A new Mac app, AI First Virtual Linux Desktop, lets AI agents run as root in a hardware-sandboxed Linux virtual machine, with no permission prompts, and includes preinstalled Claude Code, Codex, Gemin…
Bullet, a coding agent launched from YC's Summer 2026 batch, claims 95.8% on SWE-bench Verified at 119 seconds per task, but its founders concede the benchmark is saturated and the speed pitch is the …
Bernstein, a deterministic orchestrator for CLI coding agents, is now in beta, enabling users to run 44 CLI coding agents from a single scheduler. Developed by sipyourdrink-ltd, Bernstein coordinates …
Developer Nicolas Dabene outlines a method for finding, verifying, and adapting reusable skills for AI coding agents, emphasizing that skills are workflows rather than magic knowledge pills. He advise…
A developer has released Codex Pulse, an open-source native macOS app that displays Codex and optional Claude Web quota windows in the menu bar, desktop widget, and a unified dashboard. The tool is re…
Sealos has released sealos-skills, an AI agent skills bundle that enables deploying projects, provisioning databases, and object storage with a single command, compatible with Claude Code, Gemini CLI,…
Upstream, a Paris-based email client that integrates AI to manage inboxes, went generally available on June 3, 2026, backed by a $3M pre-seed from Y Combinator, Connect Ventures, Roosh Ventures, and o…
Coding agents Claude Code and Codex consistently over-predict their own wall-clock runtime, according to research conducted as part of MATS 10 with Maksym Andriushchenko. The study introduced AgentTim…
A developer released a prompt for Claude and Codex agents that automatically verifies Row Level Security (RLS) policies on every table in a Supabase project, aiming to help developers check database s…
Entire, a developer tooling company, introduced a workflow that lets developers review AI-generated code with multiple AI agents from different model families, such as using Codex to build and Claude …
OpenAI launched Computer History for ChatGPT on macOS this week, a feature that logs users' interactions with websites and applications to build personalized context, available to Pro, Business, and E…
DeepSeek released an early version of its open source agent harness, DeepSeek Harness, built on the Cordis meta-framework, which treats models, tools, skills, sessions, sandboxes, filesystems, loops, …
OpenAI has released Codex in the ChatGPT desktop app for Linux in preview, a move that received 461 upvotes on Hacker News. Developers are already building CLI tools to control Codex alongside Claude,…
Multiple tools for managing parallel AI agents reached production status, including Taurus Agents for multi-agent hierarchies, Neal for Claude and Codex coordination, Agentic Ship as an open-source Lo…
OpenAI and Anthropic are pursuing divergent market strategies, with Anthropic focusing on enterprise workflows and operational efficiency akin to Palantir, while OpenAI targets consumer personal assis…
Niteshift.dev launched a full-stack cloud platform for coding agents that configures entire application stacks, including services, databases, auth, workers, and seeded data, by reading docs, scripts,…
Developer Matt Pocock shares five agent skills he uses daily to enhance AI coding assistants like Codex, covering research, design review, React best practices, code simplification, and end-to-end tes…
An engineer from tamiz.pro argues that the trust problem in AI agents stems from a structural mismatch between traditional software engineering and autonomous code generation, and proposes five archit…
DeepSeek has released DeepSeek-V4-Pro-0813, an advanced AI model with enhanced agent capabilities, now available via its website, mobile app, and API. The model scored 62.7 on the DeepSWE benchmark, u…
MongoDB, Inc. (NASDAQ: MDB) announced at MongoDB.local Build Fest the availability of MongoDB Atlas Managed MCP Server, a fully hosted service that connects coding agents to MongoDB Atlas without addi…