OpenAI's preview release of the GPT-5.6 series introduces three distinct tiers—Sol, Terra, and Luna—signaling the end of single-model API integration. Developers must now build intelligent routing lay…
Voyfai has deployed an autonomous AI agent that detects production issues, writes fixes, and opens pull requests without human initiation. The system operates in five stages from observability to revi…
OpenAI is investigating Codex quota depletion after Pro plan users exhausted weekly limits in one to two days, revealing that AI coding agent adoption is outpacing capacity forecasts. Engineering lead…
Meta has restricted its engineers from using Anthropic's Claude Code and OpenAI's Codex AI coding tools to protect proprietary AI training data and internal codebases from exposure. The policy, effect…
Talon, an open-source agentic AI harness, launched with support for Telegram, Discord, Microsoft Teams, and terminal, offering pluggable backends including Claude Agent SDK, Kilo, OpenCode, Codex, and…
OpenAI set up a 'warroom' to investigate reports that its Codex coding agent is depleting user usage limits faster than expected, with the company attributing the issue to abuse and fraud prevention s…
Brain.md, an open standard for persistent project memory, allows coding agents to store and retrieve durable knowledge as plain Markdown files in a repository, ensuring decisions and constraints outli…
VibeRaven, a new open-source tool for AI coding agents, provides production workflows that enforce evidence-based task completion, separating code fixes from provider dashboard work and requiring appr…
OpenAI is investigating issues with Codex usage limits after some users experienced faster usage drain. The Codex team spent Sunday in a war room analyzing logs, and OpenAI has issued a full reset of …
OpenAI's head of Codex, Andrew Ambrosino, said AI still struggles with creative design because taste and judgment are harder to measure than code. Figma CEO Dylan Field echoed that AI models produce a…
OpenAI has begun rolling out GPT-5.6 series models in limited preview to trusted partners via API and Codex, with models Sol, Terra, and Luna. The rollout is coordinated with the U.S. government befor…
A developer argues that coding agents need auditable denylists to enforce file access boundaries, rather than relying on prompts to avoid sensitive files. The developer emphasizes that access control …
Developer tooling company Warp is betting that engineering leaders will not standardize on a single coding agent, but instead use multiple agents through a unified control plane. Warp's Oz platform no…
A developer released Nearest-Neighbor, a dating app for AI agents that lets autonomous agents create profiles, swipe, match, and message each other. The tool ships as a plugin for Claude Code, Codex, …
NewMax launched a desktop AI agent that prioritizes local execution and privacy, allowing users to run workflows, automate browser tasks, and process files without sending sensitive data to the cloud.…
Smolagents, a Python library from Hugging Face for building AI agents, prioritizes code-based actions over JSON tool calls, enabling loops, conditionals, and tool composition. However, this design shi…
A new open-source meta-skill called 'self-learning' enables AI coding agents like Claude Code and Cursor to automatically capture and persist reusable workflows, commands, and project knowledge across…
Two funding rounds in one week signal that agent evaluation and simulation have become a market category. Patronus AI closed a $50 million round to build digital worlds for stress-testing AI agents, w…
Claude Code's plan mode splits multi-file work into a planning step and an execution step, requiring user approval before any code changes. The author uses it for changes spanning three or more files …
Claude's TUI coding agent allows users to configure its status line by executing arbitrary commands, enabling custom displays like Git branch and claw count. Codex's status line is limited to a fixed …