Codex and Claude Code's /goal feature allows users to implement a project from a Product Requirements Document without manual oversight, replacing tedious back-and-forth prompts with autonomous execut…
A developer has released Chatcode, an open-source tool that provides a universal layer for persisted agentic sessions, allowing users to remotely control AI coding assistants like Claude Code and Code…
Walmart has developed an internal AI coding assistant called Code Puppy to avoid vendor lock-in with dominant AI providers like OpenAI and Anthropic. Created by distinguished engineer Mike Pfaffenberg…
Repowire, a new open-source tool, connects multiple coding agents like Claude Code and Codex across different repositories, allowing them to pass messages and coordinate tasks without manual copy-past…
Help Scout users can now manage their customer support workflows from the command line with Hscli, a new scriptable CLI tool designed for terminals, CI pipelines, and AI agents. The tool outputs JSON …
A developer discovered that using the same AI model to both write and review code led to undetected bugs, as the model lacked independent judgment and defended its own flawed interpretations. To addre…
OpenAI introduced a new ChatGPT security feature called Active sessions, allowing users to review and log out of individual or all active sessions across devices, now available for all account types. …
A developer open-sourced agmsg, a 500-line Bash and SQLite tool that enables direct messaging between CLI AI agents, and saw it grow from 5 to 320 GitHub stars in a week. The project, built to elimina…
Developer Simon Willison wired OpenAI's Codex into Claude Code as a consulting subagent to get adversarial reviews from a different model family, aiming to catch correlated blind spots in reasoning. T…
Hugging Face redesigned its `hf` command-line interface to optimize it for AI coding agents, which now account for significant traffic on the Hub. The new CLI auto-detects when an agent is driving it …
An AI agent built and launched its own storefront, registered as the first seller on the OpenTrust marketplace, and committed a tested bug fix to the platform's codebase — but earned $0 in revenue on …
A developer describes a multi-model agentic coding setup where Claude Code delegates implementation tasks to OpenAI's Codex in an isolated git worktree, then runs an approval loop requiring human revi…
A developer used GPT 5.5 in Codex to build a browser-based auto-battler game called Mini-Loot in under five minutes with a single prompt. The AI generated a complete, playable game using just three fi…
An independent audit of 6,762 Model Context Protocol (MCP) servers found that 42% earned an A or B grade while 38% scored D or F, with 13% of registry-listed servers unreachable. The audit, conducted …
Mutagen 0.4.0 introduces a Rust-based service extraction layer that decouples static dependency mapping from generative reasoning, reducing token consumption and latency in agentic workflows. The rele…
OpenAI is integrating its Codex agent directly into ChatGPT, eliminating the need for users to toggle between separate applications. The company aims to make Codex's automation and task-completion cap…
GitClear's analysis of 211 million lines of code reveals that refactoring is declining while duplicated code is increasing, a pattern the project attributes to agentic tech debt. A developer created a…
Visr, a new open-source tool, transcribes the entire trajectory of terminal sessions—including every command, output, retry, and fix—rather than just the final diff. The tool, installable via Homebrew…
Axiom, a seven-month-old startup, solved all 12 problems on the 2025 Putnam exam, scoring 12/12 within the time limit and outperforming both top undergraduates and other AI systems. The feat demonstra…
Gustavo Quenca, an iOS developer at KWAN, identified a recurring problem with AI coding assistants: developers waste time repeating the same context and instructions for each new interaction. To solve…