Installation
Getting started with agent frameworks and tools
Build a playbook about Installation
Save articles from this feed, then generate a personalized implementation guide
OpenClaw v2026.5.25-beta.1 is a maintenance release focusing on bug fixes and platform compatibility improvements. Key fixes address iMessage attachment handling, Windows native support for package scripts, Alpine Linux installer compatibility, and MCP server timeout issues. The release includes numerous test infrastructure improvements and configuration enhancements to ensure stability across Linux, macOS, and Windows platforms.
★★★★★OpenClaw v2026.5.24-beta.1 introduces significant performance optimizations across the Gateway layer through caching and lazy-loading strategies, adds real-time collaboration features for WebUI and Discord voice callers, expands the Meeting Notes plugin with Discord integration, and includes extensive documentation improvements and CLI enhancements. Key additions include adaptive image compression, improved diagnostics with sanitized telemetry, and refined sub-agent bootstrap context management. The release also modernizes the Plugin SDK with updated messaging APIs and adds new maintainer tooling for bug-sweep workflows.
★★★★★This guide demonstrates how to build Claude Managed Agents with persistent memory capabilities that learn and retain user preferences across multiple sessions. Users create a memory store, configure a shopping agent with file access tools, and show how the agent automatically reads and updates customer preferences on repeat visits. The memory system uses a simple file-based approach mounted at /mnt/memory/ that both the agent and application can access via API.
★★★★★OpenClaw v2026.4.24-beta.2 addresses critical runtime issues on Windows by fixing package-root dependency resolution in bundled-plugin installations. The release ensures compatibility during updates from v2026.4.23 by temporarily disabling future bundled plugins until the updater completes. This prevents npm update failures and compatibility breakage in copied-runtime environments.
★★★★★OpenClaw v2026.4.15-beta.1 introduces significant enhancements across control UI, memory management, and security. Key additions include OAuth token health monitoring, cloud storage support for LanceDB memory indexes, GitHub Copilot embedding provider integration, and experimental lean mode for local models. The release focuses on security hardening with credential redaction, symlink protection, and improved authentication handling, alongside numerous bug fixes for CLI configuration, memory access control, and provider failover logic.
★★★★★OpenClaw v2026.4.12 is a comprehensive quality release emphasizing plugin loading reliability, memory system improvements, and expanded local model support. Key additions include an Active Memory sub-agent plugin, local MLX speech provider for Talk Mode, LM Studio provider for self-hosted models, and enhanced Feishu setup workflows. The release also addresses critical security fixes, dreaming/narrative stability, and improves gateway lifecycle management and Matrix client streaming support.
★★★★★This tutorial introduces the Claude Managed Agents API by walking through a practical debugging workflow where an agent iteratively fixes failing tests in a Python package. It covers the three core resources (Agent, Environment, Session), file mounting, and the streaming event loop pattern. The example demonstrates how agents autonomously discover the iterate-observe-fix loop by running tests, reading failures, editing code, and repeating until all assertions pass.
★★★★★The Claude Agent SDK provides built-in session management functions to build conversation history sidebars without writing custom parsers. This cookbook demonstrates how to list, read, rename, tag, and fork sessions stored as JSONL transcripts on disk. By leveraging SDK primitives like list_sessions(), get_session_messages(), and rename_session(), developers can implement session browsers for desktop apps, IDE extensions, and chatbots without managing file I/O directly.
★★★★★