Memory Systems

OpenAI Agents Python v0.19.3 is a maintenance release focused on bug fixes and stability improvements across core agent functionality, session management, real-time features, and extensions. The release addresses 34 bug fixes including tool name collision resolution, guardrail reporting, streaming behavior, and session persistence. Key areas improved include MCP auto-pagination, sandbox hardening, real-time audio handling, and AnyLLM provider stream management.

OpenClaw v2026.7.1-1 release addresses five critical fixes improving system stability and reliability. Key improvements include fixing Codex progress replies to complete full turns, repairing Memory Core startup conflicts, handling WSL permission errors gracefully, recovering from legacy migration issues, and resolving managed plugin update problems. These fixes prevent fatal restart loops, enable proper error recovery, and ensure smooth upgrades across the platform.

OpenClaw v2026.7.2-beta.7 introduces major stability and feature enhancements including state safety with quarantine stores and crash-recoverable snapshots, durable channel delivery across multiple platforms, session rewind/branching capabilities, interactive MCP Apps with dashboards, structured questions and approvals, meeting integration with Teams/Zoom/Google Meet, Wear OS companion app, and guided local inference setup. The release also adds Claude Opus 5 support, native app improvements across macOS/Linux, enhanced memory recall, scheduling with dynamic cadence, Fish Audio speech synthesis, and numerous security hardening fixes.

OpenAI Agents Python v0.19.2 is a maintenance release focused on bug fixes and stability improvements across multiple subsystems. Key improvements include exposing original callables through wrappers, fixing guardrail result reporting, enhancing MCP credential redaction for security, improving memory session item counting, and resolving voice/audio dispatcher issues. The release also addresses sandbox environment preservation, modal path validation, realtime event payload handling, and tracing deadline management.

OpenAI Agents Python v0.19.1 is a maintenance release focused on bug fixes and stability improvements across sandbox path handling, audio diagnostics, WebSocket error handling, model execution, memory management, and tracing. Key fixes address streamed model input handling, guardrail task cancellation, SQLite session counting, and batch trace processing. Documentation updates include URL corrections, tracing integration links, and standardization of decorator usage in examples.

OpenClaw v2026.7.2-beta.5 introduces major reliability and safety improvements including crash-recoverable state management with quarantine stores, durable channel delivery across multiple platforms, session rewind/branching capabilities, interactive MCP Apps with dashboards, and structured question/approval workflows. The release adds support for new models (Claude Opus 5, Kimi K3, GPT Live), native apps for macOS/Linux/Wear OS, meeting integrations (Teams, Zoom, Google Meet), and guided local inference setup. Extensive security fixes address authorization, SQLite data safety, channel delivery persistence, and session lifecycle management.

OpenAI Agents Python v0.18.3 release includes configurable tracing spans for tasks and turns, improved realtime response usage tracking, and 13 bug fixes addressing serialization, memory management, concurrent execution isolation, and schema handling. Key improvements enhance reliability in handoff preservation, session state management, and error handling across computer vision, sandbox, and model provider integrations.

crewAI 1.15.3a1 introduces execution interception points with improved hook documentation, adds organization ID support to PlusAPI, and enables declarative flows on TUI. The release includes significant bug fixes for tool execution, memory management, token usage reporting, and hook behavior. Multiple enhancements improve custom OpenAI URL handling and prevent unintended side effects in execution workflows.

Onyx is an open-source chat UI (YC W24) that works with any LLM and provides enterprise-grade features like RAG, web search, MCP, and deep research. Built by the creators of Danswer, the team pivoted after realizing users wanted secure, self-hosted chat interfaces with world-class UX rather than just search. The platform supports RBAC, SSO, and on-prem hosting, with key innovations in context management and model-agnostic tool handling that enable reliable multi-model deployments at scale.

OpenClaw v2026.7.2-beta.1 introduces remote coding sessions on cloud workers, native automation and mobile capabilities, safer channel operations, guided Control UI setup, improved gateway and session recovery, and new Linux packaging options. The release encompasses 2425 merged PRs with major enhancements to session management, coding agents, security boundaries, and reliability across multiple platforms including mobile, desktop, and headless systems.

Google ADK Python v2.4.0 introduces significant enhancements including mTLS support across multiple tools, OpenAI Responses API integration, Managed Agents API backing, and streaming improvements for thoughts and media. The release adds workflow-as-tool capabilities, enhanced database session management, and improved analytics with thinking/tool-use token tracking. Multiple bug fixes address security concerns, path traversal prevention, and SDK compatibility updates.

Release 2026.7.4 of modelcontextprotocol/servers updates four core server packages to version 2026.7.4. The release includes updates to the everything server, filesystem server, sequential-thinking server, and memory server. This is a coordinated release across multiple MCP server implementations.

Claude Code v2.1.186 introduces CLI authentication for MCP servers, enhanced workflow filtering, and improved agent team management. Key fixes address streaming failures after sleep, subagent transcript issues, and permission prompt handling. The release also improves skill metadata flexibility, memory management, and background session behavior with better user control over tool permissions.

OpenClaw v2026.6.8 is a major release focusing on improved channel delivery (Telegram/WhatsApp), enhanced agent and gateway recovery mechanisms, expanded provider/model support (GLM-5.2, Claude Haiku 4.5), better usage hooks with native footer rendering, and UI/mobile stability improvements. The release includes fixes for memory management, state handling, diagnostics, and numerous edge cases across channels, agents, and runtime systems.

OpenClaw v2026.6.8-beta.2 delivers significant improvements across messaging channels, agent recovery, provider/model handling, and UI stability. Telegram and WhatsApp now support richer message formatting with better delivery reliability, while agent and gateway recovery mechanisms are enhanced across multiple failure scenarios. The release includes expanded provider support (GLM-5.2, Claude Haiku 4.5), improved usage hooks with native footer rendering, and numerous fixes for memory, state diagnostics, and mobile UI flows.

OpenClaw v2026.6.8-beta.1 introduces significant improvements to channel delivery (Telegram rich text, WhatsApp ACP bindings), agent and gateway recovery mechanisms, expanded provider/model support (GLM-5.2, Claude Haiku 4.5), enhanced usage hooks with footer rendering, and UI/mobile stability fixes. The release addresses 50+ issues across messaging, runtime reliability, authentication, memory management, and user interface components, with contributions from 30+ developers.

OpenClaw v2026.6.7-beta.1 delivers significant improvements across channel delivery, provider resilience, security boundaries, and recovery paths. Key enhancements include tighter Slack/Telegram integration, better model handling for Kimi/Mistral/DeepSeek/Anthropic, safer auth contexts, and improved failure recovery for agents and cron jobs. The release also strengthens UI/docs accessibility, Docker bundling, and QA validation with new scorecard taxonomy artifacts.

crewAI v1.14.7 introduces pluggable backends for memory, knowledge, RAG, and flow management, along with a native Snowflake Cortex LLM provider and chat API for conversational flows. The release includes significant bug fixes for checkpoint restoration, telemetry, file input handling, and security vulnerabilities. Performance improvements focus on lazy-loading docling imports to speed up crewai imports, while refactoring decouples conversational logic and splits flow.py into modular components.

OpenAI Agents Python v0.17.5 release includes bug fixes for sandbox error retryability, tool-end hook result typing, and SpeechGroupSpanData slots optimization. The release also bumps the Modal sandbox extra to 1.4.3 and adds comprehensive documentation improvements including a MongoDB session memory example, docstring corrections, and external tracing processor updates. Test coverage enhancements were made for streaming paths and retry helpers.

Claude Code v2.1.172 introduces hierarchical sub-agent spawning (up to 5 levels deep), improves AWS region configuration handling for Bedrock, and adds a marketplace search feature. The release includes numerous bug fixes addressing context management, session stability, model selection, and UI responsiveness issues. Performance optimizations reduce CPU usage and improve message handling in long conversations.