Full-text search across 8053 articles. Combine with topic and date filters; results sorted by relevance.
SkillGild has released open-source TypeScript, Python and Go SDKs under the MIT license that let developers search its skill catalog, run hosted skills and drive hybrid skill sessions from their own code, scripts, backen…
Fission AI maintains OpenSpec, an MIT-licensed open-source tool that makes AI coding agents such as Claude Code and Codex write proposals, requirement specs, design docs and task lists before implementing code. The tool,…
A software studio founder detailed a multi-model AI coding workflow that assigns work to tiers by error cost, reserving Tier A models such as Claude Opus and GPT Sol for foundational decisions like PRDs, database schemas…
SpaceXAI's Grok Bot added manager controls for shared Team Bots and voice calls in releases dated September 30th, per the product's official changelog, which lists the features under versions 0.64.0 and 0.65.0 rather tha…
Reflection announced Beam, a text-only 501B-total / 23B-active mixture-of-experts model for coding, agentic and scientific work, trained from scratch on 23.8T pretraining tokens with full weights under Apache 2.0 due thi…
A developer has released T-Zero Context Architect V3, an open-source tool that uses AST-based static analysis to strip function implementations from a codebase while preserving signatures, docstrings, decorators and impo…
Vercel's January 2026 agent evals found that a compressed docs index in AGENTS.md reached a 100% pass rate at getting AI coding agents to follow architecture decision records, while a skill carrying the same material wen…
A developer built a Claude Code mod that runs Freedoom on the doomgeneric engine inside a terminal pane beside the Claude transcript, spawning a native binary via $.process.spawn and communicating over a Unix socket or a…
Warp updated its AI addendum and privacy documentation, detailing that the terminal collects high-level product usage analytics plus AI interactions and console inputs unless users disable the "Help improve Warp" setting…
Weave Router 2.0 launched this week, claiming GPT-6 Astra-level coding agent performance at 48-54% of the cost and more than twice the speed by routing requests through a complexity classifier. On Terminal-Bench 4.0 the …
Elastic principal data scientist Susan Chang described how the company consolidated per-team agent evaluations into a shared, tracing-based framework for its production AI agents, including the attack discovery security …
Dray v0.26.0, a free Apache-2.0 macOS app from monorepo-labs, runs multiple AI coding agents — including Claude Code, Codex, Grok, pi, and fx — in a single window using existing subscriptions. The app assigns each parall…
Google's Antigravity 2.0 agent-first IDE landed on the Googlebook Play Store ahead of Googlebook OS shipping on October 4, bringing a multi-agent Manager View, Gemini 3.5 Flash as the default model, and an Android adapti…
Baldur, an early-access Python framework from baldurhq, released a decorator that makes LLM workers share a single backoff wait on a 429 or "overloaded" response and parks failed jobs for replay instead of losing them. T…
Anthropic released Claude Code v2.1.287 on Thursday, adding mods — JavaScript or TypeScript event-handler plugins that can redraw the tool's interface or intercept a tool call before it runs, enabled by default and docum…
Anthropic's Lance Martin published "Automating eval design and hillclimbing with Claude" on September 28, adding two commands to the claude-api skill: /claude-api build-eval, which interviews the user and builds an evalu…
EmDash 1.1, the first release since the CMS's 1.0 launch, adds a publishing calendar, isolated HTML/CSS/JavaScript blocks, Microsoft Entra ID sign-in and an experimental way for browser-based AI agents to search a public…
PLEXData published a build log describing a kill-switch approach to AI data access that denies by default, checks at the boundary before content moves, and logs every denial with who, what and when. The post argues that …
Andrej Karpathy published an "idea file" gist, llm-wiki.md, describing a pattern in which an AI agent writes and maintains a linked markdown knowledge base from user-supplied sources, compiling synthesis at ingest time r…
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…