new version and changelog entries.