Claude Code Introduces Cross-Session Messaging for Agent Coordination
Anthropic has released cross-session messaging for Claude Code, allowing independent AI sessions to communicate and coordinate tasks across terminals.
Read more →
Anthropic Sets Auto Mode as Default for Claude Code
Anthropic is transitioning Claude Code to run in auto mode by default for Pro, Max, and Team users, citing improved developer productivity and safety metrics.
Read more →
OpenAI Introduces Codex Security Review for GitHub Pull Requests
OpenAI documentation details new security review features for Codex, including GitHub integration, GPT-5.6 support, and automated security checks.
Read more →
Meet Agent Plugins: A New Open Standard That Unifies Agent Skills and MCP Servers in a Shared Format
Industry leaders have launched Agent Plugins 1.0.0, a vendor-neutral standard for packaging portable AI agent components like skills and MCP servers.
Read more →
Prime Intellect Releases Prime Agent Self-Improving RLM Framework
Prime Intellect has launched Prime Agent, an open-source self-improving agent framework based on Recursive Language Models and Continual Harness architectures.
Read more →
Meta Introduces Muse Code Terminal Agent and Muse Spark 1.2 Model
Meta AI Research has released Muse Code, a terminal-based coding agent, alongside Muse Spark 1.2, a model optimized for repository-scale software engineering.
Read more →
HKUDS Releases DeepCode v2 Open-Source Coding Agent
HKUDS has released DeepCode v2, an open-source coding agent designed for real-world software engineering with continuous loop engineering and verified delivery.
Read more →OpenRouter Launches Ori Eval for Automated Model Benchmarking
OpenRouter has introduced Ori Eval, a framework for developers to evaluate LLMs using repository-specific prompts, tool assertions, and automated LLM judges.
Read more →
Cloudflare Releases @cloudflare/computer Agent Runtime Environment
Cloudflare has introduced an experimental agent runtime that orchestrates between Linux containers and Workers isolates using a shared virtual filesystem.
Read more →
Y Combinator Releases QM: An Open-Source Agent Harness With Isolated Sandboxes and Postgres Memory
Y Combinator has open-sourced QM, a multiplayer agent harness designed to provide isolated and collaborative AI assistants for startups.
Read more →