Full-text search across 58891 articles. Combine with topic and date filters; results sorted by relevance.
Pi pod, an open-source project hosted at github.com/pi-pod/pipod, lets users run pi coding agent sessions in isolated "pods" on their own servers rather than through hosted sandboxes or per-token agnostic platforms. The …
WebSensePro released WSP WordPress MCP, a free WordPress plugin that implements the Model Context Protocol so AI coding agents such as Claude Desktop, Cursor and Codex can connect directly to a WordPress site's native MC…
A developer released Harness Score, an open-source scanner that grades an AI coding harness from L0 to L4 by checking repository evidence such as context files, scoped rules, skills, hooks, sensors, and CI. The tool make…
Pi, a minimal coding agent created by Mario Zechner, shipped version 0.99.0 on September 29, 2026, adding Model Context Protocol support as a core feature after more than a year of publicly rejecting it. The team address…
A developer built TaskRoute, a local Codex plugin that delegates Python function implementation to Claude Code while Codex verifies the returned work. In a single sequential comparison on a synthetic Python task, the del…
A developer built a Claude Code workflow that combines Claude's visual processing with a local Stockfish engine to generate fully commented videos of Lichess games from board screenshots and audio notes, bypassing standa…
A developer benchmarked DeepSeek 4.1 Flash against the five-role Ship-Bench suite by wiring it into GitHub Copilot Desktop through OpenRouter, and the model averaged 94.5 with 5/5 phases passed, beating the prior Grok 4.…
NVIDIA's Infrastructure Controller (NICo) shipped with hard-coded credentials, tracked as CVE-2026-65113 with a CVSS score of 9.8, affecting versions 0 through 1.9 and allowing unauthenticated remote access to the contro…
A developer detailed a year-long effort to refine a Claude Code MCP setup, settling on four active servers across two machines: Context7 and CodeGraph on a work laptop, plus Discord and Chrome extension servers on a Mac …
GitHub Copilot CLI now supports whole codebase indexing (WCI) for C++ code intelligence, using the Microsoft C++ Language Server to build a persistent symbol index across an entire project, including files that aren't cu…
A developer building Ordewell, an open-source Apache-2.0 orchestrator that turns a single goal into a reviewed plan of coding-agent tasks, has detailed how its planner runs inside a read-only exploration envelope enforce…
Developers should read their own full diff line by line and run an AI review before requesting human review, according to a guidance post on AI-assisted coding. The post recommends fixing or rejecting each AI finding per…
The Rails Foundation reported on September 21st that GPT-6 Astra kept first place in its feature-development benchmark and raised its solve rate from 35% at medium reasoning effort to 53.3% at maximum effort, completing …
A developer guide lays out four levels of UI components — headless, design system (such as shadcn/ui), layout, and consumer — and five rules for keeping AI coding agents from producing sloppy interfaces. The rules direct…
GitHub made its improved Copilot code review experience generally available, adding a refreshed overview comment that groups findings into Open, Resolved since last review, and Previously missed, plus titles on each revi…
A 64-task SWE-bench Pro coding benchmark run by Deploymentsafety found that Anthropic's Fable 5.1 solved 51 of 64 tasks at roughly €2.4 per solved task, while OpenAI's GPT-6 Astra solved 34 of 64 at about €1.6 per solved…
Arcjet launched agent runtime security on September 17, a product from founder David Mytton that observes, enforces and audits AI agent actions before they execute, available now with a free 15-day trial. The product ing…
Anthropic launched a redesigned Projects feature in Claude Code in beta, turning a project into a single coordinator conversation that spawns parallel cloud sessions called threads, each running on its own branch and rep…
A Microsoft developer's evaluation of GPT-5.6 Luna's knowledge of Dev Proxy versions was invalidated because the coding agent located a local Dev Proxy installation and source checkout on the host machine despite web acc…
Archkeel, a tool from rapiddweller, checks architecture boundaries and declared changes in AI-assisted code by comparing an accepted commit with a candidate and verifying the candidate matches an expectation published be…