All AI tools

Index any website and ask questions about it, with cited answers grounded in its content via RAG.

AgentRecall

Persistent cross-session agent memory that surfaces the most relevant past memories using the Intelligent Distance Protocol.

agentrender-mcp

Convert URLs into screenshots, PDFs or structured extracts.

agentrpc

Other AI tools

Connect to any function, any language, across network boundaries using AgentRPC.

AgentRun

AgentRun is a Python library for safely running Python code generated by large language models (LLMs). Built on the Docker Python SDK and RestrictedPython, it provides an API that executes isolated code in a single line. Key features include: checking code safety before execution, running in a fully isolated Docker container, configurable resource limits (CPU, memory, timeout), automatic dependency installation and uninstallation, dependency caching, automatic cleanup of generated files, and support for self-hosting via a REST API. The library has 97% test coverage, full static typing, and only two dependencies. It is suitable for scenarios that require letting LLMs execute code, such as mathematical calculations and data analysis, while preventing the execution of dangerous code.

Agentrunner

AI productivity

All-in-one AI workflow builder with visual prompt engineering and deployment tools.

agents

Collection of 112 agents + 146 skills + 73 specialized plugins for Claude Code — the largest to date.

Agents flex

Java-based LLM application framework similar to LangChain.

agents-cli

CLI and skill pack that turns any coding assistant (Claude Code, Codex, Gemini CLI, Cursor) into an expert at creating, evaluating, and deploying AI agents on Google Cloud.

agents-md-cookbook

Tool-agnostic AGENTS.md authoring kit (MIT) with 15 stack-specific templates, a tool compatibility matrix, an npm CLI + GitHub Action linter (`agents-md-lint`), and a migrator (`agents-md-migrate`) that converts `.cursorrules`, `CLAUDE.md`, Copilot, Windsurf, Cline, and Aider configs to AGENTS.md. W

AGENTS.inc

AGENTS.inc is an enterprise service provider offering autonomous AI agents (Agents-as-a-Service), focused on enterprise marketing, sales, and market intelligence scenarios. Its agents run on the enterprise's own data and can autonomously complete tasks such as market research, marketing campaign generation, and customer conversations. They have been put into production environments, with customers including Kaufland, AXA, E.ON, Petrobras, Henkel, and Messe München. The company was selected as one of 27 companies worldwide in the Everest Group Agentic AI Matrix, alongside Microsoft, Google, AWS, IBM, and Salesforce.

agents.md

An open standard for codebase documentation designed specifically for AI coding agents. Provides structured context, instructions, and constraints to help agents work more effectively and safely.

AgentScale

AgentScale is an enterprise-oriented AI automation platform. Its official introduction states that it uses robotic process automation (RPA), large language models (LLMs), and AI agents to provide automation solutions for enterprises. Currently, publicly available information contains only this one-sentence overview; information about specific functional modules, usage methods, applicable scenarios, platform support, pricing models, and other details is not yet available.

agentscore-mcp-server

Security trust layer that monitors MCP packages on npm for install scripts, command injection, hardcoded secrets, capability drift and publisher posture.

AgentSDR

AI marketing

Kandid is an AI sales agent tool for Shopify and D2C brands, offered in the form of AgentSDR. It can automatically greet visitors, answer product questions, recommend suitable products, and guide customers all the way to checkout on websites, WhatsApp, and Instagram. It supports adding to cart directly in chat, a unified inbox for managing multi-channel conversations, one-click handoff to a human agent, and can be trained on greetings, tone, knowledge, and handoff rules. It can be installed and deployed without code, provides a conversion data dashboard, and displays real-time metrics such as conversations, cart value, and orders. It is suitable for many categories including fashion, beauty, home, electronics, health, and automotive. Installation is free, with paid plans and usage fees available, subject to the Shopify App Store.

agentseal-mcp

Action logs for AI agents: records every action in a SHA-256 hash chain as an audit trail.

AgentServices

x402-paid crypto/market data APIs with 37 MCP tools for AI agents — BTC indicators, DeFi stats, macro data. USDC micropayments on Base.

agentset

Agentset is an open-source RAG platform for building, evaluating, and shipping production-grade RAG and agent applications. It provides an end-to-end toolchain from data ingestion, vector indexing, evaluation benchmarks, and a chat playground to managed deployment, with built-in capabilities such as citations, deep research, 22+ file formats, partitioning, and MCP servers. The platform is model-agnostic and can be paired with your choice of LLM, embedding model, and vector database, and it offers an API, typed SDKs, and an OpenAPI specification, with multi-tenancy support. The tech stack is based on TypeScript, Next.js, AI SDK, Prisma, Supabase, and Trigger.dev.

agentshare-mcp

Solana DeFi intelligence: Meteora DLMM pool briefs and details, Solana DEX data and DefiLlama scouting, plus secondary commerce tools.

agentskeptic

AgentSkeptic is a tool for verifying the true system state of AI agent workflows. By comparing structured tool activity records with the actual data in downstream databases (such as SQL), it detects silent failures where "the trajectory shows success but the stored data is inconsistent," and outputs a deterministic Outcome Certificate. The default path requires no API key or authorization, and supports local offline verification, CI integration, and frameworks such as Python/LangGraph/CrewAI.

AgentSkills

AI productivity

Historical third-party summary: An AI agent skills catalog for discovering reusable skill instructions, prompt templates and workflow materials through categories and search.

agentskit

AgentsKit is a toolkit for building AI agents in JavaScript, offering a lightweight core, React and terminal interfaces, an autonomous runtime, tools, skills, memory, RAG and observability capabilities, scalable plug-and-play from a chat interface to a full agent. Its core has zero runtime dependencies and enforces a 10 KB gzip budget via CI. Materials state that it includes 24 focused packages, 7 framework bindings, 25 native adapters, 50 integrations, 140 catalog providers, 5,000+ catalog models, 21 ready-made skills, 17 memory backends and 69 recipes. The project is independently developed by an individual; the core @agentskit/core has reached v1.12.8 with its API frozen at the minor version level, while the rest of the ecosystem is released on independent beta tracks with clearly defined stability tiers.

AgentSquare

AgentSquare is the official implementation of the paper "AgentSquare: Automatic LLM Agent Search in Modular Design Space," providing code, prompts, and results for automatically searching LLM agents in a modular design space, supporting tasks such as ALFWorld, WebShop, and SciWorld.

AgentStamp

AgentStamp — Trust, Verified. One Line of Code.

Agentstore

AI manga character chatbots with customizable features and NSFW options.

agentty

Native C++26 terminal coding agent and drop-in claude-code alternative. Single static binary, sub-millisecond cold start, sandboxed by default, and model-agnostic (Claude, OpenAI, Groq, OpenRouter, Ollama). Runs inside Zed over ACP and drives air-gapped hosts over SSH. MIT.

agentUniverse

agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications. Furthermore, through the community, they can exchange and share practices of patterns across different domains.

agentverse

AgentVerse is an open-source framework for deploying multiple agents based on large language models (LLMs), mainly providing two frameworks: task-solving and simulation. The task-solving framework assembles multiple agents into an automatic multi-agent system to collaboratively complete tasks such as software development and consulting; the simulation framework allows users to set up custom environments to observe or interact with the behavior of multiple agents, and is suitable for games, social behavior research, and more. The project supports the OpenAI API, Azure OpenAI, as well as local models such as LLaMA and Vicuna, provides CLI and GUI examples, and includes demonstrations such as an NLP classroom and the Prisoner's Dilemma.

Agentwallah

Premium AI tools and agents marketplace for boosting productivity and AI adoption.

agentwallet-mcp

Permissionless wallets for AI agents on EVM chains and Solana: wallet creation, transaction signing, token transfers and x402 payments in USDC.

agentward

MCP proxy that enforces least-privilege YAML policies on tool calls, classifies PII/PHI, detects dangerous skill chains and generates compliance audit trails.

agentwatch

Local-only TUI + web dashboard observing every AI coding agent on your machine (Claude Code, Codex, Gemini CLI, Cursor, Hermes, OpenClaw) on one unified timeline. Per-turn token + cost accounting with cache-hit weighting, MAD z-score anomaly detection, context compaction visualizer, hybrid semantic

AgentWP

Other AI tools

AgentWP is a collection of AI features integrated into WordPress.com, providing capabilities centered on WordPress websites such as AI website building, content writing, image generation and editing, design assistance, and AI agent connectivity. It includes the WordPress Agent that works within the editor, conversational management available through Telegram, and Studio Code (beta), which can build a complete WordPress site from a prompt and push it to hosting. Users can connect MCP-enabled AI tools such as Claude and ChatGPT to their sites to read, write, and manage content, comments, media, and more within authorized scope. The official documentation states that the related features require a paid plan; specific pricing is not provided.

Agentz ai

AI-driven digital receptionist for 24/7 customer engagement and task automation.

AgentZee