Multi-Agent Systems

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 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.

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.

crewAI v1.11.1 introduces a flow_structure() serializer for Flow class introspection and addresses multiple security vulnerabilities by updating dependencies (pypdf, tinytag, langchain-core). Key fixes include preserving full LLM config during HITL resume for non-OpenAI providers, preventing path traversal in FileWriterTool, and resolving crashes in lock_store when redis is unavailable. The release also includes documentation improvements for custom tools and event listeners, plus refactoring to replace urllib with requests and improve type serialization.

OpenAI Agents Python v0.12.2 is a maintenance release that fixes two critical issues: orphan hosted shell calls during multi-turn replay and normalized input list handling for filtered handoff follow-ups. The release includes documentation updates and improves the stability of agent interactions in complex conversation scenarios.

OpenClaw v2026.3.12 introduces major UI/dashboard improvements with modular views, fast-mode toggles for OpenAI and Anthropic models, provider-plugin architecture for Ollama/vLLM/SGLang, Kubernetes deployment support, and subagent session control. The release includes 30+ fixes addressing security vulnerabilities (device pairing, plugin auto-load, Unicode obfuscation), model compatibility issues (Kimi Coding, OpenRouter, Moonshot), chat deduplication across platforms (Slack, Telegram, iMessage, Mattermost), and infrastructure stability (session discovery, plugin caching, Windows updates).

This cookbook demonstrates how to connect Claude agents to external systems using MCP (Model Context Protocol) servers for GitHub monitoring and CI workflows. The guide covers integrating Git and GitHub MCP servers to enable agents to interact with repositories, manage workflows, and perform observability tasks. By leveraging MCP servers, agents gain access to specialized tools for Git operations, GitHub platform integration, and CI/CD monitoring without relying on command-line interfaces.

This cookbook article introduces the Claude Agent SDK for building multi-agent systems, using a Chief of Staff agent for a startup as the primary example. It demonstrates key features including persistent memory via CLAUDE.md files, bash tool execution for Python scripts, and coordination of specialized subagents. The article progressively builds a comprehensive agent system that aggregates insights from multiple domains to provide executive summaries and actionable recommendations for a CEO managing a $10M Series A startup.

OpenClaw v2026.3.7 introduces major enhancements to context engine plugins, persistent channel bindings for Discord/Telegram, multi-language UI support (Spanish), improved web search capabilities, and Docker containerization optimizations. The release includes a breaking change requiring explicit gateway auth mode configuration. Key additions enable alternative context management strategies, durable ACP thread routing, per-topic agent overrides, and enhanced security with config validation.

Microsoft AutoGen python-v0.5.7 release introduces improvements to AzureAISearchTool with unified search methods (full-text, vector, and hybrid), enhanced SelectorGroupChat with model_context parameter for better speaker selection, and improved OTEL tracing with additional metadata. The release also includes various bug fixes and improvements to agent runtime, documentation, and integrations with external services like Anthropic Bedrock and MCP servers.

Microsoft AutoGen v0.6.0 introduces concurrent agent execution in GraphFlow with fan-out-fan-in patterns, callable conditions for edge routing, and a new OpenAIAgent backed by OpenAI's Response API. Key improvements include enhanced MCP support, AssistantAgent workbench capabilities, code executor optimizations, and expanded model client compatibility across Ollama, Anthropic Bedrock, and OpenAI platforms.

Microsoft AutoGen released python-v0.6.1 with bug fixes for GraphFlow cycle checking and graph validation logic. The release also adds function calls and results tracking in ToolCallSummaryMessage.

Microsoft AutoGen python-v0.6.2 introduces streaming tools with `BaseStreamTool` and `StreamWorkbench` support, adds `tool_choice` parameter to `ChatCompletionClient`, and enables `AssistantAgent` with an inner tool calling loop via `max_tool_iterations`. Additional features include OpenTelemetry GenAI traces, Mem0 memory extension, `output_task_messages` flag, GraphFlow improvements, and support for latest models like Gemini 2.5 Flash.

Microsoft AutoGen python-v0.6.4 release includes improvements to GraphFlow for better state management and task resumption, enhancements to Workbench implementations with tool name/description overrides, and fixes for function calling support and conversation context pollution. The release also adds new features like Qwen2.5VL support, DuckDuckGo search tools, and improved documentation generation.

Microsoft AutoGen python-v0.7.1 release introduces major features including OpenAIAgent support for built-in tools, nested Team participants in GroupChat, RedisMemory extension, and upgrades to latest MCP and GraphRAG versions. Key improvements also include an `include_name_in_message` flag for optional name fields in OpenAI messages, JSON schema format support, and various bug fixes for serialization and tool handling.

Microsoft AutoGen released python-v0.7.2 with several improvements including making DockerCommandLineCodeExecutor the default for MagenticOne team, adding approval_func option to CodeExecutorAgent, and adding parallel_tool_call support to OpenAI model client config. The release also includes bug fixes for structured logging serialization and new Redis agent memory support for JSON and MARKDOWN formats.

Microsoft AutoGen python-v0.7.3 release includes bug fixes for RedisStore serialization, OpenAIAgent function tool schema, and pydantic model typing with anyOf/oneOf support. The release also adds GPT-5 model info, ensures task runner tools are strict, and updates documentation with corrections for MCP examples and version references.

Microsoft AutoGen releases python-v0.7.4 with bug fixes for Redis deserialization errors and streaming support issues. The release includes documentation updates and version bumps, with contributions from new contributor BenConstable9.

Microsoft AutoGen releases python-v0.7.5 with 18 bug fixes and improvements including support for linear memory in RedisMemory, thinking mode support for Anthropic client, fixes for streaming response handling, GraphFlow cycle detection, and security enhancements with DockerCommandLineCodeExecutor. The release addresses issues with Bedrock streaming, JSON schema conversion, token counting, and MCP session management.

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.