OpenAI's internal culture is characterized by a 'Doacracy' where responsibility is held by those who do the work, leading to a low-bias, high-variance direction of progress, according to a former Open…
A developer using OpenCode switched from LiteLLM to Bifrost, a single Go binary with a local SQLite config store, to route requests across 9 providers with automatic fallbacks, eliminating interruptio…
Cua, an open-source project for Computer-Use Agents, shipped an update providing infrastructure to train and evaluate AI agents that control full desktops on macOS, Linux, and Windows without stealing…
A developer explains that the key to effective AI agents is context engineering rather than prompt engineering, detailing the observe-think-act loop and the importance of setting up context, memory, a…
Make This Better launched an AI-powered feedback widget that captures screenshots, DOM snapshots, and console logs when users report issues, then uses AI to clarify and extract the underlying need, an…
A six-run benchmark by an independent developer found that Codex skills saved tokens on a medium 2048 game build but lost on a small fix, with GPT-5.6-sol runs showing the same engineering-loop skill …
Frontis AI released Frontis-MA1, a 35B open-weights model, along with the full OpenMLE stack, claiming it improves Medal Average on MLE-Bench Lite from 39.39% to 60.61% with OpenMLE-Evo and to 71.21% …
Entire, the coding agent session capture platform, expanded its external agent plugin support to include Kilo Code and Oh My Pi, enabling users to capture sessions as checkpoints with summaries, file …
Vipps engineer Eivind Barstad Waaler argues that a dedicated AI platform is justified only when the same access, cost, compliance, and observability problems recur across teams, and proposes the small…
Vibsync engineers report that while AI coding agents reliably boost individual developer speed, team throughput often stagnates due to coordination costs such as duplicated discovery, decision drift, …
Y Combinator's open-source QM agent runtime, version 0.1.4, has drawn 6,600 GitHub stars, 700 forks, 68 pull requests, and 14 open issues within two days of publication, according to a code review by …
The GitHub project 'goutoujunshi' has gained nearly 1,500 stars for its Python-based approach to combining emotional intelligence with relationship advice. The tool analyzes emotions and relational dy…
Kota, an open-source tool that enables AI agent CLIs to collaborate in a shared workspace, was released by its creator after months of personal use. It supports Codex, Claude Code, Pi, OpenCode, Gemin…
Open Interpreter, a fork of OpenAI's Codex, now emulates the harnesses of Claude Code and Kimi for low-cost models, enabling AI agents to read, edit, and render Office documents through a single binar…
A 16-year-old developer named Aarav has released Sprocket, an open-source AI agent for hardware and software development that can autonomously purchase items from any website, including hardware parts…
Hannes M. (hmans) open-sourced Chatto, a self-hostable team and group chat app, and revealed that he has not written a single line of code since February 2026, relying instead on AI coding agents. He …
NomaDamas released k-skill, an MIT-licensed collection of 100+ agent skills for Claude Code, Codex, and OpenCode that enable AI agents to interact with Korean-specific services such as SRT/KTX train b…
A developer has released an open-source Codex skill called Adaptive Model Router that dynamically assigns subtasks to the most cost-effective AI model, rather than always using the strongest or cheape…
DeepSeek's V4-Flash model exited preview and is now available in public beta, with benchmark scores surpassing V4-Pro-Preview and native agent support, according to a tweet from DeepSeek. The author d…
A solo AI consultant in Slovakia has adopted a high-risk workflow that removes human approval gates from AI coding agents, replacing them with automated checks. The developer uses Claude Code with the…