Recently Evaluated

An open-source CLI for orchestrating long-running coding agents from a single terminal, with phases for research, planning, implementation, review, and PR creation.

A vLLM blog post explaining Semantic Router as an open serving-layer runtime for bounded micro-agents, with routing patterns like Confidence, Ratings, ReMoM, Fusion, and Workflows behind a single model API.

Music0 AI is a web-based AI music generator and music video maker that lets users create tracks without signing up. The page also highlights multiple music styles, commercial licensing, export options, and API access for developers.

Hail is a communications MCP server for AI agents, giving them a phone number, SMS line, and email inbox through one endpoint. It supports inbound and outbound voice, text, and email, with managed cloud and open-source self-hosting options.

INFINI is an open-source portable agent loop spec and reference implementation for defining workflows in a Loopfile and running them across engines. The repo includes a CLI, mock-mode execution, trace comparison, audit checks, and a prototype UI.

A long-form technical article on building ship-ready AI agents in Rails with the Anthropic Ruby SDK, covering tool design, agent loops, MCP servers, human approval, testing, and cost control.

TypeScript SDK that adds an agent-facing visualize tool and embedded interactive charts to an MCP server. It supports SQL-backed chart rendering, text fallbacks for non-widget clients, and adapters for several warehouse systems.

A pull request adding AMD GPU support to tiny-vLLM through ROCm/HIP while keeping the existing CUDA build path unchanged. The snapshot describes the compatibility header, CMake option, architecture selection, and validation on multiple AMD GPUs.

A deterministic Python project for empirical law discovery in elementary cellular automata, with simulation, discovery, reproducibility guides, and published preprints.

Open-source email firewall that classifies inbound mail into SILENT, QUEUE, PUSH, or AUTO using a deterministic policy around LLM-scored signals.

Standalone Playwright CLI for AI agent browser automation. It provides a real Chromium browser with structured commands, persistent sessions, token-optimized screenshots, and an eval escape hatch for custom interactions.

A skill for coding agents that routes slash commands and trigger phrases to zerostack, a lightweight CLI coding agent for coding, planning, reviewing, and orchestration tasks.

wavecat is a fully local personal agent that watches your screen and runs entirely on-device. The page explains its privacy focus, hardware requirements, local model setup, and supported platforms.

A CLI/browser skill for AI agents that turns websites into numbered actions with stable references, persistent sessions, and human handoff for auth, CAPTCHA, and MFA.

Exfault is an autonomous Android security testing tool that uses AI agents, static analysis, dynamic analysis, authenticated workflows, and cloud emulators to produce reproducible findings and reports.

A free browser-based tool that claims to detect whether text is AI-generated, with example inputs, inline explanations, and FAQ notes about privacy and local processing.

A DeepSeek paper about DSpark, a full-stack codebase for training and evaluating speculative decoding algorithms to speed up LLM inference.

Reference implementation for using Linux Pressure Stall Information to trim an LLM KV cache under memory pressure. The repo includes requirements, basic usage commands, a simulator, a llama.cpp runner, and benchmark scripts with example results.

Open protocol and reference router for capability-aware AI routing across local and cloud models, with install steps and deployment details in the README.

Open-source N64 game engine and visual editor built with libdragon and tiny3d. It targets real hardware and accurate emulators, with GLTF import, HDR+bloom, big-texture support, scene management, audio, collision, and node-graph scripting.

A local-first, self-hosted home assistant that runs a local LLM as a single brain for Home Assistant, voice, memory, reminders, media control, and other scoped tools.

A technical write-up showing how agentic AI was used to reverse engineer a label printer app, generate a Go-based Bluetooth printing workflow, build a browser version, and even extend the project to an ESP32-S3 hardware replacement.

FencePreview is an AI fence visualization tool for contractors. It lets users upload a yard photo, trace the fence line, and generate a realistic preview of different fence materials and styles to help close jobs faster.

An AI-powered pipeline that turns diarized podcasts or interviews into YouTube-ready videos with semantic B-roll, burned-in subtitles, optional TTS voice replacement, and YouTube publishing.