Agent Tools | AI Tools Directory

Accomplish

Accomplish is an open‑source AI desktop agent that runs locally to automate file management, document creation, and browser workflows. It supports bring‑your‑own API keys (OpenAI, Anthropic, Google, xAI, etc.) or fully local models via Ollama/LM Studio, offers user‑approved actions with logs, custom reusable skills, and integrations with tools like Notion, Google Drive, and Dropbox via local APIs. MIT‑licensed with installers for macOS and Windows 11.

ADK Python

ADK Python is an open-source, code-first Python toolkit by Google for building, evaluating, and deploying sophisticated AI agents. It offers a modular framework for creating both single and multi-agent systems, enabling flexible integration, testing, and deployment across various environments, including cloud platforms such as Cloud Run and Vertex AI Agent Engine. It is optimized for the Gemini and Google ecosystem while remaining model- and deployment-agnostic.

AG2

AG2 (formerly AutoGen) is an open-source software platform designed for building AI agents and facilitating multi-agent interactions to solve complex tasks. It supports integration with various large language models and provides various orchestration patterns for AI agents, enabling flexible and efficient tool usage and human collaboration.

Agent Zero

Prompt‑based AI agent framework with tools, instruments, projects, and MCP server integration.

Agentic Browser

An open-source AI agent designed for web automation and scraping. It orchestrates specialized agents (Planner, Browser, and Critique) to automate browser interactions such as form filling, data extraction, e-commerce searches, and content retrieval via a natural language interface.

AgenticSeek

An autonomous AI agent framework designed to run locally or on remote servers, offering both CLI and web interfaces for interaction and task automation.

Archon OS

Knowledge and task management backbone for AI coding assistants with agents, web crawling, RAG, and reranking services.

AutoGen

A programming framework by Microsoft for creating and orchestrating multi-agent AI workflows with an extensible design.

AutoGPT

Open platform to build, deploy, and manage continuous AI agents with benchmarking and agent protocol support.

Camel

Camel is an open‐source AI agent framework by camel-ai that provides multi-model integration, support for advanced LLMs (e.g., GPT-5, Claude 4.1), custom sandboxing, and workforce prompting features. Its active development is evident from its version releases on GitHub, demonstrating its capability to orchestrate AI agent workflows.

CrewAI

A framework for orchestrating autonomous AI agents, enabling role-playing and complex multi-agent workflows.

Dify

A production-ready platform for developing and deploying agent-driven workflows, enabling collaboration between multiple AI agents.

Dive

Dive is an open-source MCP Host Desktop Application that integrates with various large language models (LLMs) supporting function calling capabilities. It offers universal LLM support (including ChatGPT, Anthropic, Ollama, and more), cross-platform compatibility (Windows, macOS, Linux), and advanced features like custom instructions, API management, and auto-update mechanisms via the Model Context Protocol (MCP).

elizaOS

A framework for creating autonomous agents, featuring connectors for Discord, Twitter, and Telegram, support for various AI models, multi-agent functionality, document ingestion, and memory storage capabilities.

Evo AI

Open-source AI agents platform featuring multiple agent types (sequential, parallel, workflow), UI+backend, A2A protocol, and tracing via Langfuse.

Gemini CLI

Open‑source AI agent CLI by Google with built‑in tools, MCP server integration, and scripting

GitHub MCP Server

GitHub’s official Model Context Protocol (MCP) server that lets AI agents and chat assistants securely access GitHub context and actions via natural language. It enables repository browsing and code search, issue/PR creation and management, Actions/workflow insights, security findings and Dependabot alerts review, and team collaboration data. Supported as a remote, GitHub‑hosted MCP server (OAuth or PAT) with quick setup in VS Code 1.101+ and other MCP hosts; a local server option is also available.

HumanLayer

An API and SDK enabling AI agents to communicate with humans for help, feedback, and approvals during complex workflow management.

II-Agent

II-Agent is an open-source intelligent agent framework that streamlines and enhances workflows across multiple domains. It provides a CLI interface and a WebSocket-powered, React-based frontend, and integrates with several leading language model providers (e.g., Anthropic Claude and Google Gemini). It also includes performance evaluation on the GAIA benchmark.

JARVIS

JARVIS is an AI system developed by Microsoft that connects large language models with expert AI models from the ML community. It orchestrates task planning, model selection, and execution by leveraging multiple approaches (CLI, Gradio demo, web APIs) and supports integration with cloud and local deployments.

leon-ai/leon

An open-source personal assistant that runs on your own server, providing a customizable, self-hosted AI assistant experience.

Letta

Open-source agent framework with new v1 agent architecture, parallel tool calls, human-in-the-loop tool execution, and improved memory search.

Manus AI

Manus AI is an autonomous AI agent designed to execute complex tasks across multiple domains, including report writing, data analysis, content generation, and more. It features multi-modal capabilities, advanced tool integration (e.g., web browsers, code editors, database systems), and adaptive learning to optimize performance. The tool claims state-of-the-art performance on the GAIA benchmark, positioning itself as a competitive alternative to leading AI models.

MCP Calculator

Xiaozhi MCP sample program is an open-source project demonstrating the Model Context Protocol (MCP), which enables language models to invoke external tools such as calculators, email operations, knowledge search, and more. It features secure WebSocket communication, real-time streaming, automatic reconnection, and a simple interface for tool creation.

MCP Toolbox for Databases

MCP Toolbox for Databases is an open source MCP server that simplifies building Gen AI tools for database access. It handles complexities such as connection pooling, authentication, and observability, enabling seamless integration of database functionalities into AI workflows.

monday.com MCP (Agent Toolkit)

Open framework and tools for connecting AI agents to monday.com via MCP, enabling secure access to structured data and actions.

Nanobrowser

Open‑source Chrome extension for AI web automation with multi‑agent support and flexible LLM backends.

Nodetool

Nodetool is an agent framework that offers intelligent agent nodes supporting all LLM providers, a comprehensive tool suite, and advanced workflow management features including node visualization, global shortcuts, and integrations with services like Brightdata, Gemini, and Ollama. It also includes document and media processing nodes for PDF extraction and text-to-speech, along with core platform enhancements.

NVIDIA AgentIQ

An open-source toolkit for connecting and optimizing teams of AI agents by treating agent workflows as simple function calls, ensuring composability and scalable agent orchestration.

OpenAI Agents Python

A lightweight and powerful framework for multi-agent workflows built on LLMs, complete with built‐in agent tracing and management.

OpenManus

OpenManus is an open-source project that replicates the capabilities of the Manus AI agent by providing a modular, containerized multi-agent framework. It enables autonomous execution of complex tasks such as travel planning, data analysis, and content generation, and is built with Docker, Python, and JavaScript.

ottomator-agents

A GitHub repository hosting a collection of open-source AI agents built for the oTTomator Live Agent Studio platform. This repository contains various agents that perform tasks such as web research, content generation, and automation. It serves as a hub for deploying and experimenting with multiple AI agents and is actively maintained under the MIT license.

OWL

OWL (Optimized Workforce Learning) is an open-source multi-agent collaboration framework built on top of the CAMEL-AI Framework. It enables dynamic agent interactions and integrates various toolkits (such as web search, file writing, terminal execution, and browser automation) to facilitate robust and efficient task automation across real-world domains.

PALITRA.ai Beta

An AI tool in beta phase that transitions from passive tools to autonomous agents handling sensitive information, offering functionalities such as user activity review.

Pipecat

An open-source Python framework for building real-time voice and multimodal conversational agents that includes robust handling of transcription data.

RobotPai

RobotPai is an AI-driven autonomous agent project hosted on Hugging Face Spaces. It integrates large language models with multiple tool bindings (including search, retrieval, and state graph management) to provide conversational assistance and dynamic tool orchestration. The commit shows updates to system prompt handling, retrieval tool integration, and LLM bindings.

Second Me

Second Me is an open‐source platform that lets you train and deploy a personalized AI self. It uses hierarchical memory modeling and the Me-Alignment Algorithm to capture your memories and identity, enabling your AI to switch roles, collaborate on a decentralized network, and serve as a private, self-hosted personal assistant.

Sim

Open‑source platform to build and deploy AI agents with Ollama or vLLM, Web UI, and pgvector‑powered knowledge bases; supports Docker and self‑hosting.

Smolagents

A barebones framework for building AI agents that support multi-modal inputs and tool integration.

smolagents

An open-source Python library that simplifies building and running AI agents with minimal code, complete with CLI tools and memory management features.

SmythOS

SmythOS lets you build and deploy AI agents without manual coding. Describe your needs, and Agent Weaver creates it automatically using the best AI models and APIs. Integrate with OpenAI, Hugging Face, Amazon Bedrock, and more—no manual coding required.

Suna (Kortix)

Open‑source platform to build, manage, and train AI agents with workflows, browser automation, data layer, and self‑hosting.

SuperAGI

A dev-first open source autonomous AI agent framework designed for building, managing, and running autonomous agents.

surf.new

Open-source alternative to OpenAI Operator for testing web agents with real-time browser interaction and support for multiple AI providers.

Swarm

An experimental, educational framework by OpenAI for lightweight multi-agent orchestration. Swarm enables agents to offload tasks through simple handoffs and demonstrates scalable, stateless agent interactions using the Chat Completions API. Note that it has been superseded by the production-ready OpenAI Agents SDK.

WebAgent (WebWalker & WebDancer)

WebAgent is an open-source autonomous agent framework by Alibaba Group for information seeking. It comprises two complementary systems: WebWalker, a benchmark for LLMs in web traversal (ACL2025), and WebDancer, a native agentic search reasoning model (Preprint). Utilizing the ReAct framework with a four-stage training paradigm including supervised fine-tuning and reinforcement learning, it is designed to handle long-horizon, multi-step web traversal and autonomous search tasks.