Agent Teams

crewAI v1.13.0a3 introduces token usage tracking in LLM events and tool metadata publishing to AMP. The release includes bug fixes for GPT-5.x model compatibility, comprehensive documentation updates on SSO configuration and agent capabilities, and significant refactoring converting Flow and LLM classes to Pydantic BaseModel with improved type annotations.

crewAI v1.13.0a4 is a minor alpha release that updates the changelog and version documentation from v1.13.0a3. This release represents incremental progress in the 1.13.0 alpha development cycle. The update was contributed by @greysonlalonde and focuses on maintaining accurate release documentation.

OpenClaw v2026.3.31 is a major release introducing significant breaking changes to node execution, plugin SDK deprecations, and stricter security defaults for dangerous code scanning. Key improvements include a unified background task control plane, new channel integrations (QQ Bot), enhanced Matrix/MCP support, and security hardening across gateway authentication and node command execution. The release emphasizes safer defaults while expanding platform capabilities for agents, channels, and integrations.

OpenClaw v2026.3.31-beta.1 introduces significant breaking changes to node execution, plugin SDK deprecation, and stricter security defaults for plugin/skill installation. Key improvements include unified background task management with flow control, expanded channel support (QQ Bot), enhanced MCP capabilities with remote HTTP/SSE servers, and security hardening across gateway authentication, node commands, and event handling. Multiple channel-specific enhancements (Matrix, LINE, Teams, WhatsApp, Slack) and provider integrations (OpenAI Responses, Pi Codex, TTS diagnostics) round out the release.

This cookbook teaches context engineering strategies for long-running AI agents, focusing on three key techniques: compaction (summarizing context), tool-result clearing (removing re-fetchable tool outputs), and memory (persistent external storage). The guide addresses context rot—the degradation of model performance as context windows grow—and provides practical implementations using Claude's API. Through a research agent example, it demonstrates how to combine these strategies to manage token growth, maintain conversation continuity, and persist knowledge across sessions.

OpenAI Agents Python v0.13.3 is a maintenance release addressing two critical bugs: fixing stale hydrated input IDs in server conversation tracking and enabling raw image_url content parts in chat completions. The release also includes documentation improvements for non-OpenAI providers, updated translations, and code quality enhancements with Ruff linting.

crewAI v1.13.0rc1 is a release candidate update that includes documentation improvements, specifically updating the changelog and version information for v1.13.0a2. This is a pre-release version preparing for the full 1.13.0 stable release. The release was contributed by @greysonlalonde.

crewAI releases version 1.13.0a1 with critical bug fixes addressing documentation workflow issues and cache management for enterprise releases. The update includes comprehensive RBAC permissions documentation and deployment guides. Key improvements focus on Node.js LTS stability and package publishing reliability.

crewAI releases version 1.13.0a2, an alpha release focusing on deployment automation and enterprise reliability improvements. The release includes auto-update functionality for deployment test repositories during release cycles and enhanced resilience mechanisms for enterprise deployments. Documentation has been updated to reflect the new version and changelog entries.

CrewAI 1.12.0 introduces significant enhancements including Qdrant Edge storage backend, native OpenAI-compatible provider support (OpenRouter, DeepSeek, Ollama, vLLM, Cerebras, Dashscope), agent skills implementation, and automatic root_scope for hierarchical memory isolation. The release adds Arabic language support, a new docs-check CLI command, logout functionality, and resolves multiple bugs across type checking, HITL flow system, and memory management. Documentation improvements include a new CONTRIBUTING.md guide and instructions for using CrewAI without LiteLLM.

crewAI v1.12.0a3 is a patch release addressing critical bugs in credential handling for trace batch operations and the HITL (Human-in-the-Loop) flow system. The release includes documentation updates to reflect version changes from v1.12.0a2. This alpha version continues stabilization efforts for the 1.12.0 release cycle with contributions from @akaKuruma and @greysonlalonde.

OpenClaw v2026.3.24 introduces significant enhancements across gateway compatibility, agent tooling, and platform integrations. Key updates include OpenAI API compatibility improvements, Microsoft Teams SDK migration with streaming support, skill installation recipes with one-click setup, and expanded platform support for Slack, Discord, Telegram, and WhatsApp. The release also addresses numerous security, sandbox, and reliability fixes across media dispatch, channel startup, and message routing.

CrewAI 1.12.0a1 introduces native OpenAI-compatible provider support (OpenRouter, DeepSeek, Ollama, vLLM, Cerebras, Dashscope), agent skills, and automatic hierarchical memory isolation via root_scope. The release includes Arabic language support for documentation and tooling, a new docs-check command, and significant refactoring to decouple from LiteLLM while resolving mypy type-checking errors across all packages.

OpenClaw v2026.3.24-beta.1 introduces significant enhancements across gateway compatibility, agent tooling, platform integrations, and UI improvements. Key additions include OpenAI API compatibility endpoints, Microsoft Teams SDK migration with streaming support, skill installation recipes, and Docker container command support. The release focuses on improving user experience through better tool visibility, rich interactive replies, and comprehensive bug fixes across Telegram, Slack, Discord, WhatsApp, and other platforms.

Claude Code v2.1.83 introduces significant improvements to policy management, environment reactivity, security, and user experience. Key additions include a drop-in directory for managed settings, new hook events for environment changes, transcript search functionality, and enhanced subprocess credential scrubbing. The release addresses numerous stability issues, performance regressions, and UI glitches while improving startup latency and memory usage across various platforms.

OpenAI Agents Python v0.13.0 is a minor release that updates the default Realtime websocket model to gpt-realtime-1.5, expands MCP server capabilities with resource management and session tracking, and introduces opt-in reasoning content replay for chat completions. The release includes critical runtime stability fixes for concurrent writes, tool removal edge cases, and batch executor races, with no breaking changes.

LangChain v1.2.13 release includes LangSmith integration metadata enhancements for agent creation and chat model initialization, security updates for dependencies (PyJWT, pyasn1), bug fixes for OpenAI Responses API and Runtime exports, and general maintenance improvements including linting and CI optimizations.

Canary is an AI QA agent that analyzes pull requests by understanding codebases, identifying affected user workflows, and automatically generating and executing end-to-end tests. The platform connects to repositories, reads diffs to understand intent, runs tests against preview apps, and reports results directly on PRs with recordings. Beyond PR testing, it supports regression suites and continuous testing via plain English prompts, addressing the gap where modern AI tools accelerate development but lack comprehensive real-world behavior testing before merge.

OpenAI Agents Python v0.12.5 release includes enhancements to MCP (Model Context Protocol) integration with exposed authentication and HTTP client factory parameters, improved error recovery for streamed nested agent outputs, and fixes for resource closure and timeout handling in isolated sessions. The release focuses on reliability improvements for agent streaming and MCP communication.

Agent Skills are organized folder structures that encapsulate specialized expertise and knowledge that Claude can automatically invoke when relevant to a user's task. These skills enable Claude to access domain-specific tools, knowledge bases, and capabilities without explicit user instruction. Skills are designed to be modular, reusable, and automatically triggered based on task context and relevance.