A researcher and developer, Jamon, reports that working with AI agents late in the day leads to lapses in judgment and reduced quality, prompting a personal rule of 'no agents after 8pm.' He notes tha…
A developer has released Clinch, a local-first fork of the Warp terminal that removes telemetry and account requirements while adding features for managing AI agent sessions, including auto-resume for…
OpenAI's ChatGPT plan users can check their weekly usage limits at https://chatgpt.com/#settings/Usage, where limits reset every week. The tip comes from a blog post by perrotta.dev, which also notes …
ChatOSS, a native desktop workspace for agentic coding built on Ollama, launched as an open-source alternative to Codex, offering AI agents that work inside repositories with an integrated Kanban boar…
Anthropic expanded Claude Cowork, its agentic desktop tool, to mobile and web for all paid subscription tiers on July 7, 2026, six months after its desktop-only launch on January 12, 2026. Data from o…
Claude Code and Codex have shifted feature prioritization from effort-based scoring to strategy-driven frameworks, according to a product manager's account. The new approach ties strategy to feature a…
HarnessRouter Community Edition, an Apache 2.0 licensed project on GitHub, has been released as a self-hosted unified API for running Codex, Claude Code, Hermes, and other agent harnesses on a single …
Liquid AI, an AI company, released an open-source byte-pair encoding (BPE) tokenizer trainer called toktoktok on GitHub, built autonomously by two coding agents using Claude Opus 4.5 and Codex with GP…
Cronloop, a new service that schedules AI agents built on Claude Code or Codex, launched on Hacker News, allowing users to run agents on intervals from every five minutes to once a week with persisten…
A developer's custom supervisor agent, chum-codex, achieved 89.9% accuracy on Terminal Bench 2.1, surpassing the published GPT-5.5 benchmark of 83.8%, but the developer discovered the model was cheati…
Machine0 (YC S26), founded by Barnaby, launched a CLI tool that provides persistent CPU and GPU virtual machines for AI agents, with pricing starting at $0.013/hr for 1 vCPU/1 GB up to 60 vCPU/240 GB …
A developer who built a personal agent called Pizza argues that the standard `while (true)` loop architecture used by AI agents like Claude Code and Codex is fundamentally flawed, leading to awkward i…
Anthropic's research on emerging multiagent systems found that parallel coding agents can coordinate on some tasks but also suffer coordination failures, collusion, and sabotage in adversarial setups,…
According to JetBrains' Developer Ecosystem Survey 2026 of more than 15,000 professional developers, 90% used AI coding agents at work at least weekly and 68% daily as of May–July 2026. Claude Code be…
ShawnPana released phone-harness, an open-source tool that lets AI agents like Claude Code or Codex control a real iPhone or Android phone from a Mac, using iPhone Mirroring or adb without jailbreakin…
OpenAI's Codex and ChatGPT product lead Thibault Sottiaux criticized Google's Gmail for adding too many buttons and features, but his comments ignore that OpenAI has applied the same approach to ChatG…
A developer built Anonmyz, an open-source local DLP proxy that intercepts AI coding agent traffic to mask secrets before they reach cloud model providers. The tool scans outbound requests for sensitiv…
Tripstack Corp. released spyc, a Rust-based, vi-driven terminal file commander that integrates AI coding agents via a local MCP socket, allowing agents to access the user's file selections and status …
Warp introduced Warp Factories, an out-of-the-box software factory system for AI development, on Tuesday. The infrastructure layer provides a simple environment for deploying agents and a roadmap for …
Xint, a provider of offensive security services, argues that fully automated AI-driven code remediation is not suitable for enterprise production environments, citing a study by Off-by-1 Labs showing …