Antigma Labs released Ante, a self-contained coding agent in a single ~15MB Rust binary that runs offline with zero runtime dependencies, achieving 82.7% on Terminal-Bench 2.1 (368/445 trials) using D…
A developer measured the fixed token overhead of spawning subagents in Claude Code and found it to be roughly 436,000 tokens per agent before any useful work, dwarfing the payload cost. In a compariso…
Nutanix launched an open-source model context protocol (MCP) server for its Nutanix Cloud Platform (NCP) that uses the Prism v4 API to let AI assistants like GitHub Copilot, Claude Code, and Cursor tr…
A developer built an orchestrator for Claude Code that routes tasks to optimal models based on task shape rather than perceived difficulty, using markdown-based policy files and an append-only ledger.…
A student developer shares strategies for minimizing AI coding agent costs, emphasizing well-scoped prompts, frugal model selection, and using free-tier models to compress prompts before sending them …
Starting August 14, Anthropic's Claude Code will make auto mode the default for Pro, Max, and Team plans, using a classifier to review actions instead of prompting on every tool call, with no token ch…
Docker Inc. launched Docker Sandboxes, a new product that isolates AI coding agents in microVMs with their own kernels and private Docker daemons, rather than containers, to make bypass-mode agents sa…
Anthropic's Claude Code performs best when projects are set up with a CLAUDE.md contract, a nine-step per-feature development loop, separate review models, and living Markdown boards, according to a w…
Airbnb CEO Brian Chesky publicly confirmed for the first time that he is working on an AI lab, though he declined to provide details. The company reported Q2 2026 revenue of $3.6 billion, up 17% year …
Neo4j's Graph ML and GenAI Research team introduced the Meta Knowledge Graph (MKG), a graph-structured context layer that supplies AI agents with operational metadata—semantic descriptions of enterpri…
A developer has released an open-source, 100% native Swift harness for macOS, claiming it is the first non-Electron alternative to tools like Cline, Codex, and Claude Code. The project, licensed under…
Security researchers disclosed a CVSS 10.0 vulnerability in AI coding agents from three vendors, including Claude Code, Gemini CLI, and OpenAI Codex, stemming from a time-of-check-to-time-of-use (TOCT…
Phinq, an open source runtime governance layer for AI agents, intercepts every agent tool call, classifies it by risk, holds irreversible actions for human approval, and records each decision in a tam…
A former Privacy International staffer replaced dozens of mobile apps with private Progressive Web Apps (PWAs) built using Anthropic's Claude Code, citing 20 years of privacy law violations by mobile …
Vendict, a third-party risk management startup, rebuilt its software development lifecycle around the thesis that the SDLC itself is the context for AI agents, achieving reliable agent participation i…
A senior software engineer in Silicon Valley who initially praised Anthropic's Claude Code for boosting his productivity now reports that AI-generated code caused his product to crash twice, leading h…
Docker launched Sandboxes, disposable microVM environments for AI coding agents, which reached the top of Hacker News with 285 points. The product uses libkrun-based microVMs with isolated kernels and…
AI educator Grace Clarke, who taught herself Claude Code and now runs her service business on custom tools built with Claude, shares her methods for non-technical users in a podcast episode, including…
Anthropic's Claude Code can be organized into a file-based workspace that improves long-term productivity for product managers, according to a guide published on the company's engineering blog. The st…
Databricks Cost Optimizer, a read-only FinOps toolkit and Agent Skill for Codex and Claude Code, identifies cost spikes and applies only approved optimizations, achieving a 68.5% reduction in daily ef…