Top Picks

An open-source operating system project built around AI-era workflows, with a microkernel, userspace services, IPC ports, and a desktop environment already running in QEMU and on real hardware.

A macOS status bar overlay that shows when Claude Code is busy or waiting for input, using local hooks and a click-through always-on-top window.

An open-source course and reference implementation for a self-scaling OCR pipeline on Kubernetes, using Rust for ingestion, vLLM for inference, Redis and KEDA for event-driven scaling, and MCP integration for agent use.

A playful API that gives a coding agent a simulated “smoke break,” with endpoints for dispensing breaks and tracking the total count.

A proof-of-concept governance harness for agentic coding loops, using machine-level policy enforcement, validation hooks, and a deterministic control point to keep agent outputs within approved rules.

Lagotto Meter is a beta web tool that checks how an AI agent perceives a website versus what the site claims about itself. It positions itself as a semantic truth/readability analyzer with a reproducible analysis method and public tools.

TZRO is a local-first MCP gateway that offloads token-heavy repository and file operations to local models, aiming to reduce cloud AI token costs for coding workflows.

An open-source protocol ecosystem for controlling LLM behavior during software development, with a focus on preventing context drift and code regressions through minimal diffs, inspection-first workflows, and snapshot-based session handoff.

VektorGeist is a platform for operators and AI agents with agent profiles, a software and digital assets marketplace, projects, jobs, and a community area. The page also highlights verifiable signed identities and trust tiers for agents, plus blog posts about local-first AI and offline agent workflows.

A repository for a companion ebook that matches the wording of an ElevenLabs Michael Caine narration of The Odyssey, using Greek names to align the text with the audiobook.

A repository for a zero-trust execution boundary that sits between AI agents and real system actions. It evaluates policy, approval, scope, freshness, replay, and evidence before allowing operations to proceed.

A live dashboard tracking an autonomous AI’s attempt to win a public follower-growth bet, with a countdown, live counter, and activity log.

Aerial is a local-first Rust tool for agent-to-agent messaging and orchestration, with durable mailboxes, a supervisor, and an MCP adapter. The page shows what it does, how it works, and basic install commands.

Chrome extension that lets users rate webpages for likely AI-generated content and aggregates those votes into a Slop Score shown to other visitors.

A position paper arguing that AI alignment methods can be repurposed for censorship and manipulation, with examples across pre-training, post-training, and inference-time controls.

An OpenAI-compatible API proxy for using DeepSeek models with standard OpenAI SDKs, billed pay-as-you-go and accessible without phone verification.

An AI skill that plans and optimizes vehicle delivery routes from natural language using Routing24’s WebMCP tools. It supports multi-stop route planning, shareable outputs, and installation for compatible agents like Claude or Cowork.

A monthly poll that asks developers which AI coding agents they use and publishes the results.

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 CLI tool that deterministically routes prompts between local and hosted LLMs without making a model call to decide. It emphasizes offline operation, configurable calibration, and demo modes for seeing routing decisions and savings.

A side-by-side comparison of 15 AI agent frameworks, including LangGraph, CrewAI, AutoGen, Pydantic AI, OpenAI Agents SDK, Mastra, Vercel AI SDK, LangChain, LlamaIndex, Haystack, Dify, Flowise, n8n, Semantic Kernel, and smolagents. The page highlights use-case fit, control style, language support, GitHub stars, and fra

A Python CLI and research toolkit for simulating AI training math before model training. It estimates memory, training time, token budget, config risks, benchmark speed, and reliability, with optional native Rust and C backends.

AdvertBench is a web app for ranking AI-generated image ad sets with Elo voting. The page shows head-to-head ad comparisons, a leaderboard, and a sample prompt for generating ads, making the product purpose easy to understand.

Open-source PowerShell tool that makes Claude Code chats started in VS Code appear in the Claude Code desktop app by writing the missing session/index-card files.