Recently Evaluated

RiskKernel is an open-source, self-hosted reliability runtime for AI agents. It adds hard budgets, kill switches, crash-resumable runs, human approval gates, and OpenTelemetry export, with support for OpenAI, Anthropic, and existing agent stacks.

A free, Apple-notarized macOS menu-bar app that forces short rain-themed breaks while AI agents keep running in the background.

LocalCode turns plain English into CLI commands on Apple Silicon Macs using Apple’s on-device Foundation Models framework, then asks for approval before running them.

SlopGuard is a desktop Chrome extension that scans images on webpages for AI generation signals using local detection methods, including metadata, SynthID, and a visual classifier.

A Steel blog post that dissects Claude Code’s deep-research workflow and contrasts it with other research systems. It also positions Steel as an open-source browser API for AI agents, making the page relevant for AI builders.

AutoGPU is an open-source project for using AI agents to design and harden a GPU-like chip end to end, from Verilog through synthesis and place-and-route to GDSII. The repo shows a concrete fp8 matmul accelerator flow, quick-start steps, and documentation for running the design/hardening process.

Linux-only kernel-level audit feed for Claude Code or other matched agent sessions, streaming exec, file, and network activity in real time.

Runtime safety net for LLM agents that detects runaway token growth, classifies failure patterns, and suggests fixes without extra LLM calls. The project includes a Rust core, Python SDK, examples, benchmarks, and benchmark claims across multiple models and runs.

Open-source voice-driven multi-agent assistant for building real projects on a Mac, with voice, web chat, and WhatsApp channels plus CLI-based task runners.

A Blue41 case study on how a banking AI assistant could be abused through indirect prompt injection, and what mitigation layers help reduce the risk.

A macOS SwiftBar plugin that shows Claude Code quota gauges in the menu bar, with per-account usage, reset timers, and a dropdown with detailed limits.

A set of small AI app experiments focused on “the use of the useless,” including AI Almanac, Forget, and Nickname Machine for history, closure, and naming moments.

A focused article-style site arguing for domain-specific languages in LLM workflows, with concrete examples around structured extraction, validation, and pricing rules.

Terra is an off-market property intelligence platform that scores parcels from public records to surface owners likely to sell before listings appear.

OpenLoomi is an open-source desktop AI workspace that connects to apps like email, calendar, chat, docs, and project trackers to build a persistent context graph with proactive actions and local-first storage.

Subarr is an open-source coordination layer for the *arr subtitle stack. It adds subtitle coverage tracking, audio-language verification, provider success tracking, queue management, Whisper tuning, and post-transcription quality checks for Bazarr/Subgen workflows.

Python library that automates ChatGPT and Gemini through the web UI, using a real Chrome browser to send prompts, upload files, and return responses as Python objects.

Offline AI file organizer for Mac that sorts and categorizes files in Desktop and Downloads using a local model, with a 30-day free trial and one-time purchase options.

A local-first desktop environment for dispatching coding tasks to any model and any agent, with diff review, terminal streaming, task history, and per-project configuration.

Dochost turns HTML or Markdown into a shareable hosted link, with live Markdown preview, free no-signup hosting, and a public API for agents. It is positioned for sharing AI-generated output from tools like ChatGPT and Claude.

Google’s Gemini 3.5 Live Translate is a near real-time speech-to-speech translation model that works across 70+ languages and is being rolled out in Google AI Studio, Google Meet, and Google Translate.

A TypeScript stealth browser runtime for AI agents that drives real Chrome over raw CDP, with MCP support and accessibility-tree based interaction.

Open-source agentic end-to-end browser testing tool for web apps. It runs JSON-defined test journeys in Docker and can be used as a CLI or optional self-hosted web app.

A GitHub repository that packages Claude Desktop for Linux with install paths for Debian/Ubuntu, Fedora/RHEL, Arch AUR, and NixOS, plus MCP support and system integration features.