Agent Teams

OpenClaw v2026.3.13-1 is a recovery release addressing a GitHub immutability constraint where the original v2026.3.13 tag could not be reused. This patch release includes 50+ bug fixes and improvements across compaction, session management, platform integrations (Telegram, Discord, Slack, Android, iOS), security hardening, and UI refinements. Key fixes address token counting in compaction, SSRF vulnerabilities, gateway metadata failures, and memory regressions in the build system.

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 v2026.3.13-beta.1 is a pre-release featuring significant UI/UX improvements across Android and iOS onboarding, enhanced browser automation with Chrome DevTools MCP support, and numerous stability fixes. Key improvements include redesigned chat settings, first-run welcome flows, batched browser actions, and critical security patches for device pairing and webhook authentication. The release maintains macOS app version compatibility for future non-beta releases.

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 build AI agents with persistent memory using Claude's memory tool and context editing capabilities. It addresses challenges of long-running agents losing learned patterns between sessions and context window overflow by implementing cross-conversation learning and automatic context management. The guide covers practical implementations for use cases like code review assistants, research assistants, and customer support bots, with setup instructions and best practices for memory security and organization.

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.

This cookbook teaches how to build a research agent using Claude Agent SDK with WebSearch tool for autonomous information gathering and synthesis. The guide demonstrates creating a functional research agent in just a few lines of code, then progresses to production improvements including conversation memory, system prompts for specialized behavior, and multimodal research capabilities. The agent autonomously decides when and how to search, follows promising leads, and synthesizes findings without predefined workflows.

This cookbook demonstrates building an autonomous SRE incident response agent using the Claude Agent SDK with read-write MCP tools for safe infrastructure access. The agent can investigate incidents by querying metrics and logs, diagnose root causes, apply remediations by editing configs and restarting services, and document post-mortems. The pattern uses a subprocess-based MCP server with scoped tool access, clear tool descriptions, and human-in-the-loop workflows to enable autonomous yet controlled incident response.

This cookbook demonstrates automatic context compaction for managing token limits in long-running agentic workflows. It shows how the Claude Agent Python SDK can automatically compress conversation history when token usage exceeds a threshold, enabling tasks to continue beyond the 200k token context limit. The example uses a customer service agent processing support tickets, where each ticket requires multiple tool calls that accumulate in conversation history. By implementing context compaction with the compaction_control parameter, agents can maintain focus and efficiency across many iterations without manual context management.

Programmatic Tool Calling (PTC) enables Claude to write and execute code that calls tools directly within the code execution environment, eliminating round-trips through the model for each tool invocation. This approach significantly reduces latency and token consumption, especially when dealing with large datasets or sequential tool dependencies. The cookbook demonstrates PTC using a team expense management API scenario where Claude analyzes employee expenses across multiple tool calls, filters irrelevant data programmatically, and identifies budget overages without excessive context window usage.

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.

Claude Code v2.1.71 introduces the `/loop` command for recurring prompt execution and cron scheduling tools, adds rebindable voice activation keybindings, and expands bash auto-approval allowlist with common utilities. The release focuses on stability improvements, fixing critical issues like stdin freezes in long sessions, CoreAudio initialization delays, OAuth token refresh failures, and image processing context overflow. Multiple UX and plugin management enhancements improve startup performance, fork isolation, and multi-instance reliability.

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 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 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.