All AI tools

Email and SMS for AI agents via a local mail server: disposable inboxes, sending and receiving email, and fetching verification codes.

agenticos

AgenticOS is an open-source (Apache-2.0) self-hosted AI agent layer maintained by Vstorm, built on Pydantic AI, enabling enterprises to build, share, and govern AI agents on their own servers, models, and rules, with support for budgets, approvals, and audit records.

agenticpay

x402 micropayments stack for MCP: pay-per-tool-call USDC settlement on Solana via a self-hostable facilitator, with SDK, CLI and paywall middleware.

agentify

Agentify is an open-source command-line tool developed by MonadWorks for compiling OpenAPI/Swagger specifications into multiple interface files for AI agents. Starting from a single OpenAPI specification, it can generate up to 9 output formats, including MCP server, CLAUDE.md, AGENTS.md, .cursorrules, Skills, llms.txt, GEMINI.md, A2A, and CLI. The tool parses the specification into an intermediate representation, AgentifyIR, then generates artifacts in each format through pluggable emitters, and performs security scanning (input sanitization, prompt injection pattern detection, generated code scanning) before writing to disk. It is suitable for developers who want their APIs to be callable by AI agents, supports Swagger 2.0 and OpenAPI 3.x, and can handle APIs ranging from small (13 endpoints) to very large (1000+ endpoints).

agentinterviews_mcp

Run AI-led qualitative research interviews and surveys with Agent Interviews: create interviewers, manage projects, recruit participants and analyze results.

AgentK

AgentK is a self-evolving, modular autonomous agent AGI system, in which multiple agents collaborate and new agents can be built on demand to complete tasks. In its name, "K" stands for kernel, and the goal is to bootstrap itself with only the minimum agents and tools, then gradually grow its own "mind." AgentK's mind consists of two parts: the agents that collaborate to solve problems, and the tools used by the agents to interact with the external world. Both are developed as ordinary Python files (located in the agents and tools directories), making it easy to track progress and contribute. The system contains four core agents: Hermes is responsible for interacting with humans to understand goals, managing task creation and assignment, and coordinating other agents; AgentSmith is the architect, responsible for creating and maintaining other agents, ensuring they are equipped with the necessary tools and testing their functionality; ToolMaker is the tool developer, creating and optimizing the tools needed by agents to perform tasks; WebResearcher is the knowledge collector, conducting in-depth online research to provide the latest information and help agents make informed decisions. AgentK is built on the LangGraph and LangChain frameworks and runs in an isolated Docker container, requiring the latest version of Docker to be installed. To use it, copy .env.template to .env and set the environment variables.

AgentLab

AgentLab is an open-source framework for developing, testing, and benchmarking Web Agents, focusing on scalability and reproducibility. Provided by ServiceNow and built on BrowserGym, the framework supports large-scale parallel experiments and multiple benchmarks. AgentLab is primarily for research purposes and is not a consumer-facing product, so risks should be noted when using it. It provides foundational modules for building agents, unified LLM API support (OpenRouter, OpenAI, Azure, or self-hosted TGI), a recommended way to run benchmarks such as WebArena, multiple reproducibility features, and a unified leaderboard.

Agentlabs

AI assistants

UI as a service for building chat-based AI Assistants with built-in features.

agentleak

Other AI tools

AgentLeak is an open-source privacy testing tool for AI agents, providing a Python SDK, CLI, and MCP tools for detecting potential data leaks in execution channels such as tool calls, memory, inter-agent messages, and logs. It performs deterministic scoring on each execution trace (based on the AgentRisk risk index), generates redacted reports, and can set privacy gates in CI. All detection and scoring are performed locally, with no cloud dependency and no large model dependency, and data never leaves the user's machine.

agentlego

AgentLego is a tool API library open-sourced by the InternLM team, used to extend and enhance intelligent agents based on large language models (LLMs). It provides a rich set of multimodal tools covering capabilities such as visual perception, image generation and editing, speech processing, and vision-language reasoning, and supports flexible tool interfaces, allowing users to extend custom tools with any type of parameters and outputs. AgentLego can be easily integrated into mainstream agent frameworks such as LangChain, Transformers Agents, and Lagent, and also supports tool serviceization and remote access, making it convenient for use in scenarios that require heavy machine learning models (such as ViT) or special environments (such as GPU, CUDA).

agentlens

Tamper-evident AI agent observability: hash-chained audit log with verification and signed export (EU AI Act Art. 12), plus OpenTelemetry GenAI traces.

agentloop

AgentLoop is a Claude agent starter project built on Anthropic's official SDK and Next.js. Its core code is about 150 lines and fully implements streaming output and the tool-calling loop. It does not rely on any framework, nor does it include a huge SaaS template; after cloning, you can deploy it by adding an API key. The project uses the MIT license and provides two example tools (get current time, calculate) as well as a single-function extension point, making it easy for developers to add custom tools. In addition, the author also provides a free Agent Token Profiler tool for analyzing the token consumption of an agent in each round of conversation, and has published research on the token cost of open-source AI agents. AgentLoop Pro is a paid version that provides fixes for eight common problems in production environments, using a pay-as-you-go model starting at $9.

AgentMail

Email provider built specifically for AI agents, with dedicated inboxes, send-and-receive flows, persistent storage, and MCP-aware developer tooling.

agentmail

OFAC sanctions screening of names, wallets and countries before payment, via MCP, HTTP or CLI.

agentmail-mcp

Email for AI agents: create inboxes on the fly to send, receive and act on email.

agentmako

Local codebase intelligence backed by SQLite: context packets, indexed code and schema facts, diagnostics and optional Postgres/Supabase awareness.

Agentman

Other AI tools

Agentman is a platform that turns expert workflows into reliable AI software. It provides an Agentic Harness, which gives AI agents the tools, context, state, and checks they need to complete repeatable, high-stakes work according to team best practices, while keeping every step visible and every decision owned by a human. Its Medman product is aimed at independent medical clinics and is already in real-world use for tasks such as eligibility verification, inbox triage, and prior authorization. The platform also offers an Agent Skills library, 600+ MCP connectors, human review points, version control, and evaluations.

Agentmatch ai

AgentMatch.AI helps consumers find top real estate agents with unbiased recommendations.

Agentmaxx

AI agent analyzes facial attractiveness and provides personalized improvement tips.

agentmd-mcp

Convert PDF, DOCX, HTML and URLs to clean, LLM-ready Markdown with tables preserved and boilerplate stripped.

agentmem

Governed memory for coding agents with trust lifecycle (hypothesis, active, validated, deprecated), conflict detection, staleness tracking and health scoring.

agentmemory-codex-windows

Windows AgentMemory downstream for Codex with project-scoped persistent memory, bounded cross-project recall, and an authenticated loopback MCP service; prebuilt Windows releases a

agentnet

Agent-to-agent referral network where AI agents discover, recommend and refer users to each other, with a bilateral trust model and referral tracking.

AgentOne

AgentOne is a fully-featured AI agent desktop app that takes a goal in plain language and carries it out end-to-end across your apps. It connects 600+ AI models from 20+ providers (OpenAI, Anthropic, Google, xAI, Mistral, Groq, Cerebras, and more) with 2,000+ extensions for apps like Gmail, Notion,

AgentoolRank

AgentoolRank is a data-driven AI Agent tool directory website that ranks tools by GitHub activity and updates daily. The website currently tracks 621 tools and allows browsing by category, including frameworks, orchestration tools, coding agents, and more. Its notable feature is support for describing in natural language what you want to build, with AI recommending a tool stack. It also provides an open-source dataset, with all 621 tools available free of charge in JSON/CSV format and updated daily, and offers a weekly summary subscription for new AI Agent tools and trends.

agentops

AgentOps is a Python SDK for AI agent monitoring, LLM cost tracking, and benchmarking, supporting the development process from prototype to production. It automatically captures analytics data for all LLM calls, and sessions can be viewed in the AgentOps dashboard. AgentOps provides a first-class developer experience, adding powerful observability to agents, tools, and functions with minimal code (added line by line), supporting input/output recording, exception handling, async/await functions, generator functions, and custom attributes and names. It integrates with most LLM and agent frameworks, including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, CamelAI, Cohere, Anthropic, Mistral, LiteLLM, LlamaIndex, Llama Stack, SwarmZero, and more. The AgentOps application itself is open source under the MIT license.

AgentPace

Minimal macOS menu bar app that helps developers pace Claude Code and Codex usage across weekly and five-hour quota windows.

agentpack

Repo-native task continuity for coding agents: a reviewed task-state ledger of decisions, dead ends, evidence and checkpoints that later sessions resume from.

agentpay-vn

Non-custodial VietQR payments in Vietnam: generate a VietQR code for the user and auto-confirm settlement from the merchant's bank feed.

AgentPilot

AgentPilot is an open-source, multi-purpose workflow automation platform for creating, organizing, and executing AI workflows, from a single LLM to complex multi-member AI-driven processes. It provides an intuitive and feature-rich interface, supporting real-time chat, branching conversations, graphical workflows, nestable blocks and tools, custom UI, structured output, a code interpreter, and scheduled scheduling (an advanced feature). Users can create agents, manage conversation folders, save multi-member workflows as a single agent, and nest them indefinitely. The platform integrates LiteLLM to support 100+ models, integrates Open Interpreter to execute code in 9 languages, and supports plugins and module extensions.

agentplane

Local-first, Git-native CLI harness for repo-local coding-agent work, recording task state, accepted plans, verification evidence, and finish records inside the repository.

AgentPolis

A trading, social, and collaboration platform built specifically for AI Agents

Agentpro AI

We transform AI voice solutions to a strategic advantage for your business. We build and deploy autonomous AI voice agents with human-like conversational techniques that can handle a number of tasks for businesses. Our voice agents have customizable human-like voices, and can handle a variety of tas

Agentprobe

Free agentic commerce readiness scorer. Probes any URL across 13 signals (llms.txt, OpenAPI spec, MCP endpoint, catalog API, quote API, checkout, payment rails, fulfillment proof) and returns a 0–110 score with a CERTIFIED badge. MCP server available at /mcp.

agentradar-mcp