Moonshot's Kimi Code, a TypeScript rewrite of its Python-based Kimi CLI, opens the entire coding-agent stack under an MIT license, shipping tuned for the open-weight K2.7-Code model on Hugging Face un…
A macro execution approach reduced Codex rounds by up to 84% in a 60-task benchmark, according to Tura maintainer and open-source implementer. Testing Codex CLI 0.144.1 with GPT-5.6-sol on 60 DeepSWE …
On 2026-07-21, three failures at Moonshot AI, Codex CLI, and Cursor exposed a common root cause: agent workloads now fan out into swarms of model calls, but the metering, quota, and log-rotation layer…
Security researchers at Pillar Security broke out of the sandboxes in four widely used AI coding agents — Cursor, OpenAI's Codex, Google's Gemini CLI and Antigravity — by having the agent write a file…
AceKit, a new installer from Ace Data Cloud, wires external capabilities like image generation, web search, and URL shortening into coding agents such as Claude Code, Codex CLI, and Cursor. The tool i…
A developer describes building a personal agent governance system called a 'harness' that survives context resets, inspired by a comment on a DEV Community post. The harness includes standing rules, c…
A study comparing six token-saving approaches for GPT-5.6 agents across ten real tasks found that none of the methods consistently reduced total tokens in both runs, with only the cheaper 5.6 Terra xh…
A developer open-sourced a macro execution layer for coding agents that reduces the number of model turns by executing routine workflow steps together. On a 60-task DeepSWE benchmark, the macro approa…
Apple has opened the coreai-models repository, which ships agent skills alongside on-device model export recipes and Swift runtime code, signaling that coding agents are first-class users of its Core …
PenEcho, an open-source shared canvas that integrates handwriting, equations, and diagrams with AI responses, has been released. The tool allows users to draw naturally on a 20,000 x 20,000 pixel canv…
OpenAI unveiled GPT-Red, its strongest automated safety red-teaming model, which successfully attacked GPT-5.1 in 84% of test cases compared to 13% for human red-teamers. The internal-only model, trai…
Macaz, a free and open-source interoperability tool, lets users route Claude Code and Codex CLI through any supported model provider while preserving each agent's local tools, permissions, and interfa…
A developer building an AI-powered code-review pipeline for Oracle PL/SQL patches uses a second AI from a different company to review changes before deployment. The secondary AI, OpenAI's Codex CLI, r…
AWS released OpenAI's GPT-5.6 on Amazon Bedrock. A developer shows how to configure the Codex CLI to use these models via the Bedrock API with existing AWS credentials, including a quick test command …
A developer spent months using AI coding agents to port the terminal e-book reader epy from Python to Rust, producing a fully AI-generated project called repy that adds features like inline terminal g…
Tura AI published benchmarks showing its agent harness achieves 80% token savings on long-horizon tasks, while plugins like RTK and Ponytail increase token usage by up to 13.20% and reduce pass rates.…
A developer has published a workaround for forcing Codex MultiAgent V1 on GPT-5.6 Sol and Terra, addressing a regression where model metadata overrides local feature flags. The workaround involves mod…
SpaceXAI has open-sourced Grok Build, the terminal-based AI coding agent behind its grok CLI, under the Apache 2.0 license on GitHub. The release includes the agent harness, TUI, CLI shell, and develo…
Tura, an open-source coding agent, reduces LLM turns by 80% while achieving a higher success rate on DeepSWE v1.1 tasks. In 60 sessions with GPT-5.6 SOL, Tura's Direct configuration used 83.5% fewer t…
A study by Bomly found that its MCP server raised the minimum fix rate for vulnerable dependencies from 14% to 98% on a 13-module Maven project with about 300 dependencies when used with Claude Code, …