AI coding agents such as Claude Code and Codex still require developers to act as the feedback loop, correcting generated code one iteration at a time because of missing project context, ambiguous spe…
A developer documented a modular setup for running the affaan-m/ECC agent harness inside Cursor, symlinking only common and TypeScript rules into .cursor/rules/ and registering ECC's MCP servers via .…
Developer XiaoDuoYa released Codex with ChatGPT, an open-source bridge that connects a ChatGPT web subscription to a local Codex terminal session via a read-only Model Context Protocol (MCP) server. T…
Rubric's team published a numbered list of agent design patterns drawn from building agents internally and for clients including Graphite and Albertsons, recommending system prompts stay under 5,000 t…
A developer built a browser-playable recreation of Halo 3's Guardian map as a personal website, using OpenAI's Codex with Astra to generate 20,552 lines of TypeScript across 118 files at a cost of 973…
DevRecap, a tool published on GitHub, reconstructs developer work history from Codex, Claude Code, and Git logs to automatically generate standups, recaps, and work reports. According to GitHub, DevRe…
Skillsynch released txcript, a Rust library and CLI tool that converts and transfers agent sessions between Claude Code, Codex, OpenCode, and Cursor, preserving messages, reasoning, and tool history w…
A developer has launched Radio, a provider-agnostic communication layer that lets AI agents from different vendors and machines join a single shared conversation via a URL. Built as a core primitive o…
GPT-6 Astra saturated ArXivMath at 94% and BrokenArXiv at 96%, prompting benchmark operators to revise both pipelines so that GPT-6 Astra now scores 88% on ArXivMath August and 81% on BrokenArXiv Augu…
A developer tested OpenAI's Codex and GitHub Copilot for building proof-of-concept applications, finding Codex produced a working React PDF viewer and extraction tool with iterative prompting while Gi…
Microsoft released Visual Studio Code 1.138 on September 16, 2026, adding the ability to run agent sessions inside local Dev Containers, expanded Codex support in the agent host, and a preview session…
A developer who has extensively used AI coding tools including Codex, Cursor, Claude Code, Copilot, and GLM reports that despite roughly 5x productivity gains, human oversight remains essential. The e…
A developer's audit of pi's session logs against OpenRouter's generation API found a supposedly cheap DeepSeek V4.1 Flash setup paying about three times what it should, because OpenRouter's default Au…
Google released Android Bench 2.0, adding long-horizon tasks (LHT) and agentic evaluation to its benchmark for large language models assisting Android developers. The highest pass rate on the new mult…
Diogo Almeida, an ex-OpenAI researcher who says his work became the research behind ChatGPT, launched TypeSafe AI's first model, Jev, in early access on Tuesday, describing it as a decision model that…
GreyNoise reported that a likely Russian-speaking threat actor used an AI agent swarm to compromise 440 PaperCut NG/MF print servers across 395 organizations in 48 countries, exploiting CVE-2026-81578…
Marco released Agentbox, an MIT-licensed CLI that copies a project, skills, and subscription OAuth into Docker or cloud sandboxes so multiple coding agents such as Claude, Codex, and PI can run in par…
Wenlan launched as a local AI knowledge-base daemon that builds and maintains source-backed wiki pages without overwriting user edits, available for download on macOS Apple Silicon, Windows x64, and L…
Pyor released /pyor:review, a Claude Code plugin and cross-agent skill that opens working changes as a local pre-PR review in the Pyor desktop app before a PR exists. The tool runs a panel of fresh su…
Google has expanded internal access to Anthropic's Claude Opus 5 for coding through its Antigravity development platform, while keeping Gemini as its primary and foundational model for internal develo…