Memory Systems

This tutorial introduces Projects in Claude.ai, a feature that enables users to organize their work by maintaining persistent context and custom instructions across conversations. Projects allow you to group related conversations, documents, and settings in one place, making it easier to manage complex workflows and maintain consistency across multiple interactions with Claude.

OpenAI Agents Python v0.12.4 release includes critical bug fixes for MCP (Model Context Protocol) tool invocations, retry logic improvements, and SQLite session memory handling. The update normalizes cancelled MCP invocations into tool errors, adds resilience for transient HTTP failures, fixes custom table name support in AdvancedSQLiteSession, and caps jittered retry delays. Documentation improvements and CI hardening were also included.

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.

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 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 developers how to manage long-running Claude conversations by implementing session memory compaction using background threading and prompt caching. Rather than waiting for context limits to be exceeded (reactive approach), the pattern enables instant compaction by proactively building summaries in the background. The guide covers writing effective session memory prompts, implementing background threading for zero-latency compaction, and applying prompt caching to reduce costs by ~80%. It includes Python code examples demonstrating both traditional (slow) and instant (fast) compaction strategies for conversational applications.

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.

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-v0.6.2 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-v0.7.1 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.

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 1.9.0 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.

Google ADK Python v1.21.0 introduces support for the Gemini Interactions API, enhances tools with header providers and SSL verification, upgrades BigQueryAgentAnalytics to v2.0, and adds Gemma3Ollama model integration. The release includes numerous bug fixes for LiteLLM response formatting, Spanner client initialization, OpenAPI schema generation, and security updates for FastAPI/Starlette vulnerabilities.

Google ADK Python v1.25.0 release introduces significant enhancements including a simple prompt optimizer demo, new CLI flags for auto session creation, event-delta memory management, and post-invocation token compaction. The release adds support for external access tokens in Google credentials, new tools like MCP resource loading and SkillToolset, plus health/version endpoints to the web server. Multiple bug fixes address async iteration, event loop issues, metadata preservation in streaming responses, and PostgreSQL timestamp handling.

Google ADK Python v1.26.0 release introduces major features including intra-invocation token compaction, Apigee LLM chat completions integration, Agent Skills spec compliance, BigQuery search catalog support, and an Agent Registry system. The release also includes numerous bug fixes for streaming tools, memory services, authentication, and various integrations across core, models, tools, evals, and services components.

Release 2025.8.4 of modelcontextprotocol/servers updates three packages: server-everything, server-memory, and mcp-server-time, all to version 2025.8.4. This release includes improvements and updates across the Model Context Protocol server implementations.

Release 2025.9.25 of modelcontextprotocol/servers updates four packages: server-everything, server-memory, mcp-server-git, and mcp-server-time, all to version 2025.9.25. This release includes updates across multiple MCP server implementations for enhanced functionality.

Release 2025.11.25 of modelcontextprotocol/servers updates five packages including sequential-thinking, everything, filesystem, memory, and git servers. All packages are bumped to version 2025.11.25.