Local models such as Qwen 3.6 and Gemma 4 are close to being useful for Kotlin Multiplatform code generation but still fall short for many developers, according to Mark Murphy's experiments. Murphy su…
Vercel and Herdr have launched a plugin that lets terminal coding agents like Claude Code, Codex, and OpenCode run in isolated Vercel Sandboxes, orchestrated from Herdr's tmux-style manager. The plugi…
Netlify now supports open-weight AI models including DeepSeek, Qwen, GLM, and Kimi through partnerships with OpenRouter and OpenCode, giving every customer full model freedom via Agent Runners and AI …
Flare, the error-tracking service for Laravel, now supports OAuth for its MCP server, CLI, and REST API, replacing API tokens with browser-based consent and granular permissions. MCP clients like Clau…
Ocean, a new tool from Mosaic Inc., centralizes AI agent sessions from Claude Code, Codex, OpenCode, Hermes, Pi, and other harnesses into a searchable platform, enabling teams to recover context behin…
Cloudflare introduced WriteGuard, a policy engine providing fine-grained controls for Model Context Protocol (MCP) servers, now in private beta for Cloudflare MCP server portals. The tool addresses ri…
DeepSeek V4 Flash ranked first in OpenRouter's weekly model-usage ranking for July 27 to Aug. 2, processing 7.22 trillion tokens on the multi-model aggregation platform. On Aug. 1, the model processed…
A master's degree student in Business Administration reports spending roughly $55/month on AI subscriptions including ChatGPT Plus ($20/month), Consensus ($9/month with student discount), Google AI Pr…
Cloudflare's post on orchestrating AI code review across thousands of merge requests highlights JSONL as the response surface for unreliable, long-running agent processes, where each line is a complet…
Meta's Muse Spark 1.2 is now available on Vercel AI Gateway, featuring improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows. The model is desi…
DeepSeek's V4 Flash and Qwen-3.8-Max have rewritten the cost equation for large language models, with Nous Research offering DSV4 Flash at a 90% discount and OpenCode reporting 8 trillion tokens proce…
Tikal released ADLC Team Skills, an open-source team layer for the Twelve-Factor Agentic SDLC, designed to bring team coding standards to AI coding agents such as Claude Code, Codex, OpenCode, Cursor,…
Debarshi Basak released Clawx, an open-source package manager that treats agent-driven tasks as installable packages, where each package is a Markdown file with YAML metadata that becomes the system p…
Anthropic's Claude Code subagents provide isolated context windows and restricted tool allowlists to handle noisy, parallelizable tasks, keeping main conversation context clean. The feature is distinc…
Shrivara has released TokenBar, a free macOS menu bar app that tracks daily AI usage across Claude, Codex, OpenCode, and pi, displaying spend, tokens, and cache hit rates with odometer-style updates. …
A developer's guide explains how spec-driven development can make AI coding agents like Claude Code, OpenCode, and Cursor Agent produce production-quality code by providing structured specifications i…
Y Combinator has open-sourced QM (quartermaster), a multiplayer agent harness for work that runs in Slack and on the web, under the MIT license. The harness, used internally by YC across accounting, l…
Ante, the agent harness developed by the company behind this test, passed all 10 Terminal-Bench 2.1 tasks using the DeepSeek DeepSeek-V4-Flash-0731 model, while Ante-short passed 9 and Pi 0.73.1, 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…
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 …