Boogu-Image-0.1, an open-source unified multimodal understanding and generation model family from the Boogu Project, matches or surpasses other open-source models and approaches leading closed-source …
A third-party repository inspired by Andrej Karpathy's observations about AI coding failures has amassed over 189,000 GitHub stars. The project, created by Jiayuan Zhang under the account multica-ai, …
Matt Pocock, a TypeScript educator, open-sourced his personal .claude directory as the repo mattpocock/skills, which has amassed over 160,000 GitHub stars. The repository contains around 36 Claude Cod…
GitHub launched a technical preview of GitHub Copilot, an AI pair programmer that suggests whole lines or entire functions as developers type. Developed with OpenAI and powered by OpenAI Codex, the to…
Astrio released Forall, an AI coding agent that generates spec-driven code alongside machine-checkable proofs, available via a binary install. The tool supports TypeScript, Java, and Rust, with plans …
OpenAI's Codex encrypted sub-agent prompts, removing the plaintext audit trail that humans used to inspect delegated tasks after dispatch. A developer proposes a pre-dispatch authorization gate that c…
A developer released Flippermind-lite, a Super Tiny Language Model (STLM) designed to run on small devices like the Flipper Zero and Raspberry Pi. The project uses Qwen2.5-0.5B and includes fixes for …
Tahr Security has released a set of 11 security skills on GitHub, with 31 total installs, including skills for auditing secrets, mapping attack surfaces, and testing AI agents.…
Tom Huang's Shanghai team shipped Open Design, an open-source alternative to Anthropic's Claude Design, eleven days after the latter's April 17 launch. The local-first tool, which routes through codin…
CodeRabbit launched Post-Merge Actions, a feature that lets its AI agent automatically execute follow-up tasks such as updating changelogs, bumping versions, or creating tickets after a pull request m…
Zerostack, a minimal coding agent written in Rust and inspired by pi and opencode, launches with a 26MB binary and ~30k lines of code, consuming roughly 16MB of RAM on average versus ~300MB for JS-bas…
Open Science Desktop, a local-first, model-agnostic workbench for AI research, has been launched as an open-source project built with the Tauri framework. The tool, which has garnered 766 GitHub stars…
The terminal-based coding agent market has exploded to 35 actively maintained CLI agents as of July 3, 2026, according to a mid-year survey. Anthropic's Claude Code research preview in February 2025 s…
HarnessReport converts HarnessDelta's redacted JSON findings into native CI review artifacts for SARIF, GitHub, and GitLab formats. The adapter, part of the Nekoautomata Miki open-source portfolio, ma…
OpenAI's GPT-5.6 Sol achieved the highest score on ReactBench v1 at 43.1%, a new benchmark for coding agents on realistic React tasks, while Anthropic's Claude Fable 5 scored 41.2% at 6.3 times the co…
A developer's experience with Claude generating 47 passing tests for a payment processing module failed to catch a race condition that caused a production payment failure three days later. The 2025 St…
A developer released ai-credit-scrub v1.1.0, a free, offline-first Go CLI that removes explicit AI-agent credit lines from commit messages and pull request bodies before they reach Git history or GitH…
Security firm Mindgard publicly disclosed a binary planting vulnerability in Cursor, affecting 7 million users, after seven months without a patch from the vendor. The same attack class was separately…
Fin has published a curated set of Claude Code skills and hooks used by hundreds of its engineers, alongside a framework distinguishing effective from ineffective skills based on its internal experien…
Deja, a zero-dependency open-source binary, turns local agent conversation histories from Claude Code, Codex, and opencode into a searchable memory layer that works over SSH. The tool indexes gigabyte…