OpenCode, an open-source AI coding harness, has grown from 650,000 to nearly 8 million monthly active users in months. Co-founder Dax Raad discusses how the company turned Anthropic's blocking of Clau…
Conductor, a multi-agent IDE startup founded by former Vercel employee Charlie Holtz, launched Cloud Workspaces built on Vercel Sandboxes to enable developers to run multiple parallel coding agents re…
OpenAI's Codex /goal command transforms AI from a turn-based assistant into an autonomous agent capable of working for hours on complex tasks without constant prompting. In a 30-minute episode, Claire…
An engineer who wired eight MCP servers into a single Claude agent discovered that three pairs of tools silently collided due to the protocol's lack of built-in namespace support. The collisions cause…
Wolf has launched a new tool that transforms Slack threads into collaborative workspaces where human team members and AI agents can interact within the same chat. The platform allows agents to create …
A developer released a demo of a self-managing codebase using long-horizon agents that autonomously triages errors, upgrades libraries, and rolls back regressions. The system runs three Anthropic Mana…
This article explains how large language models (LLMs) like ChatGPT decide which brands to mention, using a technical process called Retrieval-Augmented Generation (RAG). The system first retrieves re…
The article describes a developer's creation of a premium, dark-mode portfolio template built with React and Tailwind v4, designed to achieve high performance and a minimalist aesthetic similar to com…
The author canceled their $20 Claude Cowork subscription after switching to OpenWork, an open-source, free AI coding tool that handled real tasks without requiring configuration. OpenWork impressed th…
The article describes a practical implementation of a multi-agent AI architecture where seven different AI models (including Claude Opus, MiniMax, Hermes, Gemini, and Groq Llama) work together autonom…
The article explains that software products with fewer features often win in crowded markets because they focus on delivering a specific user experience or "fantasy," such as competence, control, or b…
Materialize has been using LLM-based coding agents since February 2026 to find bugs in existing code and open pull requests, coinciding with the release of Anthropic's Opus 4.6. The system scans pull …
First-generation MCP servers, which wrapped REST APIs for tools like Jira and GitHub, caused excessive token usage and context bloat. It introduces the "ultra-mcp-toolkit," which uses strategies like …
A new workspace platform is integrating 80% of the functionality from seven separate tools — including Jira, Slack, Notion, Figma, and coding environments — into a single graph-based system to elimina…
Productivity and infrastructure companies must now design for AI agents as their primary users, not humans, as agents increasingly handle tasks that people once performed manually. Traditional metrics…
A developer built a tool called `/orc` to solve "context rot" in AI coding agents, where long conversations caused models to forget rules and produce worse results. The tool splits the coding workflow…
Nimbalyst has launched a unified workspace that integrates Obsidian, Linear, Terminal, Codex app, and Conductor into a single environment for agentic engineering. The platform eliminates context switc…
Anthropic is now valued at $1-1.2 trillion after reporting 80x annualized growth in Q1, making it the 11th to 15th most valuable company in the world and overtaking OpenAI in valuation. Meanwhile, Blo…
Glama lists over 22,000 MCP servers, PulseMCP tracks 14,000+, and mcp.so and other registries add thousands more, but a handful of well-chosen servers composed thoughtfully outperform a full stack for…
Autonomous multi-agent workflow for OpenCode that takes a Linear issue ID and automatically plans, implements, tests, and opens a draft pull request without user interaction. The workflow uses five sp…