Top Story
[Release] anthropics/claude-code v2.1.225: v2.1.225
Claude Code v2.1.225 introduces gateway spend-limit support with detailed cap information, adds workspace trust prompts for untrusted directories, and fixes critical issues including OAuth token handling, MCP server authentication failures on macOS, safety-filter refusal counting, cross-session message persistence, and conversation history corruption. The release also improves Remote Control functionality with direct photo handling and enhanced session messaging capabilities.
- Gateway spend-limit warnings now display the cap amount, reset time, and operator's message for better cost transparency
- Workspace trust prompt added to `claude agents` command for untrusted directories, matching core `claude` behavior
- Fixed critical 401 error when short-lived tokens replace long-lived OAuth tokens, which broke headless sessions until restart
- +7 more key points...
By Topic
Agent Teams
See all 10 →[Release] crewaiInc/crewAI 1.15.13: 1.15.13
crewAI version 1.15.13 is a maintenance release focusing on bug fixes and documentation improvements. Key fixes include preserving LiteLLM provider routing, hardening LLM event-bus mocks, correcting Anthropic cache token usage reporting, and addressing a security vulnerability in the h2 dependency. Documentation enhancements include a new locale synchronization workflow and corrections to README links and contribution guidance.
joaomdmoura
[Release] openclaw/openclaw v2026.6.33: openclaw 2026.6.33
OpenClaw v2026.6.33 is a major security and reliability release featuring safer network boundaries with response size caps and credential protection, more reliable long-running agents with improved stall detection, stronger channel delivery for Discord and Telegram, safer credential recovery mechanisms, and support for extended-stable package updates. The release includes 169 merged PRs addressing authorization, tool authority, external tooling scoping, and numerous stability fixes across gateway, provider, browser, and webhook systems.
RomneyDa
[Release] openclaw/openclaw v2026.6.34: openclaw 2026.6.34
OpenClaw v2026.6.34 is an extended-stable maintenance release focused on security hardening and reliability improvements without new features. Key enhancements include safer browser and network boundaries with sandboxed routes, more resilient agent and provider runs with improved session handling, stronger channel recovery mechanisms, safer operator diagnostics with credential protection, and more robust local runtime state management. The release includes 25 merged PRs addressing execution safety, delivery stability, and gateway reliability, with upcoming deprecations for Plugin SDK migration scheduled after July 24.
RomneyDa
Security
See all 4 →[Release] google/adk-python v1.38.0: v1.38.0
Google ADK Python v1.38.0 release introduces safety settings forwarding to the Live API and addresses critical security and stability issues. Key improvements include preventing shell execution vulnerabilities in ReadFileTool, excluding problematic nltk dependency versions, fixing Live API agent transfers, and enhancing evaluation error handling. This release focuses on security hardening and reliability improvements for agent development.
wuliang229
OpenClaw Has 385,000 Stars — and Sandboxing Off by Default
OpenClaw is a highly popular open-source personal AI assistant with 385,400 GitHub stars and 81,018 forks. It integrates with multiple messaging platforms including WhatsApp, Telegram, Slack, Discord, and Signal. A critical security concern is that sandboxing is disabled by default, which could pose risks if the assistant executes untrusted code. The project demonstrates significant community adoption but highlights the importance of secure default configurations in AI agent frameworks.
skill md
385,000 stars. Sandboxing off by default. #shorts
OpenClaw is a popular open-source project with 385,400 GitHub stars that enables multi-platform messaging integration across WhatsApp, Telegram, Discord, and other services. The project has a significant security consideration: sandboxing is disabled by default, which allows arbitrary code execution. This design choice prioritizes flexibility but requires users to be aware of potential security implications when deploying the system.
skill md
Tool Use
Setup & Infrastructure
Today's Breakdown
Sources
Content Types
Difficulty
Want to save articles & build playbooks?
Create a free account to save articles to your library, build AI-generated implementation playbooks, and get content matched to your stack.
Or just get it by email
No account needed. Unsubscribe anytime.