Top Story
[Release] anthropics/claude-code v2.1.236: v2.1.236
Claude Code v2.1.236 introduces the `ANTHROPIC_DEFAULT_MODEL` environment variable for persistent model selection, adds cross-session idle notifications via `notify_when_idle`, and enhances sandbox security with precedence-based wildcard read-deny rules on macOS. The release fixes 20+ bugs affecting clipboard operations, fullscreen rendering, subprocess handling, and terminal UI consistency, while improving auto mode classification, startup performance, and accessibility with screen reader support.
- Set default model for new sessions with `ANTHROPIC_DEFAULT_MODEL` env var; `/model` picker still overrides and persists across restarts
- Use `notify_when_idle` in cross-session `SendMessage` to request another Claude Code session to send a notice when idle (macOS/Linux, opt-in, no polling)
- Wildcard read-deny sandbox rules (e.g., `**/.env`) now take precedence inside allowed regions on macOS and can't be bypassed by file renaming
- +7 more key points...
By Topic
Agent Teams
See all 11 →[Release] crewaiInc/crewAI 1.15.17: 1.15.17
crewAI v1.15.17 introduces declarative conversational flows with opt-in conversational mode, improves tool handling with AMP slug support and oversized message chunking, and fixes critical bugs including MCP server configuration, agent scope closure, tool error attribution, and OpenAI Responses API compatibility. The release enhances security with SSRF checks per redirect hop and resolves native tool call issues.
joaomdmoura
Watch This To Fix Your AI Agents (Skills, Plugins)
This video discusses fixing AI agents through skills and plugins implementation. The content covers strategies for enhancing AI agent capabilities, likely including how to properly configure and integrate skills/plugins for better performance. The discussion involves insights from an AI expert on optimizing agent functionality and addressing common issues in AI agent development.
Greg Isenberg
AutoGen v0.4.2 bổ sung Docker Sandbox tự động: Cách ly Agent hoàn toàn khỏi hệ thống Host 👉 AutoGe
AutoGen v0.4.2 introduces automatic Docker Sandbox functionality that provides complete isolation of AI agents from the host system. This feature enhances security by running agents in containerized environments, preventing direct access to host resources. The update enables safer execution of agent code while maintaining full functionality and control over the sandboxed environment.
AI Cho Người Bận
Integrations
See all 5 →[Release] langchain-ai/langchain langchain-anthropic==1.6.1: langchain-anthropic==1.6.1
langchain-anthropic version 1.6.1 was released with a critical bug fix that filters invalid tool calls from v1 content. This patch addresses issues with tool call handling in the Anthropic integration for LangChain, improving reliability when processing tool invocations. The release maintains backward compatibility while resolving edge cases in content processing.
github-actions[bot]
[Release] langchain-ai/langchain langchain-anthropic==1.6.0: langchain-anthropic==1.6.0
langchain-anthropic version 1.6.0 introduces standard model exception types for improved error handling across the LangChain framework. The release includes infrastructure improvements for LangSmith gateway support in CI/CD pipelines and fixes a grep search scope issue in the Anthropic integration. This update enhances reliability and consistency in exception handling for Anthropic-based LangChain applications.
github-actions[bot]
[Release] langchain-ai/langchain langchain-openai==1.6.0: langchain-openai==1.6.0
langchain-openai version 1.6.0 introduces standard model exception types for improved error handling across the core framework. The release includes a fix that raises clear, informative errors when unexpected response types are encountered in the `_create_chat_result` method. These changes enhance debugging and error transparency for OpenAI integration users.
github-actions[bot]
Tool Use
[Release] anthropics/claude-code v2.1.237: v2.1.237
Claude Code v2.1.237 introduces two key improvements: a fix for prompt caching compatibility with LLM gateways and custom base URLs, and a new "Concise" output style that prioritizes results over preamble. The Concise mode maintains thorough work while reducing narrative overhead, available in the Output style configuration.
ashwin-ant
The Viral AI Assistant Started as a 1-Hour Hack
Peter Steinberger shares the origin story of OpenClaw, a viral open-source AI agent that started as a quick 1-hour hack. The project demonstrates how rapid prototyping and scrappy development can lead to successful AI tools. The talk covers the initial concept, early implementation decisions, and how the project evolved from a simple experiment into a widely-adopted open-source solution.
TECHSPRESSO
MCP Servers
Multi-Agent Systems
Memory & Identity
Security
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.