A developer released AgentGuardBench v0.1.1, an open multilingual benchmark of 120 synthetic scenarios for evaluating privacy, security and responsible behaviour in tool-using AI agents. The benchmark…
A developer has released Stave, an open-source tool that generates deterministic, machine-readable HIPAA compliance evidence for Amazon S3 buckets, citing specific HIPAA sections such as 164.312(a)(1)…
A developer built VivaMate, a local AI-powered viva preparation assistant that runs an open-weight model through Ollama to help a friend revise college notes. The Streamlit and Python tool generates p…
A developer built CampusCopilot, a personal AI learning workspace for college students that links study, coding practice, performance tracking and scheduling into a single loop. The system uses a TF-I…
A developer has built Tweak, a tool that lets clients point directly at elements on a live staging site to file change requests, keeping each request attached to the exact page and element as it moves…
A developer built College Copilot, a Streamlit app that ingests a student's scattered college updates — WhatsApp exports, notice PDFs and screenshots — and matches them against her subjects, attendanc…
A developer A/B-tested nine popular AI coding-agent skills against Sonnet 5.5 and Haiku 4.5 using Anthropic's claude plugin eval, running 19 test cases three times per arm, and found four of the nine …
A developer built GlucoPulse, an open-source, privacy-first metabolic digital twin that forecasts post-meal glucose spikes using Prior Labs' TabPFN tabular foundation model and Google Gemma 2 for plai…
An applied AI engineer outlines a practical evaluation loop for RAG and classification systems, arguing that aggregate accuracy metrics can mask increased product risk. The approach stores per-case me…
A developer built StudySaathi, a local-first AI study companion that runs on a user's own machine via Ollama and Google's open-weight gemma3:1b model, turning pasted class notes into simplified explan…
A developer built StudyMate, an AI-powered interview practice tool that lets users answer common interview questions and receive scored feedback with strengths and areas for improvement. The project p…
A developer has released Synapse, an open-source (Apache-2.0) Go control plane that runs the full security-assessment lifecycle behind a single gate and treats every result as re-checkable evidence ra…
A developer built ShouldISkipClass.ai, an open-source, fully local web app that uses Google's Gemma 3 (4B) model via Ollama to advise students on whether they can safely skip a class based on attendan…
More than 13,000 internal screenshots from over 300 organizations, including Fortune 500 companies and a frontier AI lab, were exposed in a publicly accessible storage bucket after AI browser agents u…
A developer built FriendStudy AI, an open-source AI study companion that combines study planning, AI-generated explanations and quizzes, and progress tracking in a single workspace. The app runs Qwen …
A developer built RoastMyResume, an open-source AI tool that delivers brutally honest, section-by-section resume feedback and job-description matching to help a friend who kept getting rejected from i…
A developer-tested comparison of seven GitHub Copilot alternatives found Cursor the best overall pick for most developers, scoring 4.4 out of 5 across agent depth, editor polish, value and free tier, …
A developer built StudyBuddy CLI, a terminal-based AI study companion that converts notes into flashcards and quizzes users via the SM-2 spaced-repetition algorithm, running entirely locally through O…
A developer built sessionhub, an open-source (MIT) Go binary with a SQLite database that acts as a registry and unified inbox for every Claude Code session across multiple machines. The tool uses Clau…
A developer has published a small, drop-in Python pattern for capping agent-loop costs by wrapping each model call in a per-task budget that records token spend by step and raises a BudgetExceeded err…