Agent Teams

crewAI 1.8.0 introduces production-ready Flows and Crews architecture with native async chain support for agent-to-agent (a2a) communication, including poll/stream/push update mechanisms. The release adds human-in-the-loop (HITL) feedback capabilities for Flows, streaming tool call events, and enhanced event handling through improved EventListener and TraceCollectionListener.

crewAI 1.8.1 release introduces A2A (Agent-to-Agent) task execution utilities with server configuration and additional transports, along with bug fixes for Azure model support, flow execution error handling, and frame inspection depth. The release also includes documentation updates for A2A features and work-in-progress PII redaction documentation.

crewAI 1.9.0 introduces structured outputs and response_format support across providers, native multimodal file handling with OpenAI responses API, and Keycloak SSO provider support. The release includes improvements to tool calling, event ordering with parent-child hierarchy, a2a task execution utilities, and various bug fixes for file storage, API handling, and error management.

CrewAI 1.10.0 introduces enhanced MCP tool resolution, improved JSON argument parsing, user input handling in Flows, and migrates the CLI HTTP client from requests to httpx. The release includes 20+ bug fixes addressing tool validation, schema handling, callback execution, and race conditions, plus documentation updates for security guidance and 96 new integration actions.

OpenAI Agents Python SDK v0.9.0 drops Python 3.9 support and introduces configurable timeout handling for function tools with options for timeout_seconds, timeout_behavior, and timeout_error_function. The release also narrows the Agent#as_tool() return type to FunctionTool, adds ToolOutputTrimmer for context management, and includes fixes for tracing and audio buffer handling.

OpenAI Agents Python v0.9.1 release includes critical bug fixes for input history materialization, tracing function spans, import-time fork hazards, and nested agent-tool state persistence. The release also bumps the RunState schema to 1.1 with explicit backward-read policy and includes comprehensive documentation updates.

OpenAI Agents Python v0.9.2 introduces a new `reasoning_item_id_policy: 'omit'` option for RunConfig to prevent 400 errors when using reasoning models with inconsistent item sets. The release includes fixes for reasoning item filtering in nested handoffs and voice trace handling, plus documentation updates.

OpenAI Agents Python v0.10.0 introduces WebSocket mode support for the Responses API as an opt-in feature, enabling more efficient real-time communication. The release includes utilities like `responses_websocket_session()` and configuration options to enable WebSocket connections globally or per-agent, along with bug fixes for token usage tracking.

OpenAI Agents Python v0.10.2 release includes bug fixes for trace reattachment without duplicates, oversized tracing span payload sanitization, MCP policy approval requirements, and exposure of model request IDs on raw responses. The release also includes documentation structure improvements and updates to translated pages.

OpenAI Agents Python v0.10.3 release includes new features for exposing immutable agent tool invocation metadata on run results and adding RunResult tool_context accessor for agent tools. Performance improvements include using deque for BFS queue and voice task ordering, along with comprehensive documentation updates and test enhancements.

OpenAI Agents Python v0.10.4 release includes a critical fix for isolating parallel function tool failures to prevent cascading errors. The release also improves documentation navigation and entry points, updates translated documentation, and adds stability checks for async teardown operations.

OpenAI Agents Python v0.10.5 release adds explicit MultiProvider prefix modes and improves error handling by returning McpError as structured results instead of crashing agent runs. The release includes extensive documentation improvements for Dapr sessions, realtime transport, agent runtime flows, and fixes Python 3.11+ compatibility issues.

Google ADK Python v1.20.0 introduces multi-provider LLM support (Claude, LiteLLM), streaming function call arguments, and a new APIRegistryToolset for Cloud API integration. The release includes numerous bug fixes for agent validation, response processing, path handling, and LLM compatibility improvements.

OpenClaw v2026.2.24 release introduces enhanced auto-reply/abort shortcuts with multilingual support, improved Android UX with native onboarding, and critical security hardening including multi-user trust model detection and Docker namespace restrictions. The release includes breaking changes to heartbeat delivery targeting and sandbox security, along with extensive fixes for routing isolation, channel-specific message delivery, Discord voice reliability, and cross-platform messaging stability.

OpenClaw v2026.2.25-beta.1 release includes improvements to Android chat streaming and startup performance, UI enhancements for mobile compose actions, and a major refactor of heartbeat configuration policy. The release addresses numerous critical fixes across Telegram, Slack, Discord, and LINE channels, including subagent delivery state machine improvements, webhook handling, session threading, media routing, and typing indicator management.

OpenClaw v2026.2.25 release includes improvements to Android chat streaming and startup performance, UI enhancements for mobile compose actions, and a breaking change to heartbeat direct message delivery policy (now `allow` by default). The release contains numerous bug fixes across Telegram, Slack, Discord, LINE channels, agent routing, cron scheduling, and model fallback logic.

OpenClaw v2026.2.26 introduces major features including External Secrets Management with a complete workflow, ACP/Thread-bound agents as first-class runtimes, new agent routing CLI commands for account-scoped management, and Android device capabilities. The release also includes numerous fixes for Telegram DM allowlist inheritance, delivery queue recovery, typing indicators across channels, and various platform-specific lifecycle and authentication improvements.

Strata is an open-source MCP server by Klavis AI that enables AI agents to access thousands of API tools through progressive discovery rather than overwhelming them with all options at once. The system guides agents through hierarchical categories and actions, achieving 15.2% higher accuracy than official GitHub and Notion servers while supporting complex multi-app workflows with 83%+ accuracy.

Wild Moose is an autonomous AI agent designed for production debugging that connects to observability data like logs and metrics from Datadog. Rather than focusing on code generation, it performs root-cause analysis by exploring multiple data sources through conversational interfaces, combining code execution with API invocations to answer debugging questions.

Nous is an open-source TypeScript agent framework combining features of CrewAI, OpenDevon, and LangFuse, designed for building autonomous and software engineering agents with integrated tooling. It includes a Web UI, database persistence, tracing, human-in-the-loop functionality, and a novel autonomous agent that generates Python code executed in a WebAssembly sandbox for improved reasoning and reduced LLM costs.