DocuWriter.ai launched an AI-powered code documentation tool that generates book-style documentation, API docs, and UML diagrams from source code via AST parsing and a code-aware retrieval pipeline, a…
Northstar launches an AI-powered pull request review tool for GitHub and Azure DevOps teams, offering flat-rate pricing instead of per-seat fees. The tool analyzes diffs in memory without storing them…
XAI open-sourced its AI coding agent "Grok Build" on GitHub under the Apache 2.0 license after a massive data breach in which the tool uploaded users' SSH keys, password databases, documents, and phot…
A developer created agent-gate, an open-source Python library that adds a deterministic policy gate between an AI agent's decisions and real-world actions. The gate issues single-use tokens only after…
A new method called DoLQ uses a multi-agent AI architecture, including a Scientist Agent powered by a large language model, to discover differential equations by combining qualitative and quantitative…
Quantum Circuit Vision, a new benchmark of 132 quantum circuits across 13 categories, evaluates multimodal AI agents' ability to understand circuit diagrams and generate executable code for Amazon Bra…
SpaceXAI has open-sourced Grok Build, the terminal-based AI coding agent behind its grok CLI, under the Apache 2.0 license on GitHub. The release includes the agent harness, TUI, CLI shell, and develo…
XAI has released Grok Build, an open-source project on GitHub that provides a framework for building and deploying AI models. The project aims to automate tasks like data preprocessing and model deplo…
A novel convolution-inspired network structure for classifying ancient cuneiform tablets outperforms the state-of-the-art transformer-based network Point-BERT, according to researchers who developed t…
A new Raycast extension called Claude Fleet lets developers manage Claude Code agents, pull requests, and worktrees directly from the Raycast launcher, reading Claude Code's own session registry for l…
HealthClaw, an open-source AI health coach, boosted answer accuracy from 0.2% to 45.7% on a synthetic year-long benchmark while reducing unnecessary data exposure by 71.7%, according to its developers…
A study of 2,991 GitHub projects found that AI bots significantly alter group dynamics, boosting repeated collaboration, social memory, and role differentiation while reducing conflict cascades almost…
GitHub announced agentic autofix for code scanning alerts in public preview on July 10, 2026. A developer proposed an evaluation framework with failure classes and reliability gates to measure autofix…
GitHub announced on July 14, 2026 that security reviews are now available in the GitHub Copilot app. A proposed research protocol outlines how to evaluate whether reviewers using the tool can build ev…
GitHub announced on July 8, 2026 that GitHub Mobile can initiate a Copilot cloud-agent workflow to fix pull-request merge conflicts. The company recommends a bounded instruction model over a simple ta…
GitHub announced on July 14, 2026 that Copilot for JetBrains expanded bring-your-own-key capabilities. A proposed accessibility test plan outlines how keyboard and screen-reader users should interact …
A developer created a beginner project for schema validation using GitHub's new Issue Fields feature, which became generally available on July 2, 2026. The project demonstrates how to validate structu…
GitHub announced on July 2, 2026 that Copilot CLI no longer requires a personal access token when running in GitHub Actions. A developer provided a migration template for removing the PAT injection fr…
GitHub announced on July 10, 2026 that CodeQL 2.26.0 adds AI prompt-injection detection. A developer provides implementation templates for building a regression fixture to test the query, emphasizing …
A team of researchers achieved an average precision of 0.875 and a macro-F1 of 0.72 on the Ambivalence/Hesitancy Video Recognition Challenge of the 11th ABAW Competition using an audio-text system tha…