Tag
An open-source repository called 'The Agency' with 147 specialized AI agents across 12 divisions has rapidly gained 50K GitHub stars, representing a structured approach to AI-assisted development.
Google's Agents CLI provides a unified tool for scaffolding, evaluating, and deploying AI agents, addressing the fragmented workflow in agentic engineering. The article walks through building a RAG agent using the CLI, showcasing its integration with coding agents and ADK patterns.
This article explores the concept of using a text editor as a user interface for command-line programs, highlighting how it leverages the editor's full editing capabilities while remaining simple to implement, with examples like crontab -e and a custom image gallery tool.
An open-source agent orchestration tool that enables one-command installation for Claude Code and Codex, allowing users to create agent teams with playbooks and network recall of agents built by other developers.
OpenRouter introduces MCP integration, providing live model intelligence for agents to select and price models in real-time, simplifying long-running agent development.
Suggests using Codex CLI to learn how to run LLMs locally.
Minimus has announced that its hardened container images are now available for free, with a free tier offering images as-is without support. Paid subscriptions provide prioritized security updates and support.
The author shares lessons from designing a testing framework in Guile, focusing on how adding context to test definitions makes tests more reusable and improves developer experience.
Crabbox is a new tool that gives AI coding agents isolated cloud environments to test and verify PRs, enabling them to work in parallel without conflicts and reducing the review bottleneck.
Modal discusses the importance of managing the entire lifecycle of sandbox systems beyond initial boot, highlighting tools like .wait_until_ready().
Cloudflare announced temporary accounts that let developers deploy Workers to ephemeral projects without sign-up, lasting 60 minutes and optionally claimable for permanence, aimed at AI agents but useful broadly.
This article from Chrome Developers details the agentic browsing category in Lighthouse, which evaluates how ready websites are to interact with AI agents. The category focuses on data collection and providing actionable signals rather than a traditional numerical score, and includes audits for WebMCP, accessibility, and content stability.
Magnitude is a coding agent that runs entirely on open models, costing 60% less than Claude Code with no drop in performance. It is available via npm as a CLI tool.
A blog post advocating for package managers to support global hooks as a more secure and flexible alternative to current package security measures like registries or shell wrappers.
LangChain introduces On-Call Copilot, a new agent template in LangSmith Fleet that triages alerts, investigates root causes across code and traces, manages tickets, and routes incidents to the right channels while continuously learning from runbooks and escalation rules.
Epic Games announces Lore, an open-source version control system designed for scalability and optimized for projects combining code with large binary assets, catering to developers and artists.
A detailed technical article explaining how to build an automated agent for domain operations using Porkbun, Cloudflare, and Wrangler, covering domain registration, DNS migration, and static site deployment with code examples.
Brevio provides 184 free browser-based tools for PDF, image, development, and AI tasks, all without requiring uploads or signup.
An Anthropic engineer explains how to use Claude Code in a loop to autonomously write code and manage PRs, allowing developers to step away from the keyboard entirely.
Factory 2.0 connects AI agents to the entire software workflow, managing a feedback loop from tickets to incidents, treating every signal as training data.