AI Tools

A 119-call benchmark across seven document-parsing providers and 11 real-world documents found Extend was the only API with zero hallucinations and a perfect 1.00 table row F1 score, while Claude direct led raw field acc…

Pipper launched as a single Electron desktop interface for controlling multiple AI coding agents, built on the ACP protocol to support Claude Code, Codex, Cursor, OpenCode, and Grok out of the box. The app is available a…

A developer building SaaS products with AI coding agents reports that an agent refused a ticket to delete a supposedly dead legacy backend after verifying it held 192 applied database migrations and built two of five pro…

A developer built >_Fa, an open-source agent harness written in Dart, by consuming roughly 40 billion tokens across cheap models like Kimi K3 and GLM-5.3 at a cost of about $17,000–$20,000 over three months, with no huma…

SpaceXAI launched Grok 4.7 on September 21st, a larger base model with a 500,000-token context window and a May 2026 knowledge cutoff, priced at the same standard API rates as Grok 4.6: $2 per million input tokens and $6…

A developer released Sommelier, an Excel add-in plus relay server that lets an AI agent work alongside a user inside an Excel spreadsheet, inspired by the marimo pair tool. The add-in is sideloadable but not yet publishe…

Developer satmihir released gobag, an open-source plugin for Claude Code that checkpoints a session's context, decisions, and pinned Git commits into a single encrypted .gobag file for restore on another machine. The plu…

A developer integrated TypeSafe's Jev, a non-LLM model that evaluates states against typed questions and returns probabilistic verdicts, as a judgment layer over a 52-tool security panel. In a pipeline run, 25 tools prod…

Worktrunk, a Rust CLI created by Maximilian Roos, wraps git worktree management into three commands — wt switch, wt list, and wt merge — to support running parallel AI coding agents such as Claude Code and Codex on the s…

XAI launched Grok 4.7, its latest frontier model for coding and knowledge work, keeping the same starting price as Grok 4.6 at $2 per million input tokens and $6 per million output tokens. Grok 4.7 scored 46.3% on Cursor…

A developer rebuilt their personal portfolio using Claude Code, with the AI writing much of the code while the developer retained control over design, accessibility, SEO, and performance decisions. The production site, b…

TickerWhale launched a free research product that assigns nightly 0-100 scores and model fair values to more than 1,300 stocks, combining quantitative models and AI analysis of markets, earnings, Wall Street activity, ne…

Tabby, an AI-powered real-time bookkeeping interface built by a former accountant, is designed to handle clients' paperwork while delivering up-to-the-minute profit-and-loss data, according to TechCrunch AI. The tool's s…

A developer argues that as capable AI models become commoditized, engineering value shifts to applying intelligence inside organizations, embodied by the Forward Deployed Engineer (FDE) role. The piece cites Accenture an…

Monday.com AI Engineering Director Dor Cohen said in a September 15 session that agent evaluations are unreliable when run against mocked APIs and databases, citing an agent tasked with retrieving 600 items that processe…

A developer built zombiescan, an open-source AWS waste scanner, and wrapped it in a Model Context Protocol (MCP) server so AI agents can query cost data through the same engine a terminal uses. The server exposes five re…

Posit's integrated development environment Positron now runs on Amazon SageMaker AI, letting data science teams query Amazon Athena, the AWS Glue Data Catalog, and Amazon S3 directly under a Space execution role without …

Humanize Max is a free browser-based AI humanizer at humanizemax.ai that rewrites AI-generated text into natural, human-sounding writing with unlimited rewrites and no paywall on the output, according to the site. The to…

A developer's viral post about a team using Claude Code for nearly all software work—specs, code, tests, and tickets—has sparked debate about a new bottleneck in AI-assisted development: human understanding. The engineer…

Benchling deployed Amazon Bedrock AgentCore Code Interpreter in Amazon Virtual Private Cloud mode to run AI agent-generated scientific code across thousands of life sciences tenants, an architecture that now processes mo…