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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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

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.

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.

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.

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.

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.

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.

Aether is an open-source core compiler for the Aether Agent Reliability Framework. It replaces fuzzy prompts with strict Weighted Intent Token (WIT) vectors to prevent Context Rot. The framework helps maintain consistent behavior in LLM agents by using precise vector representations instead of ambiguous natural language prompts.

PatchWork reads and analyzes all of your uploaded documents to create an accurate master profile. It then uses this information to generate a tailored resume for each job application, ensuring you meet the specific requirements emphasized in the job description without manual effort.

Polynya allows users to stream data from PostgreSQL databases to Iceberg format, creating isolated analytical environments for AI agents. It provides a fresh and secure querying layer without impacting production data.

ReadTube converts YouTube subscriptions into a structured, distraction-free reading format. It uses AI to generate multi-level summaries and articles from long-form video content, allowing users to consume information without scrolling or watching videos. The platform provides a searchable archive of transcripts, summaries, and user annotations.

MCP Spine is a local-first proxy that sits between an LLM and MCP servers, providing security, routing, token control, and compliance. It offers features like rate limiting, secret scrubbing, semantic routing, schema minification for token savings, state guard for file version control, and a plugin system for custom middleware hooks.

Happy Horse Video Generator converts textual descriptions or uploaded images into high-quality videos in various styles such as cinematic, anime, artistic, and realistic. Users can customize video settings like resolution, duration, and aspect ratio to match their creative vision.

NoonFlow is a macOS application designed to enhance developer productivity by integrating AI tools like Claude Code and Codex. It provides features such as server management, dashboard optimization, and improved interaction with external services.

Bunny Agent is a coding agent built on Pi Coding Agent, enabling developers to build and deploy coding agent SaaS solutions via a native AI SDK UI. It supports multi-model AI runners (Claude, Gemini, OpenAI, etc.) and integrates with remote sandboxes for development tasks.

Analyzes facial features using 17 metrics such as symmetry, canthal tilt, and facial width-to-height ratio (FWHR). It provides an attractiveness score, shopping suggestions, and comparisons to celebrity faces through web-based AI models. Results are generated via browser using TensorFlow.js without storing any user data.

Stash provides a memory layer for AI agents that allows them to remember user interactions across sessions using PostgreSQL and pgvector. It helps maintain continuity in conversations without requiring users to repeat information.

Useknockout provides a background removal API that processes images to produce transparent PNG outputs. It uses BiRefNet, a state-of-the-art model for background removal tasks, to deliver high-quality results with fast processing times and at a significantly lower cost than competing services like remove.bg.

LLMCat is a command line interface tool designed to automatically format and clean up messy codebases, making them suitable for use with large language models (LLMs). It supports multi-file processing and allows users to configure output preferences through settings files.

FalsoAI uses behavioral AI trained on persuasion science to detect cognitive manipulation patterns in digital content. It analyzes how content influences perception through tactics like emotional escalation, narrative framing, and identity signaling, rather than just verifying factual accuracy. The platform provides a structured report on detected influence techniques and their impact on the audience's perception.

cctape is a local proxy that archives every request and response made through Claude Code, offering features such as full-text search across sessions, tracking of token usage and cost, and an MCP server for Claude to access past session data.

Provides an AI-driven platform for engaging with services provided by the Los Angeles Homeless Services Authority, a joint city and county authority in charge of the HUD-funded Los Angeles Continuum of Care.

Abodex is an AI-driven real estate platform that helps users find properties in Bangalore without sharing their contact information. It streamlines the search process through a four-step chat-based system, matching new property launches to user preferences and allowing them to shortlist and schedule visits within the same interface.

PhotoSharpener uses AI to sharpen and upscale blurry or low-resolution photos into clear, crisp images. It removes noise, restores lost detail, and enhances edges without manual adjustments.

DeepSeek V4 is an advanced AI model designed to support extensive context with a large memory capacity of up to 1 million words. It offers quick response times, enhancing user interaction.

MirrorNeuron is a platform that allows users to create and run reliable AI workflows using pre-built blueprints, simplifying the process from initial setup to deployment on various platforms like laptops, edge nodes, clusters or cloud environments.

Provides instant, real-time pricing and financial metric reports for stocks. Includes analyst consensus, earnings data, and news sentiment analysis.

SketchTutor is a tool that uses artificial intelligence to generate step-by-step drawing tutorials from any uploaded photo. It breaks down the process into simple stages, allowing users to follow along at their own pace and build real drawing skills such as proportion and shading.

AISBF provides intelligent routing, load balancing, and failover across multiple AI providers. It allows building resilient AI applications with a single unified API. The service supports multi-provider integration with Google, OpenAI, Anthropic, Ollama, and more, enabling seamless switching between providers without code changes.

Vibeyard is an open-source IDE designed to help users manage multiple AI coding agent sessions. It allows running agents in parallel, tracking costs, and maintaining context, with support for Claude Code, Codex CLI, and Gemini CLI. The IDE includes features like multi-session management, cost tracking, and session resume capabilities.

Viscacha is a Python library that provides background jobs and AI workflow execution without requiring additional infrastructure like Redis or Docker. It ensures that each task is safe from crashes, retriable automatically, and fully traceable in the system logs.

This project offers an easier-to-use JavaScript API that simplifies the process of interacting with Chrome’s built-in machine learning capabilities for language processing, aimed at developers who want to leverage these features without extensive setup.

Kumbukum is an open-source solution designed to provide persistent, inspectable, and reusable memory for AI tools used within a team. It addresses the issue of AI assistants not retaining past interactions or shared context across different sessions or tools.

Conveen is an AI-driven chat app that analyzes individual and group preferences to suggest the best options. It uses a unified stack of Firebase, Gemini, and Genkit to provide real-time suggestions without switching between multiple apps or services.

Archon-memory-core is a Python library designed to address the issue of contradictory statements from users within agent systems. It simulates a scenario where users frequently change their minds about facts and evaluates which memory system can effectively handle such inconsistencies over time.

Esp-Claw is a framework designed to enable devices in the Internet of Things (IoT) ecosystem to make decisions locally, without relying on cloud services. It supports natural language input to define device behavior through conversations between users and an AI agent that utilizes both machine learning models and Lua scripts for rule-based operations.

Galen Voice takes spoken language and converts it into structured instructions that can be understood by AI agents, APIs, automation tools, and enterprise software. It uses a single instruction format that works across multiple AI systems, industries, and languages.

Pixicular offers a REST API that provides various services like age detection, object labeling, text extraction from images, among others. It ensures sub-second response times and high accuracy.

Open WebUI is a platform that enhances developer workflows with AI integration. It provides features like a native desktop app for Mac, Windows, and Linux, enabling users to run the application locally without server setup. It also introduces scheduled chat automations for recurring tasks. The platform includes automation tools in chat, allowing users to manage tasks directly within conversations. Additionally, it offers a calendar workspace for managing events and reminders, improving productivity.

Provides a leaderboard ranking various AI models based on their ability to write secure code when challenged with conversational tasks. It measures the security score of each model's responses.

Agentathon is a hackathon platform designed for AI agents to enroll, develop projects, and submit entries autonomously. The agents engage in competitions across various categories without human intervention.

FitToHire uses a single shared encoder to analyze job descriptions and resumes, identifying deep technical expertise and specific requirements more accurately than traditional keyword matching tools. It operates on an affordable $11/month VPS, offering detailed insights in under 10 seconds without requiring signup or credit card information.

A platform that allows users to test the resilience of artificial intelligence agents through a series of challenges. The AI becomes progressively more intelligent with each round, and players can assess its vulnerabilities.

Provides an AI assistant to help manage emails, calendars and tasks directly within the Chrome browser. Connects with Outlook, Google accounts and WhatsApp (for ActorDo users).

Agensi is a platform where developers can buy and sell reusable AI skills that enhance their agents' capabilities. It offers a secure, curated selection of pre-built skills, each reviewed for security and compliance with industry standards.

Kachilu Browser is a command-line interface (CLI) tool that enables automated interactions with web browsers. It allows AI agents to control the browser and handle challenges like CAPTCHAs by detecting them and routing completion through a local flow.

Mimi takes a 24 kHz audio waveform and converts it into 32 token streams. The first stream captures phonetic content (what is being said), while the remaining streams carry acoustic details such as timbre and texture. This split allows users to manipulate and control different aspects of audio independently.

Provides simplified, AI-generated summaries of US federal laws, bills, and executive orders for easier understanding. It covers recent and trending legislation as well as new executive orders.

Provides a source-first workflow for managing context and execution rules for multiple AI coding agents. It allows users to write prompts once in a canonical file and project them into various agent-specific formats, ensuring consistency across different tools.

AI Applyd automates the job application process by scanning job boards, tailoring resumes to match job requirements, and submitting applications. It rewrites resumes for ATS compatibility, tracks the application pipeline, and provides interview preparation tools. A key feature is verified application submissions with proof screenshots and real-time application status tracking.

Provides sales forecasting services by uploading a CSV file with date and value columns. Users can configure the forecast period and view interactive charts of predicted sales.

The SerpApi Claude Code Skill allows developers to integrate SerpApi into the Claude code environment, enabling advanced internet searches across various engines like Google, Amazon, and more via REST API. It supports automatic invocation based on intent, cost-aware mode selection, and updates engine parameter schemas weekly.

I Spy AI provides a tool to instantly detect whether an image is generated by AI or manipulated using deepfake technology. It supports JPEG, PNG, and WebP formats up to 15MB in size. The service can be integrated into various MCP-compatible AI agents for extended use.

Enables LLMs to perform any task in the browser by directly interacting with Chrome DevTools Protocol (CDP), providing real-time code updates as needed without pre-defined scripts or frameworks. It operates on a minimal Python setup, consisting of around 592 lines of code including helper functions and administrative tasks.

Modular allows developers to integrate full-featured AI capabilities into their applications by simply adding a few lines of code. It manages the context, embeddings, chat history, and retrieval processes, enabling faster development cycles without extensive infrastructure setup.

Developerpod is a tool for developers to create custom AI-based development utilities using TOML files. It handles context gathering and API calls with structured output provided by the user-defined schema in TOML.

Provides an all-in-one solution for businesses to manage customer support through AI agents, visual workflows, omnichannel inbox, ticketing system, and knowledge base without requiring coding skills. Deployment is quick, allowing immediate use after just five minutes setup.

Passmark is an open-source tool that leverages AI to execute natural language steps through the Playwright framework, performing end-to-end browser regression tests. It provides intelligent caching, auto-healing, and multi-model assertion verification to ensure test stability without frequent updates or retraining of AI models.

This service allows users to input a textual description of a diagram, and it generates an interactive Excalidraw representation within the user's web browser. The process uses compact code generated by LLMs and TurboQuant algorithm for efficient processing on GPU.

Proposly generates professional, tailored client proposals within 30 seconds by using AI to create personalized and context-specific content. Users describe their project details and select a tone before receiving a complete proposal ready to send via email or PDF export without any further editing required.

Scans your Claude Code installation for cross-project duplicates, unused skills, agents, and MCPs. Offers a user-guided fix to remove unnecessary tokens from the context window.

AgentKey provides secure, on-demand access to API credentials for AI agents. Instead of storing sensitive keys in .env files, agents request credentials as needed and administrators approve each request. This prevents credentials from being hardcoded into agent implementations while maintaining proper access controls.

Customer Voices allows customers to leave voice reviews using their own voice or AI-generated text. Businesses can respond with personalized voice replies and showcase these reviews on their websites.

AgentRQ is a real-time task management platform where both agents and humans can collaborate. It allows agents to assign tasks to humans and humans to assign tasks back to agents, enabling them to work simultaneously. The platform supports multiple agents running in parallel through separate workspaces.

Sky Style uses hyper-local weather data and AI to recommend outfits that help users avoid overdressing or underdressing. Users can share their location or enter a city, and the service finds the nearest weather station to provide accurate real-time weather information. The AI stylist then analyzes conditions like temperature, rain, wind, and UV and suggests appropriate clothing.

Provides a wide range of open-source text-to-speech (TTS) models and over 200 voices in more than 33 languages. Users can generate speech from various file types without needing an account, and enjoy commercial use with no credit card required.

GAI provides a flexible and idiomatic framework for building agent-style applications using LLMs. It includes a generic interface for providers and models, prompt and context helpers, and a loop for agentic-calling workflows. The library supports multiple providers and models and allows developers to implement custom providers, tools, and session management.

BR-FVD is a service that verifies the authenticity of AI-synthesized voices. It offers both general and personalized models optimized for multiple speakers and specific individuals, respectively.

devnexus provides a shared knowledge base for AI agents to retain decisions, architecture, and API contracts across software development sessions and engineering teams. It creates an Obsidian vault linked to repositories where AI agents read from before writing code. This allows context and decisions to persist between sessions, eliminating redundant work as agents learn from previous discoveries.

Cogveo provides a shared AI workspace for teams to collaborate on projects. Users can upload files, interact with an AI agent using Python to process data, and receive results via email.

Players have 60 seconds to explain as many words as possible to their AI teammate in real time. The game features a leaderboard displaying live rankings and player runs, which are visible publicly or can be saved privately after signing in.

This service is a full-stack SaaS platform focused on facilitating charitable giving, developed by a solo developer using agentic AI technology to streamline operations and enhance functionality.

Mabon is an AI job agent that scans the web continuously and surfaces only roles that truly match your profile, preferences, and location. It aims to show relevant job roles without making users manually check job boards and scroll through irrelevant listings.

mcp.hosting provides a centralized cloud platform to manage Model Context Protocol (MCP) servers. It allows users to add, remove, and edit MCP servers through a web interface, with changes syncing across all connected clients. The service uses smart routing to select appropriate tools based on task requirements.

resolved.sh provides a platform for users to create instant websites for their AI and generate revenue by selling specialized datasets, files, premium reports, blogs, courses, and other content. The service handles account creation, page setup, and monetization through features like data storefronts, API endpoints, and payment integrations. Revenue from sales goes directly to the creator with no platform fees.

l6e acts as an MCP server that adds a budget constraint to AI agents working with Cursor, Claude Code, and Windsurf. It checks each operation against a set budget before execution, ensuring agents adapt their behavior to stay within cost limits while maintaining task integrity.

Provides 193+ simple, fast, privacy-first tools that run locally in the browser. Includes AI tools for text summarization, sentiment analysis, and email writing, along with developers tools for JSON/UUID handling, Base64 encoding, regex testing, and more.

Mallary provides a unified API and dashboard for publishing, engaging, and responding across multiple social media platforms. It allows users to schedule posts, automatically add initial comments, and manage AI-powered replies. The service handles platform-specific challenges like authentication, rate limits, and API changes.

chat-rs provides a unified Rust framework to interact with multiple large language model providers (Gemini, Claude, OpenAI). It supports type-safe client construction, tool calling integration, structured output parsing, streaming responses, embeddings generation, and provider-agnostic request routing. Developers can switch between AI providers with single-line code changes while maintaining consistent API usage patterns.

These agents perform tasks provided by project owners, who post global issues and break them down into smaller tasks for the agents to complete.

Undisk MCP provides a file system with an undo function that restores any file in under 50 milliseconds. It creates an immutable version every time a file is written, and includes policy guardrails, secret detection, and tamper-evident audit trails.

PRESS START is a multi-product startup that offers a variety of services, including creating personalized bedtime stories for kids, document AI for better research and writing, and tools for brand positioning and democratic education.

Claude Code automatically scrapes Hacker News daily at 15:00 UTC to find LLM-related applications. It tests these apps in isolated Docker containers and evaluates them across 11 criteria. The service provides scores and recommendations based on the evaluation results.

This API converts any image into a shoppable recommendation engine, enhancing customer discovery and engagement on e-commerce platforms.

Proxima Fitness uses a science-backed AI to create customized periodized fitness plans tailored to individual goals such as hypertrophy, powerlifting, weight loss, and body recomposition. Users can start from scratch or choose predefined templates like Beginner SBD, Hypertrophy PPL, Powerlifting Peak.