An engineer has built SlopScan, an open-source API that detects 'slopsquatting'—malicious packages pre-registered under names hallucinated by LLMs—and integrated it into Claude Code via a skill and a …
Tencent Cloud released TencentDB Agent Memory, an MIT-licensed memory hub for AI agent teams that converts conversations, documents, and code into four shareable memory assets—Chat Memory, Skill, Wiki…
AirLLM, an Apache-2.0 Python library, enables running large language models like Llama 3.1 405B on 8GB of VRAM and DeepSeek-V3 671B on ~12GB without quantization, by streaming one layer or MoE expert …
OpenAI published ten advances in mathematics and theoretical computer science, including results on sphere packing, non-sofic groups, and a counterexample to Connes' rigidity conjecture, with Lean cer…
The value of open-source contributions as a hiring signal is weakening because AI can generate patches and pull requests at scale, making it harder for maintainers to assess genuine understanding and …
Shadscan, a new deterministic UI audit tool for React shadcn apps, scores UI fundamentals from 0 to 100 and provides evidence for each finding, covering command menus, theme shortcuts, route states, a…
Open Interpreter released a fork of Codex that emulates Claude Code and Kimi's harness for cheap models, while OfficeCLI introduced a single binary enabling AI agents to read, edit, and render Word/Ex…
Microsoft's VS Code 1.131, released on July 29, introduces subagent visibility in the Agents window, built-in offline dictation powered by Microsoft's Nemotron model, and Bring Your Own Key (BYOK) sup…
A developer has launched SkillUp, an open-source toolkit aimed at modernizing the SKILL development experience for Cadence Virtuoso EDA platforms. The toolkit includes Skill Book, a searchable documen…
A developer has released Stram, an open-source, local-first desktop agent with human approval gates, designed to act as an always-available assistant that can take safe actions on its own. The agent, …
A feature request on GitHub's Anthropic Claude Code repository, issue #63925, asks for a persistent setting to disable the VS Code extension's default auto-attachment of the active editor file and cur…
PixLog, an open-source tool by developer Zhao Xuan, adds pixel-aware visual history to Git without creating a second commit graph or staging area. It tracks exact bytes, changed regions, coordinate bl…
A developer's comparison of AI code review tools for GitHub in 2026 highlights Qodo as a standout for automated pull request reviews with repository-wide context, while noting CodeRabbit's diff-only a…
Anthropic's Claude Code plugin marketplace is a JSON file in a git repository with no field for pricing, meaning developers cannot sell plugins through the official system. The schema, verified agains…
Ablo, an open-source project on GitHub, introduces an authoritative transaction layer for shared application state in AI applications, enforcing authority, idempotency, conflicts, ordering, and confir…
OpenAI released GPT-5.6, focusing on cost efficiency rather than raw capability, while DeepMind published Gemini Robotics 2 for whole-body coordination in unstructured environments. GitHub shipped sta…
A new workflow using tuicr, gh-dash, and Claude Code or GitHub Copilot CLI enables developers to review AI-generated code locally before pushing to GitHub, preventing unreviewed agent output from reac…
In the ninth episode of the AI & Docs podcast, Tom and host talk with Sarah Deaton, a technical writer at Anthropic, about how documentation work shifts from writing to orchestrating when AI automates…
A developer reports that using an open-source AI agent called 'the-agent' to generate and maintain tests for 30 days increased code coverage from 38% to 71% without writing a single test by hand. The …
A non-coding developer maintains a self-correcting file-based protocol across four production projects, including a crypto trading system, an e-commerce web app, an AI decision system, and an agent in…