Top Picks

SPARKIT is a scientific research agent delivered through an API. It searches literature, reads PDFs, runs analyses, and returns cited Markdown reports for research workflows.

pi-hosts is a tool for the Pi coding agent that adds named SSH targets, cached host facts, guarded remote command execution, and JSONL audit logs for server work.

An open protocol for giving AI agents structured, real-time perception from external sensors and data sources. The repo includes architecture notes, quick-start install flows, and a sensor catalog concept.

OMAR is a terminal-based tool for orchestrating large hierarchies of AI agents from one place. The page shows a TUI product with support for multiple backends, tmux integration, Slack messaging, and quick-start install options for macOS, Linux, Homebrew, and source builds.

OpenUsage is a macOS menu bar app for tracking usage across AI coding subscriptions like Claude, Cursor, Copilot, Gemini, and others. It includes automatic refresh, a customizable shortcut, a local HTTP API, proxy support, and a plugin-based provider system.

A Go-based text editor built for LLM agents, with branching undo, conflict handling, audit logs, MCP support, and agent skills installation.

A research code repository for studying how fine-tuning can trigger verbatim recall of copyrighted books in large language models. It includes preprocessing, fine-tuning, generation, and memorization-evaluation scripts, with setup notes and example data.

Loopsy is an open-source tool for controlling a laptop terminal from a phone and for agent-to-agent communication across machines. It includes a CLI daemon, a web/mobile control surface, Cloudflare Workers relay deployment, and MCP integration for AI coding agents.

A Claude Code status line that shows session size, next-turn cost, and remaining budget before you type.

A vision-language foundation model for autonomous driving that combines 3D perception, driving VQA, and motion planning in one framework. The repo shows performance tables, model structure, and links to the paper, blog, and model downloads.

Radia is an agent coordination layer for independently deployed agents, with immutable records, lease-based claims, permissions, and provenance tracking for who acted and what produced each result.

Openvurp is a local-first multi-agent workspace where agents have jobs, tools, memory, and can consult each other instead of answering in isolation. The repo shows browser, CLI, and Docker setup, plus concrete workflows for running commands, writing files, and using multiple channels.

Ardent is a code-first AI agent for business work that runs in a desktop app, writes reusable code in a sandbox, and lets teams share repeatable workflows as “Abilities.”

A production-ready Rails SaaS starter designed to give coding agents strong architectural context, with authentication, billing, authorization, Hotwire, Tailwind, Kamal, and repo-based guidance for extending the app consistently.

Blume Sidecar is a desktop companion for managing coding agents across tools like Cursor, Claude Code, and Codex. It tracks agent activity, monitors rules and hidden files, shows usage limits, and suggests fixes when instructions drift from chat context.

A detailed walkthrough of using an AI agent to design a PCB end to end, from requirements and part selection through routing, validation, and fab-ready gerbers, with public repo support and build checks.

1endpoint is an AI model gateway that exposes multiple models through one compatible API with usage-based pricing and transparent per-token rates. The page highlights request formats, model pricing, cache-aware billing, and live traffic stats.

ModelPeer is an open-source tool for cross-model peer review in coding workflows. It lets Claude Code, Codex CLI, and Gemini CLI review one another as read-only engineering peers, with commands for consultation, diff review, setup, updates, and safety controls.

Autonomous QA tool that takes a URL, explores the app like a user, generates end-to-end tests, and files bug reports with screenshots and repro steps.

Chrome extension that captures a fixed screen region, runs offline OCR with bundled Tesseract, and exports page-by-page text for use with LLMs or search.

A macOS menu-bar app that tracks Claude usage pace and estimates whether a subscription will last until reset, with advice on what to change if it won’t.

An OpenTelemetry Collector distribution that turns GenAI traces into bounded metrics and keyed summaries, designed for fleet-level observability without exporting raw prompts or high-cardinality labels.

A pure C implementation for training and running a tiny GPT, with build instructions, sample output, and performance notes for macOS, Linux, and Windows.

Termaxa is a CLI gate for AI agents that previews shell command impact, blocks dangerous actions, makes backups, and records audits. It’s built for Claude Code and Cursor, with quick-start and command examples shown in the repo.