Agent-evals is a skill designed for evaluating components and end-to-end levels of agentic AI pipeline systems. It enables users to define measurement criteria, build or sample evaluation cases, run repeatable tests, track regressions over time, and derive insights from the results.

This is a classic Blackjack game where players start with $1,000 and bet on each hand to beat the dealer. Blackjack pays 3:2 odds, the dealer hits on soft 17, and the deck is reshuffled after each hand. Players' scores are determined by their highest bankroll achieved during gameplay.

Muesli is described as an open-source project that aims to handle data securely and privately on a user's device, implying it offers features related to protecting personal information from external access or breaches. However, specific functionalities are not detailed beyond this general description.

Logram is a tool designed to navigate through large logs in the terminal. Users can define the structure of their log lines, filter based on field values, and use advanced search functionalities such as boolean logic and keybindings.

Retrodex allows users to browse and catalog over 8,000 games across 20 classic consoles. It provides detailed information including beautiful box art, gameplay videos, cheat codes, and market prices.

Rudel allows users to collaborate with AI coders like Claude and Codex, providing assistance in writing code, refactoring, and other programming tasks. Users can track their sessions and monitor metrics such as success rate and commit rate.

TablePlus is a GUI tool designed for managing relational databases, supporting MySQL, PostgreSQL, SQLite, and more. It offers features like inline editing, advanced filters, code review, safe mode for production databases, and export/import capabilities. The tool also includes a metrics board for building internal dashboards and a smart query editor with autocomplete and syntax highlighting.

Allows users to build interactive maps using SQL within Snowflake without external tools or data copies. It supports multiple geospatial data types and integrates seamlessly with Snowflake’s security features.

Pictero is a web application that offers a wide range of features for image manipulation, including adjustments like brightness and contrast, annotations, social media export options, OCR capabilities, animation creation, ASCII art generation, and steganography. It supports both manual image loading and integration with several image sources.

Emergent allows users to develop production-ready applications via chat-based conversations, where AI agents handle the design, coding, and deployment process from start to finish.

Offers a dashboard with scores based on guest reviews across six categories for each hotel, along with nightly rates tracked over the past year. Users can filter results by brand or location to find the best luxury accommodations at optimal prices.

Skillify is a browser-based tool that reads URLs and generates Skill.md files, which include frontmatter, an overview, patterns, pitfalls, ready to be uploaded as skills for Claude Agent or similar AI tools. It operates client-side without any backend or proxy services.

NetHack is a classic roguelike dungeon-crawling game that has been updated to version 5.0.0, bringing new features and improvements along with addressing known issues from previous versions.

StartupLaunchPage is a platform designed to showcase and discover new startups. It offers features like a leaderboard and grid-based listings. The site also has in-game marketing and a pricing system for box placements.

Pake is a command-line tool that transforms websites into standalone desktop applications for macOS, Windows, and Linux. Built with Rust Tauri, it offers significantly smaller package sizes and faster performance compared to traditional frameworks like Electron.

Maxcred is an app that helps users choose the most beneficial credit card based on their spending habits. Users start by inputting merchants or common categories, and the app provides a comparison of cards tailored to maximize rewards.

Provides tools to look up IP address details such as owner information, ASN (Autonomous System Number), geolocation, reverse DNS, CIDR range, and blocklist status. It also allows users to browse Autonomous System Numbers, find organization IPv4 allocations, and view country-specific IPv4 statistics.

Private AI Skills is a service for syncing AI agent skills across different machines, projects, and teams. It provides a single source of truth for skills, ensuring all users always have the latest versions. The service uses end-to-end encryption to keep secrets secure.

ReflowPDF uses AI to convert PDF documents into fully editable HTML, allowing users to modify text and tables without manually recreating the document layout. The system automatically adjusts page breaks and layouts as edits are made.

The Interactive Marimo Moss Ball is a real-time rendered WebGL application that simulates an interactive marimo moss ball. It features detailed shader effects and physics-based interactions, allowing users to click and interact with the moss ball in their browser.

Users can input a significant date and receive reminders for upcoming life events within the next 30 years. The service provides calendar files to be imported into various devices.

This project demonstrates how to integrate Tailscale into a minimal Linux host VM for each container instance on macOS. It runs Tailscale in userspace networking mode, enabling secure SSH connections and MagicDNS without exposing ports or configuring separate SSH servers.

This service repeatedly changes the browser tab title to names of common debugging and reverse engineering tools. Games like Fortnite use anti-cheat systems that check for these tool names in open window titles, which can result in players being kicked or banned even if the tools are not actually installed.

PyFlue allows developers to create agent workflows using Markdown descriptions combined with Python execution. It provides persistent sessions with resumable history, policy-controlled sandbox environments for filesystem and shell access, and validates outputs using Pydantic models. The framework also enables deployment across multiple platforms including Docker, cloud providers, and CI/CD pipelines.

A calendar-based application designed to help users manage and track their paid time off (PTO) days. Users can view, export/import data in various formats such as PDF.

Provides a pure Swift (version 6) implementation of the Argon2 algorithm designed to be memory safe and zero-dependency, suitable for client-side key derivation on devices such as mobile platforms where security is paramount over performance. It includes all three variants of Argon2: d, i, and id.

Provides a platform to write and run examples of the Spectre programming language directly in the browser. Includes basic features like syntax highlighting, example scripts, and execution capabilities.

HypergraphZ provides a directed hypergraph implementation in the Zig programming language. Each hyperedge can contain zero, one (unary), or multiple vertices, and can direct vertices to themselves. It is designed for modeling complex relationships and networks with multi-dimensional connections.

Tyche is a project focused on building a fully autonomous, real-time, distributed, load-balanced, and fair trading bot. It emphasizes optimizing data flows for scalability and handling high-volume trades while exploring the architecture of concurrent systems design.

KingRT Video Call App is an open-source video conferencing solution that allows users to host self-hosted video calls and organize demo requests through a website form. It provides a platform where users can schedule and conduct video calls with the ability to customize the number of participants and other settings.

thr is a small local CLI tool that enables saving explicit memories and recalling them later by meaning or text. It is designed for agent workflows, providing stable JSON output, offline semantic search capabilities, and installable skills for various coding agents.

Kubesplaining is a Kubernetes security assessment CLI that maps RBAC privilege-escalation paths in K8s clusters. It analyzes RBAC bindings and pod configurations to identify potential attack vectors by mapping out the paths an attacker could take to gain cluster-admin access or other privileged capabilities. The tool produces risk-prioritized HTML/JSON/CSV/SARIF reports showing the exact escalation chains with remediation guidance.

OpenInbox provides disposable email inboxes via API for programmatic creation, receiving, and verification of emails. It's designed for CI/CD pipelines, QA automation, and staging environments. The service also offers a Chrome extension for easy inbox generation, email field auto-fill, and real-time notifications.

Service allows users to subscribe to any RSS or Substack feed, select articles they want to read, and send these articles in a well-formatted ebook directly to their Kindle device. It simplifies access to digital content for offline reading.

Sourcery autonomously conducts deep research, fact-checks and synthesizes reports with inline citations, contradiction analysis, and source memory. The system aims to ensure every report is citation-grounded and avoids hallucinated claims.

Provides real-time visualizations of music and audio within a web browser. Users can connect their microphone or upload files to see various visual effects based on the sound input.

This tool allows you to manage systemd services through a terminal user interface (TUI). It supports viewing logs, listing services, editing unit files, and controlling the service lifecycle with commands such as start, stop, restart, mask, unmask, enable, and disable. Navigation is similar to Vim.

This web application allows users to upload an image and generate Gaussian splats in the browser, preview the result, and download it as a .ply file. It leverages ONNX Runtime Web for inference.

Seeker is a resume-to-role matching engine that compares user resumes with over 160,000 live job listings to provide personalized career advice and insights on skill gaps. It offers detailed analysis including market position, best-fit roles, and areas for improvement without requiring an account.

Julius is a preliminary attempt to create a new dialect of the Lisp programming language implemented using Common Lisp. It requires SBCL and quicklisp dependencies for usage.

Provides curated sets of questions designed to facilitate meaningful conversations between partners. Users can play solo or with their partner using a join code, and the platform offers various themes such as 'Deep Talk', 'Fun & Playful', and 'Date Night'.

Onionlink is a small C++20 Tor v3 onion-service client that communicates directly with Tor relays, builds necessary circuits for v3 access, and supports raw data exchange or HTTP requests with the service. It omits extensive security features present in standard Tor clients to focus on interoperability.

ScaleBridge automatically forwards weight measurements from a user's Withings smart scale to their Garmin Connect account, ensuring data is available in one place without manual input. Users can either sync manually or set it up for automatic background syncing.

Players try to guess a secret word by suggesting one letter at a time. If the guessed letter is in the word, it's revealed; if not, the player loses part of their 'lives'. Once all lives are lost or the entire word is guessed correctly, the game ends.

BulkPicTools offers a suite of 39 free, browser-based image tools for resizing, compressing, converting, and editing photos. All processing happens locally, ensuring privacy and speed without requiring an account or server uploads.

LISA is a semi-modular polyphonic wavetable synthesizer and configurable kinetic MIDI controller for Raspberry PICO that offers live dynamic wavetable synthesis. It supports up to 6 voices at 44.1kHz or 8 voices at 32kHz. LISA features a new LIVE engine which allows real-time shaping of wavetables with bilinear interpolation. It also provides kinetic controls for sending oscillating MIDI values and deep integration with Nallely for extended capabilities through websockets.

This service allows users to compile and parse custom Magic: The Gathering cards, providing a means to create and test non-official card designs in a digital environment. It includes features such as debugging logs, creating lobbies, and managing game states.

Models the entire lifecycle of private equity and venture capital funds, simulating capital calls to carried interest. Features include waterfall distribution simulation, J-curve visualization, and calculation of fund performance metrics like DPI, TVPI, and IRR.

Grinta is a local-first coding agent that plans, executes, validates, and finishes software tasks end-to-end without requiring a cloud control plane or locking users to a specific model vendor. It integrates with local language servers and debuggers, supports multiple LLM providers, and maintains session durability through event-stream ledger. The agent includes safety features such as risk-classified actions, audit logs, and cost/token/latency tracking.

Offers a range of services including custom software, mobile apps, UI/UX design, AI automation, web development, and idea validation. Each service is designed to integrate seamlessly with others provided by the same company.

Fabrica is a terminal-based coding agent that executes multi-step tasks using tool calls and provides an interactive TUI with features like scrolling, model switching, and autonomous file editing. It supports multiple providers including Google Gemini, Anthropic Claude, and OpenAI models for code-related tasks.

A chess application inspired by Vim and centaur concepts, allowing users to choose from top moves in their games. It features private rooms, matchmaking options like human vs AI, rush modes with varying skill levels, and a leaderboard.

The service ranks public code repositories on GitHub, GitLab, and Bitbucket based on their compatibility with various AI coding agents. Users can search for repositories by owner or name to see a list ranked according to agent-friendliness scores.

The Deep-Research Agent is designed to enhance the quality of user-generated content by providing comprehensive analysis and sourcing after a short processing time. It aims to mimic human research methods but more efficiently, offering citations, sources, and structured analysis in response to user queries.

Provides a tool to perform load testing using k6 based on OpenAPI specifications. It allows users to conduct detailed performance analysis for web applications.

The service performs trading analysis using 7 subagents across 5 phases to evaluate stocks by analyzing technical indicators, news, fundamentals, macroeconomic factors, and risk scenarios. It provides structured buy/sell/hold signals with detailed rationale via Claude Code's native Agenttool, using free market data from yfinance without requiring external LLM APIs.

This Rollup plugin provides a more accurate way to bundle TypeScript declaration files (.d.ts) using Microsoft's API Extractor, which is designed not to mangle type names or drop re-exports. It simplifies the process of integrating API Extractor into Rollup workflows by exposing it as an interface.

Piruetas is a minimalist journaling application designed for individuals to write and store personal entries on a daily basis. It allows users to create one entry per day with formatting, image uploads, and private sharing capabilities through links. The app prioritizes simplicity and data privacy by default.

Provides a local, private environment to interact with data using natural language and build machine learning models automatically. It generates actionable insights without relying on cloud services.

Shutt is a service that automatically generates aesthetic photo and video posts from your Strava activities. It turns your running data into visually appealing media that can be easily shared on social platforms.

The Male Hormone Lab Interpreter is a web-based tool that visualizes testosterone production and feedback pathway markers to determine the underlying causes of hormonal imbalances. It automatically calculates free testosterone using the Vermeulen method and provides detailed interpretation of individual hormone markers and ratios, showing their clinical significance and potential causes of abnormal values.

Allows users to edit, fill out, and understand PDF forms through conversational interaction with an AI assistant. Users can also utilize their own preferred language model for processing messages.

Provides a solid foundation to start building software as a service (SaaS) products using Flask and Python. Offers the ability to integrate AI features into the product.

Glacier is a modern macOS terminal that rethinks the terminal as a first-class macOS application. It provides auto-tiling panes, file icons, custom background images, live font and theme switching, and a true native feel with familiar copy, paste, and drag functionality. It is built with Rust and Tauri to offer a fast and self-contained experience without requiring system modifications.

Allows users to build their own matchstick puzzles quickly. The platform saves user progress locally on the device, though it may be lost if browser data is cleared or when playing in private/incognito mode.

This tool detects running processes that utilize the AF_ALG socket interface to help determine if it is safe to disable the AF_ALG kernel module. It outputs a list of processes and their file descriptors associated with AF_ALG.

The service ingests raw FHIR R4 bundles and maps them automatically to OMOP CDM tables, resolving vocabularies. It also generates synthetic hospital datasets for testing and analytics purposes.

Provides declarative React components and state helpers for integrating Codex pet spritesheets into web applications. It includes sprite animations, fixed-position rendering with drag-and-drop functionality, and integration with app states via reducers and hooks.

Passages allows users to save news, articles, and long-form content from the web in a distraction-free manner. It automatically cleans up unwanted elements and organizes saved content into ebooks that can be read on e-readers like Kobo or Kindle.

Provides a full-stack framework powered by TanStack Router, featuring server-side rendering (SSR), streaming capabilities, server functions, and more. It supports client-first development while also providing robust server-side features.

TTS Studio converts text into speech using AI. Users can select a language, voice, and adjust pitch and speaking rate before generating audio.

Provides a web-based interface to plan and visualize layouts using the Gridfinity modular storage system, allowing users to design custom drawer configurations and print bin designs.

This tool converts Docker Compose files into Kubernetes manifests and a UDS Package definition, making them ready for deployment using Zarf. It translates Compose configuration into Kubernetes resources and creates a UDS Package Custom Resource (CR) for network policy, monitoring, and trust-bundle distribution.

Reflect provides a framework that enables AI agents to learn, reason and adapt by observing their runs, capturing feedback, and turning outcomes into reusable skills. It captures every trace an agent produces during its operations, evaluates performance based on set rubrics, and continuously refines strategies for better execution in future tasks.

Nori-Slack-CLI is a command-line interface that allows coding agents to interact with the full Slack Web API. It provides direct access without interactive prompts or ASCII art, returning JSON responses and handling errors efficiently.

Herald is a terminal email client designed to be intuitive and easy to set up, allowing users to read, search, clean up, compose, and manage emails directly from the terminal. It offers context-sensitive shortcut help and optional semantic search and rules for enhanced functionality.

Stanzio is a tool that uses AI to create presentations where each slide is designed using real HTML, allowing for more sophisticated and flexible design options.

Gauntlet is a lightweight test runner for Node.js that simplifies test execution by compiling TypeScript tests before running them. It discovers test files, compiles them into a cache folder, runs the tests using Node.js's built-in test module, and provides summary reports on test results. This approach enables type checking between tests and libraries at build time rather than just IDE time.

Git-issues is a native Git issue tracking tool where issues are stored directly within the repository as plain text Markdown files. This ensures that all issues move with your code and stay version-controlled without relying on external databases or servers.

Wan 3.0 is a next-generation AI video generator that creates 4K-resolution videos from text or image prompts, with enhanced multi-subject consistency and real-time camera controls. It builds on the iterative improvements of earlier Wan versions (2.5-2.7) to deliver production-ready content for marketing, social media, and pre-visualization.

This article argues that as latent reasoning flows like Coconut become stronger, the value of external memory, source tracking, and decision logs increases.

This essay argues that vibe coding shifts the software bottleneck from creation to discovery, making trusted editorial curation more important than launch-day ranking.

Responds to triggers like webhooks and cron schedules. Spins up AI coding agents in sandboxed Docker containers with your codebase, reports results back to your chat channel, and can require human approval before actioning. Runs entirely on local machine.

Gnosis creates a searchable knowledge base that records code-related decisions, rejected alternatives, constraints, and intent during AI agent sessions. It integrates with AI agents and stores information as JSONL files with SQLite search indexing, enabling developers to access accumulated context from previous agent interactions.

YubiClicker is a clicker game where each click is performed using a physical security key via FIDO2 assertions. Users can register a hardware security key to enter a public leaderboard competing with others by tapping their key.

TermToMD is a tool that transforms messy and inconsistent terminal outputs into structured, readable Markdown. It operates entirely on the client-side, ensuring privacy by not transmitting data.

Slerp.audio is a browser-based tool that provides an audio-reactive music visualization using WebGL shaders and Web Audio analysis, featuring DJ-style deck functionality. It allows users to load their own music files, adjust local playback settings such as EQ and tuning, and edit GLSL.

Provides a catalog of common failure patterns, decision trade-offs, warning signals, and practical playbooks in software development to help engineers avoid typical pitfalls and improve project outcomes.

Cell is a terminal spreadsheet editor that allows users to edit spreadsheets using Vim-like keybindings. It supports basic formula functions and can open, manipulate, and save data in CSV, TSV, or native .cell formats.

Converts inbound emails or cron jobs into structured HTTP POST events. Users can configure endpoints once and receive data in native formats such as Slack, Discord, Teams, Telegram, PagerDuty.

Provides an AI agent that answers customer inquiries on chat, phone, and WhatsApp 24/7. The agent improves itself by learning from every interaction, identifying unanswered questions, and enhancing its responses over time.

WorkSignal uses AI technology to conduct automated phone screenings with job applicants, providing recruiters with a detailed report including transcripts, scores, and behavioral signals after each call.

Doccupine converts Markdown or MDX files into modern, visually appealing documentation websites. It supports AI integration and offers customization options such as themes and visual editing features without requiring technical knowledge.

pglite-oxide embeds the Electric SQL PGlite WASI PostgreSQL runtime in Rust, providing Rust applications with a local Postgres-compatible database without requiring a native Postgres sidecar. It enables local Postgres semantics in Rust or Tauri apps, fast Postgres-backed tests without Docker, and provides PostgreSQL connection URIs for libraries like SQLx.

OgBlocks provides pre-built animated UI components designed for React developers. These components are built with React, Motion, and Tailwind CSS, and aim to help developers ship projects faster by reducing the need to create custom animations from scratch. Users can copy and paste components directly into their projects.

Omnihuman AI 1.5 converts a single image and audio input into film-grade digital human performances, including talking, singing, and storytelling videos with synchronized lip movements, emotional expressions, and cinematic camera control.

Aluqos solves the problem of traditional AI requiring extensive setup and prompting by watching how users work and then automating tasks. The service aims to reduce the burden on engineering teams by not needing engineers for setup, and it allows teams to scale from one hire to a full team without ever needing to migrate to a different product.

ChatForm allows users to create an AI-powered chat form by first creating a free form on Google Forms and then pasting a generated link. The service converts the Google Form into an AI chat form. It emphasizes ease of use without requiring user accounts, tracking, or payment.

Seedance 2.0 generates cinematic videos using text prompts, image references, video motion controls, and audio synchronization. It focuses on visual consistency, camera movement replication, and multi-modal editing for creators needing precise video output.

MemOperator-4B is a language model designed specifically for managing memory within the MemOS system. It excels in tasks such as extracting, organizing, and updating memories from both conversations and documents. The model offers faster performance with lower resource consumption compared to larger models like Qwen3.