Agent Teams

OpenClaw v2026.4.20-beta.2 is a major release featuring UI/UX improvements to the onboarding wizard, strengthened agent prompts, tiered model pricing support, session maintenance optimizations, and numerous provider-specific enhancements for OpenAI, Anthropic, Moonshot Kimi, and other integrations. The release includes 40+ fixes addressing security, transport normalization, thinking mode handling, and plugin dependency management.

OpenClaw v2026.4.20 is a major release featuring UI/UX improvements to the onboarding wizard, enhanced agent prompts with better completion bias and verification, support for tiered model pricing including Moonshot Kimi models, session maintenance optimizations to prevent memory issues, and numerous fixes across plugins, APIs, and provider integrations. Key improvements include streaming thinking in Mattermost, better group-specific system prompts in BlueBubbles, and refined reasoning model handling across OpenAI GPT-5 and other providers.

OpenClaw v2026.4.20-beta.1 introduces significant improvements to the onboarding wizard UI, strengthens default agent prompts, adds tiered model pricing support, and enhances session maintenance with automatic pruning. The release includes numerous fixes for provider integrations (OpenAI, Anthropic, Moonshot), plugin lifecycle management, and security hardening across multiple components including SSRF guards and environment variable isolation.

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.

OpenClaw v2026.4.19-beta.2 addresses critical fixes for agent streaming, nested lane processing, and session token tracking. Key improvements include proper usage reporting for OpenAI-compatible backends, elimination of head-of-line blocking in nested agent runs, and preservation of session token totals across provider metadata variations. The release also ensures backward compatibility with legacy update verification for QA Lab runtime environments.

OpenClaw v2026.4.19-beta.1 releases critical fixes addressing cross-agent channel routing, Telegram callback handling, browser CDP connectivity, and Codex token accounting. Key improvements include proper account preservation in multi-agent setups, prevention of stale pagination buttons blocking updates, WSL-to-Windows Chrome endpoint detection, and accurate context usage reporting. Enhanced diagnostics for Windows browser startup failures provide better troubleshooting visibility.

Claude Code v2.1.114 is a minor release that addresses a critical bug fix in the permission dialog system. The update resolves a crash that occurred when an agent teams teammate requested tool permission, improving stability and reliability for collaborative agent workflows.

crewAI 1.14.2 introduces checkpoint management features including resume, diff, and prune commands with lineage tracking and forking capabilities. The release enhances LLM token tracking with reasoning and cache tokens, improves CLI ergonomics for deploy validation and template management, and fixes multiple security vulnerabilities across dependencies. Key improvements include scoped streaming handlers to prevent data contamination, recursive glob for checkpoint discovery, and better HITL (Human-in-the-Loop) resume event handling.

OpenClaw v2026.4.15 is a major release featuring Claude Opus 4.7 as the default Anthropic model, new Google Gemini text-to-speech support, a Model Auth status card for OAuth health monitoring, cloud storage support for LanceDB memory, and GitHub Copilot embedding provider integration. The release includes numerous stability fixes across gateway tools, agent replay recovery, Docker builds, Matrix E2EE, memory management, and channel integrations, plus packaging improvements to reduce bundle size and plugin runtime dependencies.

OpenAI's openai-agents-python v0.14.0 introduces Sandbox Agents, a beta feature enabling agents to run in persistent, isolated workspaces with file access, command execution, and cross-run continuity. The release includes multiple execution backends (local, Docker, hosted providers), workspace management with snapshots and resume capabilities, sandbox memory for learning across runs, and comprehensive examples. Runtime enhancements provide tracing, session lifecycle management, and seamless integration with the existing Agent and Runner framework.

crewAI version 1.14.2a5 is a minor alpha release that updates the changelog and version information from the previous v1.14.2a4 release. This is a maintenance update focused on documentation consistency. The release includes contributions from @greysonlalonde.

OpenClaw v2026.4.15-beta.1 introduces significant enhancements across control UI, memory management, and security. Key additions include OAuth token health monitoring, cloud storage support for LanceDB memory indexes, GitHub Copilot embedding provider integration, and experimental lean mode for local models. The release focuses on security hardening with credential redaction, symlink protection, and improved authentication handling, alongside numerous bug fixes for CLI configuration, memory access control, and provider failover logic.

crewAI v1.14.2a4 is a patch release introducing resume hints to devtools for improved failure handling. The release addresses critical bug fixes including strict mode forwarding to Bedrock Converse API, a pytest security vulnerability (GHSA-6w46-j5rx-g56g), and updates the OpenAI dependency lower bound to >=2.0.0. This alpha release maintains stability while preparing for the full 1.14.2 version.

OpenClaw v2026.4.14-beta.1 is a maintenance release addressing 30+ security fixes, stability improvements, and feature enhancements across messaging platforms, browser automation, scheduling, memory systems, and agent tooling. Key improvements include replacing markdown parsing to prevent ReDoS attacks, fixing Telegram forum topic handling, correcting cron scheduler behavior, and enforcing SSRF/security policies across multiple integrations. The release emphasizes background task optimization and proper context preservation across system components.

OpenClaw v2026.4.12 is a comprehensive quality release emphasizing plugin loading reliability, memory system improvements, and expanded local model support. Key additions include an Active Memory sub-agent plugin, local MLX speech provider for Talk Mode, LM Studio provider for self-hosted models, and enhanced Feishu setup workflows. The release also addresses critical security fixes, dreaming/narrative stability, and improves gateway lifecycle management and Matrix client streaming support.

crewAI 1.14.2a3 is a patch release introducing a deploy validation CLI and improved LLM initialization ergonomics. The release addresses critical security vulnerabilities in pypdf, uv, and requests libraries, plus fixes for Bedrock tool arguments, strict mode schema sanitization, and test flakiness. Documentation updates include enterprise A2A feature clarifications and OSS A2A improvements.

OpenClaw v2026.4.11 introduces major enhancements to memory/dreaming features with ChatGPT import ingestion, improved media rendering in chat UIs, expanded video generation capabilities, and better integration with platforms like Feishu and Microsoft Teams. The release includes plugin manifest improvements for declarative setup flows, performance optimizations for model discovery caching, and numerous bug fixes across OAuth, transcription, timeouts, and platform-specific issues to improve stability and user experience.

crewAI 1.14.2a2 introduces a checkpoint TUI with tree view and fork support, enhances LLM token tracking with reasoning and cache tokens, and adds checkpoint forking with lineage tracking. The release includes bug fixes for strict mode forwarding to Anthropic and Bedrock providers, and hardens the NL2SQLTool with read-only defaults and query validation. Key additions include the `from_checkpoint` parameter for kickoff methods and embedding `crewai_version` in checkpoints with a migration framework.

This tutorial demonstrates server-side prompt versioning and rollback for Managed Agents, enabling PMs to update agent prompts without code deployments. It covers creating an agent (v1), evaluating it against a labeled test set, shipping an updated prompt (v2), detecting performance regressions, and rolling back by pinning sessions to a specific version. The workflow replaces traditional code-based prompt management with immutable versioned prompts that can be quickly reverted if issues arise.

This tutorial demonstrates building a webhook-triggered SRE incident response agent using Claude Managed Agents that automatically investigates production alerts, consults runbooks, proposes infrastructure fixes via pull requests, and gates merging behind human approval. The agent combines built-in sandbox tools (bash, read, edit) with custom tools for PR management and human-in-the-loop approval, providing complete audit trails in the Anthropic Console. The example uses mocked PagerDuty, GitHub, and Datadog integrations to focus on agent patterns, with guidance for swapping in real services.