A developer built Sentinel, an autonomous agent whose memory system forgets by design rather than growing without bound. Each memory category has a hard entry cap in a single JSON state file, and when…
A developer built TrustBoundary Bench, a synthetic incident-response benchmark that tests whether AI models can distinguish untrusted evidence from authorized user instructions across 150 cases per mo…
A developer documented how YOLO mode actually works in Google's Antigravity IDE and CLI, clarifying that `agy --yolo` is not a valid flag and that the CLI equivalent is `agy --dangerously-skip-permiss…
A developer built Acoustic Atlas, an offline-first Progressive Web App that uses Google's open-weight YAMNet audio classifier via TensorFlow.js to score how "alive" a location sounds. The app processe…
A developer-run audit of the live WooCommerce skincare store mishbio.us raised its AI-readiness score from 77 to 96 out of 100 in about three hours by fixing machine-readable data rather than shopper-…
A developer has released sse-wire, a zero-dependency, fetch-based Server-Sent Events client for JavaScript that can issue POST requests with custom headers, addressing a structural limitation of the b…
A YantrikDB maintainer traced a Windows 11 write failure in the Hermes Agent install to a mislabeled error: the engine's ForeignSqliteGuard is inert on Windows, so the only path that could taint the s…
A developer built coerce-json, a zero-dependency library that takes almost-valid LLM JSON output and coerces it to fit an existing Zod schema while reporting every change it makes. The library strips …
A developer built CanopyStride, an offline-first, open-source AI agent that converts runner prompts into structured .gpx route files optimized for high tree canopy density, park trails, and autumn fol…
Stelia has open-sourced async-ceph, a library providing asynchronous Rust bindings for Ceph's RADOS, RBD, and CephFS libraries, covering object, block, and file storage. The company says it built the …
A developer published a PowerShell-based Git Safety Harness that runs six fail-closed checks — repository root, write set, stage set, branch, push URL, and a Gitleaks secret scan — before committing o…
An analysis of AI code review benchmarks found that vendor-published comparisons consistently rank their own tool first and report wildly different scores for the same rival, because each uses its own…
A developer documented running a 10,000,000-record batch LLM inference workload entirely on a local HP Z4 G4 workstation at zero cloud cost, using jemalloc with background thread decay to prevent heap…
A developer built "Can You Find It?", an open-source game in which a local Gemma 4 E4B vision model running via Ollama on a laptop secretly picks one real object in a photo of a familiar place and iss…
A developer documented that the AliExpress Scraper Actor returns zero records when an AI agent requests regional storefronts such as `ja` (Japan) or `ko` (Korea), because those pages serve client-side…
A developer built TrailMate AI, an open-source, privacy-focused Progressive Web App that runs a CLIP vision-language model entirely in the browser to identify natural objects from user photos without …
A developer measured local LLM performance on a 16 GB Apple M5 laptop using Ollama, finding that a 3-billion-parameter model generated text at 51 to 55 tokens per second while using 2.5 GB of memory a…
A developer published a TypeScript teaching build demonstrating that post-retrieval tenant filtering in RAG pipelines is both a retrieval bug and a data-boundary bug, since globally top-ranked documen…
A developer argues that prompt injection and jailbreaks are fundamentally different security problems that require different defenses, and that conflating them leaves agent deployments vulnerable. The…
Mistral entered public preview of Mistral Large 4 on 6 October 2026, a mixture-of-experts model with roughly 1.05 trillion total and 49–52 billion active parameters, priced at $1.36 per million input …