Alternatives to Open Computer Agent
Compare Open Computer Agent alternatives for your business or organization using the curated list below. SourceForge ranks the best alternatives to Open Computer Agent in 2026. Compare features, ratings, user reviews, pricing, and more from Open Computer Agent competitors and alternatives in order to make an informed decision for your business.
-
1
OpenClaw
Molty
OpenClaw is an open source autonomous personal AI assistant agent you run on your own computer, server, or VPS that goes beyond just generating text by actually performing real tasks you tell it to do in natural language through familiar chat platforms like WhatsApp, Telegram, Discord, Slack, and others. It connects to external large language models and services while prioritizing local-first execution and data control on your infrastructure so the agent can clear your inbox, send emails, manage your calendar, check you in for flights, interact with files, run scripts, and automate everyday workflows without needing predefined triggers or cloud-hosted assistants; it maintains persistent memory (remembering context across sessions) and can run continuously to proactively coordinate tasks and reminders. It supports integrations with messaging apps and community-built “skills,” letting users extend its capabilities and route different agents or tools through isolated workspaces.Starting Price: Free -
2
Lux
OpenAGI Foundation
Lux is a powerful computer-use AI platform that enables agents to operate software just like a human user—clicking, typing, navigating, and completing tasks across any interface. It offers three execution modes—Tasker, Actor, and Thinker—giving developers the ability to choose between step-by-step precision, near-instant task execution, or long-form reasoning for complex workflows. Lux can autonomously perform actions such as crawling Amazon data, running automated QA tests, or extracting insights from Nasdaq’s insider activity pages. The platform makes it possible to prototype and deploy real computer-use agents in as little as 20 minutes using developer-friendly SDKs and templates. Its agents are built to understand vague goals, execute long-running operations, and interact naturally with human-facing software instead of relying solely on APIs. Lux represents a new paradigm where AI goes beyond reasoning and content generation to directly operate computers at scale.Starting Price: Free -
3
Gemini 2.5 Computer Use
Google
Introducing the Gemini 2.5 Computer Use model, a specialized agent model built on top of Gemini 2.5 Pro’s visual reasoning capabilities, designed to interact directly with user interfaces (UIs). It is exposed via a new computer-use tool in the Gemini API, with inputs that include the user’s request, a screenshot of the UI environment, and a history of recent actions. The model generates function calls corresponding to UI actions like clicking, typing, or selecting, and may request user confirmation for higher-risk tasks. After each action is executed, a new screenshot and URL are fed back into the model to continue the loop until the task completes or is halted. It is optimized primarily for web browser control and shows promise for mobile UI interaction, though it is not yet suited for desktop OS-level control. In benchmarks across web and mobile control tasks, Gemini 2.5 Computer Use outperforms leading alternatives, delivering high accuracy at lower latency.Starting Price: Free -
4
Qwen2.5-VL
Alibaba
Qwen2.5-VL is the latest vision-language model from the Qwen series, representing a significant advancement over its predecessor, Qwen2-VL. This model excels in visual understanding, capable of recognizing a wide array of objects, including text, charts, icons, graphics, and layouts within images. It functions as a visual agent, capable of reasoning and dynamically directing tools, enabling applications such as computer and phone usage. Qwen2.5-VL can comprehend videos exceeding one hour in length and can pinpoint relevant segments within them. Additionally, it accurately localizes objects in images by generating bounding boxes or points and provides stable JSON outputs for coordinates and attributes. The model also supports structured outputs for data like scanned invoices, forms, and tables, benefiting sectors such as finance and commerce. Available in base and instruct versions across 3B, 7B, and 72B sizes, Qwen2.5-VL is accessible through platforms like Hugging Face and ModelScope.Starting Price: Free -
5
Gobii
Gobii
Gobii is a cloud-hosted platform that enables you to spin up fully managed browser-automation agents via API, allowing tasks like web-based research, form-filling, data extraction, and multi-step workflows to be automated at scale. These agents operate like “always-on employees” that can browse websites, even those without APIs, navigate dynamic content, handle JavaScript, and even rotate proxies automatically. Users can create agents, assign them prompts or tasks, and retrieve structured JSON outputs or live previews of the agent’s browser actions. Gobii supports synchronous and asynchronous task execution, secret handling for things like login credentials, schema-enforced output validation, and integrates with popular programming languages (Python, Node.js) for seamless implementation. The platform emphasises scalability (hundreds of tasks in parallel), enterprise-grade security (audit logs, proxies, task management), and a simple developer experience.Starting Price: $30 per month -
6
Jace
Zeta Labs
Meet your new AI assistant and focus on meaningful things. A groundbreaking digital assistant, JACE represents the future of AI agents, going beyond traditional uses of current AI chatbots like ChatGPT and their text-generation focus. Instead, JACE focuses on taking action in the digital world. It differs from existing AI-powered chatbots due to its complex cognitive architecture, which enables it to complete high-difficulty tasks. JACE can control and perform actions in the browser similarly to a human user, excelling in managing complex tasks that involve web automation, interaction, and direct communication. This is due to the development and training of Zeta Labs’ proprietary web-interaction model, AWA-1 (Autonomous Web Agent-1), which enables JACE to reliably execute tasks over long periods of time, effectively handling the challenges and inconsistencies commonly found in web interfaces.Starting Price: $20 per month -
7
Surfer H
H Company
Surfer H from H Company is an autonomous web-agent platform built to understand and navigate user interfaces like a human by combining three modular models; a policy model that plans tasks, a localizer model that identifies UI elements visually, and a validator model that checks outcomes. The agent works purely through the browser interface with no special API hooks, enabling it to scroll, click, type, and complete real-web tasks such as booking hotels, comparing product deals, or extracting structured information. When paired with H Company’s open-weight vision-language models, Surfer H achieved state-of-the-art performance on the WebVoyager benchmark (92.2% accuracy at around $0.13 per task) and supports deployment locally, via Docker, or on cloud infrastructure. Use cases span web automation, QA testing without brittle scripts, data harvesting, and intelligent workflow agents that interact with the web directly as a human would.Starting Price: $0.13 per task -
8
Smolagents
Smolagents
Smolagents is an AI agent framework developed to simplify the creation and deployment of intelligent agents with minimal code. It supports code-first agents where agents execute Python code snippets to perform tasks, offering enhanced efficiency compared to traditional JSON-based approaches. Smolagents integrates with large language models like those from Hugging Face, OpenAI, and others, enabling developers to create agents that can control workflows, call functions, and interact with external systems. The framework is designed to be user-friendly, requiring only a few lines of code to define and execute agents. It features secure execution environments, such as sandboxed spaces, for safe code running. Smolagents also promotes collaboration by integrating deeply with the Hugging Face Hub, allowing users to share and import tools. It supports a variety of use cases, from simple tasks to multi-agent workflows, offering flexibility and performance improvements. -
9
Surf.new
Steel.dev
Surf.new is a free, open-source playground for testing and using AI agents that can browse the web. These agents surf the web and interact with webpages similarly to how a human would, making tasks like automation and web research easy and intuitive. Whether you're a developer evaluating web agents for production use or someone looking to automate repetitive tasks like checking flights, scraping product information, or booking reservations, Surf.new provides an accessible environment to quickly experiment and see how web agents perform. Key Features: Swap between AI Agent Frameworks with a button: Supports Browser-use, an experimental Claude Computer-use-based agent, and integrates smoothly with LangChain—allowing easy experimentation with different approaches. Diverse AI Model Compatibility: Compatible with popular models including Claude 3.7, DeepSeek R1, OpenAI models, Gemini 2.0 Flash, and others—giving you the flexibility to choose what works best. -
10
Bytebot
Bytebot
Bytebot is a desktop agent platform that automates real work by using computers the same way a human does. It spins up a fresh, sandboxed desktop in the cloud and completes tasks by clicking, typing, and navigating apps through the user interface. Bytebot works across any software because it interacts directly with the screen, keyboard, and mouse. Users can scale from a single agent to hundreds running in parallel. The platform includes a full computer environment with a browser, file system, terminal, and code editor. Bytebot supports guided recovery, allowing users to step in and resume tasks if needed. It provides detailed logs and screenshots for full transparency and control.Starting Price: Free -
11
NanoClaw
NanoClaw
NanoClaw is a lightweight, open-source personal AI assistant that runs securely inside Linux containers. Designed as a simplified alternative to larger frameworks, it connects Claude Code to WhatsApp and enables autonomous task execution with isolated group contexts. Each group operates in its own container with a dedicated filesystem and memory file, ensuring strong OS-level security rather than application-level permission checks. The system runs as a single Node.js process with a minimal codebase that users can understand and modify quickly. NanoClaw supports scheduled tasks, web access, and optional integrations through modular Claude skills. It introduces Agent Swarms, allowing multiple specialized agents to collaborate within a single chat. Built for individual users rather than enterprises, NanoClaw emphasizes customization through direct code changes instead of configuration files.Starting Price: Free -
12
Anchor Browser
Anchor Browser
Anchor Browser is a cloud-hosted platform designed to enable AI agents to interact with the web in a human-like manner. It provides secure, authenticated environments where AI can navigate web pages, submit forms, and extract data in real time, facilitating the automation of web-based tasks that lack traditional APIs. The platform offers features such as full browser isolation, seamless VPN integration, and support for identity providers like Okta and Azure AD. Additionally, it includes automated CAPTCHA resolution, advanced anti-bot detection bypass, and custom session fingerprinting to ensure undetectable browser behavior. Anchor Browser is designed for scalability, allowing unlimited concurrent browsers, session durations, and deployment in any geo-location. It provides developers with full control over browsers through CDP, Playwright, APIs, or direct integration with agent frameworks, supporting any programming language.Starting Price: $0.05 per hour -
13
LobeHub
LobeHub
LobeHub is an open-source AI platform that lets users create, customize, and manage AI agents and assistant teams that grow with their needs, enabling collaboration across workflows and projects with shared context and adaptive behavior. It supports multiple AI models and providers through an intuitive interface, allowing seamless switching and conversations across models while integrating knowledge bases, plugins, and task-specific skills for enhanced productivity. Users can deploy private chat applications and assistants, connect agents to real-world tools and data sources, and organize work into projects, schedules, and workspaces with coordinated agents executing tasks in parallel. LobeHub emphasizes long-term co-evolution between humans and agents through personal memory and continual learning, offering extensible frameworks for multimodal interaction and community contributions, such as an agent marketplace and plugin ecosystem.Starting Price: $9.90 per month -
14
Opera Browser Operator
Opera
Opera is introducing its innovative Browser Operator, a feature that represents a significant step toward agentic browsing. With this AI-driven tool, Opera becomes the first major browser to perform tasks for users, allowing them to delegate tasks such as purchasing products or managing web interactions through natural language commands. Browser Operator uses AI to carry out these tasks in real time while maintaining user privacy by keeping data locally on the device, without relying on cloud or virtual machine processing. This feature is part of Opera’s larger vision to shift the role of the browser from merely a display engine to an active assistant that helps users save time and enhance productivity.Starting Price: Free -
15
TruGen AI
TruGen AI
TruGen AI transforms conversational agents into fully immersive, human-like video agents that can see, hear, respond, and act in real time, offering hyper-realistic avatars with expressive faces, eye contact, and natural body/face animations. These agents are powered by two core models: a video-avatar model that generates real-time, high-fidelity facial animation, and a vision model that enables context- and emotion-aware interaction (e.g., face recognition, action detection). Through a developer-first, API-based platform, you can embed these video agents into websites or apps in just a few lines of code. Once deployed, agents respond with sub-second latency, carry conversational memory, integrate with a knowledge base, and can call custom APIs or tools, allowing them to deliver context-aware, brand-consistent responses or execute actions rather than just chat.Starting Price: $28 per month -
16
happycapy
happycapy
happycapy is an agent-native AI platform that turns your browser into a powerful “agent computer,” enabling developers and users to deploy and run autonomous AI agents 24/7 without traditional server infrastructure, letting you delegate work across hundreds of large language models (LLMs) and AI services such as Claude Code in a secure, sandboxed environment. It supports running multiple AI agents in parallel to handle coding, automation, data-processing, and custom workflows continuously, giving teams a unified interface for orchestrating, scaling, and monitoring agent tasks. happycapy emphasizes flexibility and developer control by providing a private sandbox where agents can execute jobs, interact with code and data, and collaborate on complex tasks while managing state, logs, and outputs from AI services. It simplifies building and maintaining AI-powered applications by abstracting the complexity of infrastructure and model orchestration.Starting Price: $17 per month -
17
Cua
Cua
Cua is a computer-use agent platform that lets AI agents see screens, click buttons, type, and run code just like a human across macOS, Windows, Linux, browsers, and mobile environments. It provides cloud-based, sandboxed desktops where agents can automate real software workflows without relying on APIs. Built on open-source Cua agents, the platform enables developers to build, run, and scale computer-use agents with precision and reliability. Cua supports multi-step tasks, structured outputs, and human-in-the-loop recovery for complex automation. Agents operate in fully isolated environments to ensure safety and reproducibility. Cua is designed to make AI interaction with real applications practical and scalable.Starting Price: $10/month -
18
OpenAI Codex
OpenAI
Codex is an AI-powered coding agent from OpenAI designed to help developers build, manage, and ship software more efficiently across the entire development lifecycle. It acts as an intelligent pair programmer that can understand codebases, generate features, and deliver production-ready pull requests. Codex can safely execute commands in sandboxed environments while assisting with debugging, refactoring, and testing. A key advancement is its computer use capability, allowing it to operate your computer by seeing, clicking, and typing across applications. This enables Codex to interact with tools that don’t have APIs, making it useful for tasks like frontend testing and app navigation. The platform also includes an in-app browser and integrations with various developer tools for a more unified workflow. Codex supports automation by handling ongoing tasks such as monitoring, issue triage, and follow-ups. -
19
Agent S
Simular
Agent S is an open-source agentic framework built to enable autonomous computer use through an Agent-Computer Interface (ACI). It allows AI agents to operate graphical user interfaces similarly to humans by perceiving screens, reasoning through objectives, and executing actions across macOS, Windows, and Linux systems. The latest release, Agent S3, achieves state-of-the-art results on the OSWorld benchmark and surpasses human-level performance in complex multi-step computer tasks. By combining powerful foundation models such as GPT-5 with grounding models like UI-TARS, the framework translates visual inputs into accurate executable commands. Agent S supports multiple deployment options, including CLI, SDK, and cloud environments. It integrates seamlessly with leading model providers such as OpenAI, Anthropic, Gemini, Azure, and Hugging Face endpoints. -
20
Ace
General Agents
Ace is a computer autopilot that performs tasks on your desktop using your mouse and keyboard. Ace outperforms other models on our suite of computer use tasks, which we are open-sourcing here. We're making the ace-control models available to selected partners through our developer platform. Ace works like we do, performing mouse clicks and keystrokes based on the screen and prompt, trained by our team of software specialists and domain experts on over a million tasks. Ace outperforms other models on our suite of computer use tasks. We're making the ace-control models available to selected partners through our developer platform. Ace is a computer autopilot that performs tasks on your desktop using your mouse and keyboard. -
21
Chrome Sidekick
Chrome Sidekick
Chrome Sidekick is a browser extension that acts as an AI sidebar agent embedded in every webpage. It sees both the page’s HTML and visual content and can explain pages, automatically extract data, run workflows, and automate multi-step tasks. Users can save instructions as reusable Workflows, connect to external apps via MCP (a connector protocol), and interact with them via voice commands for hands-free operation. The assistant maintains memory, so it remembers context over time and can handle follow-up tasks. It supports switching among AI models, custom API keys, light/dark mode, and remote control via Cursor or Claude Desktop. Chrome Sidekick essentially accompanies you on every page, letting you ask questions about the current website, automate actions, and extract info without frequent switching.Starting Price: $9 per month -
22
Dendrite
Dendrite
Dendrite is a framework-agnostic platform that empowers developers to create web-based tools for AI agents, enabling them to authenticate, interact with, and extract data from any website. By simulating human-like browsing behavior, Dendrite facilitates seamless web navigation and data retrieval for AI applications. The platform offers a Python SDK, providing developers with the necessary tools to build AI agents capable of performing tasks such as interacting with web elements and extracting information. Dendrite's flexibility allows it to integrate with any tech stack, making it a versatile solution for developers aiming to enhance their AI agents' web interaction capabilities. Your Dendrite client syncs with website authentication sessions in your local browser, no need to share or store login credentials. Use our Chrome Extension, Dendrite Vault, to securely share authentication sessions from your browser with the Dendrite client. -
23
MyClaw
MyClaw
MyClaw is a managed cloud hosting platform for OpenClaw (formerly Clawdbot/Moltbot) that delivers a personal AI assistant running 24/7 with zero setup or DevOps required, letting users deploy a fully private, always-on instance of the open-source AI agent in minutes without technical configuration. It gives you your own dedicated AI agent in an isolated container that’s online around the clock, with updates, scaling, maintenance, security, and backups handled for you so you can simply log in and use it. The underlying OpenClaw assistant is a powerful open source AI capable of interacting with your digital environment, controlling applications, automating workflows, managing files, browsing the web, triaging email, automating repetitive tasks, and executing developer-oriented jobs like reviewing and refactoring code based on natural language instructions.Starting Price: $19 per month -
24
01.AI
01.AI
The 01.AI Super Employee platform transforms enterprise operations with AI agents capable of deep reasoning, task planning, and end-to-end execution. Through its centralized Solution Console, organizations can manage knowledge bases, train custom models, and deploy business-ready AI solutions with ease. Built for enterprise security, it supports on-premise deployment, secure sandboxing, and MCP connectivity for controlled access to legacy systems and external tools. 01.AI offers a comprehensive suite of industry-specific agents—from sales and insurance to supply chain, finance, and government—each designed to automate workflows across browsers, terminals, cloud phones, and interpreters. With native support for leading LLMs like DeepSeek, Qwen, and Yi, businesses gain a flexible and future-ready AI stack. The platform accelerates AI adoption by enabling rapid deployment, continuous evolution, and seamless integration across enterprise environments. -
25
potpie
potpie
Potpie is an open source platform that enables developers to create AI agents tailored to their codebases, automating tasks such as debugging, testing, system design, onboarding, code review, and documentation. By transforming your codebase into a comprehensive knowledge graph, Potpie's agents gain deep contextual understanding, allowing them to perform engineering tasks with high precision. It offers over five ready-to-use agents, including those specialized in stack trace analysis and integration test generation. Developers can also build custom agents using simple prompts, facilitating seamless integration into existing workflows. Potpie provides a user-friendly chat interface and supports a VS Code extension for direct integration into development environments. With features like multi-LLM support, developers can integrate various AI models to optimize performance and flexibility.Starting Price: $ 1 per month -
26
ai.com
ai.com
ai.com is a decentralized platform focused on accelerating the arrival of artificial general intelligence through autonomous AI agents. It allows users to claim a unique ai.com username and launch their own AI agent. The platform is built around a network of self-improving agents designed to perform real-world tasks. ai.com emphasizes decentralization to promote openness, resilience, and shared progress. Its mission is centered on advancing AI for the good of humanity. Users can join during the beta phase to secure their AI identity early. ai.com introduces a new model for building and deploying AI at scale. -
27
Claude Managed Agents
Anthropic
Claude Managed Agents is a pre-built, configurable agent system from Anthropic designed to run long-running, asynchronous tasks on managed infrastructure without requiring developers to build their own agent loops. It acts as a complete “agent harness,” allowing developers to define goals while the system handles execution, orchestration, and state management behind the scenes. Unlike direct model prompting, which requires step-by-step interaction, Managed Agents are designed for tasks that unfold over time, such as research, automation, or multi-step workflows, where the agent can continue working independently after being started. It supports advanced capabilities such as multi-agent orchestration, where a primary agent can coordinate specialized sub-agents that operate in parallel with isolated contexts, improving both speed and output quality. -
28
ChatGPT Agent
OpenAI
ChatGPT Agent is OpenAI’s next-generation AI assistant that can autonomously perform complex tasks using its own virtual computer. It can navigate websites, interact with apps, run code, and generate outputs such as editable slideshows and spreadsheets—all based on user instructions. By combining capabilities from earlier tools like Operator and deep research, it handles tasks from start to finish with fluid reasoning and action. Users stay in control, able to intervene, pause, or stop tasks anytime, with explicit permission required before significant actions. The agent integrates with apps like Gmail and GitHub, allowing it to access and act on real data securely. This powerful tool enhances productivity in both professional and personal settings by automating workflows and delivering comprehensive results. -
29
Clawd.run
Clawd.run
Clawd.run is a platform to build and deploy AI agents that can perform real tasks using large language models like Claude, GPT-4, Grok, or Gemini, combining web search, memory, file analysis, and automation into customizable assistants. Users can create agents with defined personalities and purposes, connect them to messaging channels such as Discord, WhatsApp, or the platform’s web chat, and start interacting in minutes without needing extensive infrastructure. Agents on Clawd.run have private data storage, don’t train on your conversations, and remember past interactions to become more helpful over time while offering advanced capabilities like research synthesis, content generation, and data extraction from documents. It provides simple setup steps (name the agent, link the channel, start chatting), supports file uploads for insight extraction, and lets users assign tasks as if the agent were an assistant that can help research, write, code, and analyze.Starting Price: $29 per month -
30
EasyClaw
EasyClaw
EasyClaw is a desktop application that simplifies installing and running the OpenClaw autonomous AI agent stack locally without requiring DevOps, Python, Docker, or configuration work, offering a one-click setup and a graphical dashboard that gets your agent operating across popular messaging platforms rapidly. Once installed, EasyClaw manages the OpenClaw runtime and connects your AI agent (such as ClawdBot and MoltBot) to chat apps like WhatsApp, Telegram, Signal, and iMessage so you can interact with your assistant via natural language through familiar channels. It runs natively on your computer with all execution happening locally to preserve privacy and data security, letting the agent automate tasks ranging from inbox orchestration and document summarization to reminders, real-time translation, price comparisons, and other custom workflows without cloud dependencies. -
31
Dyna.Ai
Dyna.Ai
Dyna.Ai is an enterprise-grade AI agent platform and AI-as-a-Service solution designed to transform business and customer operations by combining conversational AI, generative models, and autonomous agents that can understand and act on complex tasks across channels and languages. It enables organizations to build, train, and deploy AI employees and agent applications such as conversational assistants, voice and avatar interactions, customer engagement bots, knowledge partners, and automated task executors that operate 24/7 with adaptive, analytical, and proactive behavior. It includes tools like Agent Studio, VoiceGPT, and AvatarGPT for developing intelligent agents, and is tailored to industry domains including banking, lending, insurance, wealth management, telecom, contact centers, and BPO operations. Dyna.Ai focuses on scalable automation that integrates with existing systems, supports real-time decisioning, and improves operational efficiency. -
32
Sightify AI Agents
Sightify
Sightify | AI Agents is an LLM AI SaaS intended to automate SME workflows while ensuring data sovereignty. Some features include: Data-Sovereign Agents: Fine-tuned w/ RAG on open-source LLMs for specific business process optimization No AI Hallucinations: Source, page, and section citations for database-enforced tokens Multimodal: PDF, Excel, Word, TXT, PNG/JPEG, etc. CRM/ERP System Integration: API documentation, MCP compliant, R&D integration/support Updatable LLMs: Constant New Version Implementations (Qwen 70B, Gemma 27B) Our current AI Agents are: Knowledge Assistant: For client relationship management, HR/company regulations search, etc Contract Finalizer: Finalize legal contracts that are sent to or received from clients/partners Report Generator: Instant monthly/annual sales/marketing/budget reports Market Researcher: Research and analyze enterprise competitors, products, pricing, etc Meeting Notetaker: Employ LLM AI on audio-generated meeting notesStarting Price: $300/year/agent -
33
Mastra AI
Mastra AI
Mastra is a powerful TypeScript framework for building intelligent AI agents that can execute tasks, access knowledge bases, and maintain memory persistently within workflows. This framework simplifies the process of creating and deploying AI-powered agents by leveraging TypeScript’s capabilities to streamline development. With features like customizable agent instructions, memory, and task orchestration, Mastra provides developers with the tools to build and scale AI agents for various applications, from personal assistants to specialized domain experts.Starting Price: Free -
34
Shipable
Shipable
Shipable is a no-code AI agent platform designed to help agencies and consultants quickly build, customize, and deploy production-ready AI assistants for support, sales, onboarding, lead generation, and more across chat, voice, and embedded app environments. It enables the creation of complex, multilingual workflows without developers by combining system prompts, app integrations (email, CRM, internal tools), and payment or domain embedding in a simple visual builder. Agency teams can spin up lead-gen bots in minutes, which used to take days and multiple tools, as easily as cloning and modifying templates. With support for customer-facing voice functionality (including Arabic), Shipable scales from solo operators to larger studios, delivering robust, secure, and revenue-driving AI experiences with minimal overhead and engineering effort.Starting Price: $35 per month -
35
Project Mariner
Google DeepMind
Project Mariner is a research prototype developed by Google DeepMind, built upon their advanced AI model, Gemini 2.0. It explores the future of human-agent interaction by automating tasks within a user's browser. Leveraging multimodal understanding, Project Mariner comprehends and reasons across various browser elements, including text, code, images, and forms. This enables it to navigate complex websites, automate repetitive tasks, and provide visual feedback to users. The system can interpret voice instructions and offers updates on task progress, ensuring users remain informed and in control. Additionally, Project Mariner can follow complex instructions by breaking them down into actionable steps, understanding relationships between web elements, and providing clear plans and actions to users. Currently, Project Mariner is in the testing phase with a select group of trusted users. Those interested in participating can join the waitlist for future testing opportunities. -
36
Open Agent Studio
Cheat Layer
Open Agent Studio is not just another co-pilot it's a no-code co-pilot builder that enables solutions that are impossible in all other RPA tools today. We believe these other tools will copy this idea, so our customers have a head start over the next few months to target markets previously untouched by AI with their deep industry insight. Subscribers have access to a free 4-week course, which teaches how to evaluate product ideas and launch a custom agent with an enterprise-grade white label. Easily build agents by simply recording your keyboard and mouse actions, including scraping data and detecting the start node. The agent recorder makes it as easy as possible to build generalized agents as quickly as you can teach how to do it. Record once, then share across your organization to scale up future-proof agents. -
37
Opera Neon
Opera
Opera Neon is an agentic web browser designed to understand your intent and assist you in completing tasks seamlessly. It features AI-powered chat, smart automation to perform routine web actions, and advanced content creation tools. Opera Neon helps you work smarter by integrating intelligent agents directly into your browsing experience.Starting Price: $19.90/month -
38
Noesent
Noesent
Noesent is a multi-agent AI platform that automates critical fintech operations such as payment routing, reconciliation, support, and fraud detection. It replaces manual workflows with intelligent agents specialized in specific tasks—like Camilla for transaction verification and Monica for invoice matching—helping teams save hours daily. The system integrates securely with your existing stack and complies with top industry security standards, including ISO 27001 and 9001. Noesent’s agents work together on a centralized platform to accelerate workflows and reduce operational backlogs by up to 70%. With early access to new AI agents and direct support from founders, it delivers fast, measurable ROI. Noesent is trusted by fintechs, payment service providers, and banks worldwide. -
39
nanobot
nanobot
nanobot is an open source, ultra-lightweight personal AI assistant framework designed to deliver the core agent loop and autonomous AI capabilities in a minimal, readable codebase, approximately ~3,400–4,000 lines of Python, which is ~99% smaller than comparable large agent frameworks. It’s intentionally simple and modular, making it easy to understand, extend, and experiment with for research or custom projects. nanobot supports persistent memory, scheduled tasks, built-in tools, and integration with multiple large language models (via OpenRouter or other providers), and can run locally or be deployed quickly with CLI commands; it also offers optional real-time web search and multi-platform chat interfaces (e.g., Telegram, Discord, WhatsApp, Feishu) so you can interact with the agent from different environments. Its minimal footprint enables fast startup, low resource use, and a clean architecture that developers can adapt without heavy abstractions. -
40
HubSpot Breeze AI
HubSpot
HubSpot's Breeze AI is an advanced suite of artificial intelligence tools designed to boost productivity and efficiency for marketing, sales, and customer service teams. It includes Breeze Copilot, an in-app AI assistant that helps with tasks across HubSpot's platform; Breeze Agents, AI-powered experts that handle marketing, sales, and customer service tasks typically performed by humans; and Breeze Intelligence, which enriches contact and company data while identifying buyer intent to target the right leads effectively. These features are seamlessly integrated throughout HubSpot’s ecosystem, delivering a comprehensive AI-powered solution for customer-facing teams to work smarter and achieve better results. -
41
ConnexAI
ConnexAI
ConnexAI's advanced AI agent utilizes our proprietary Athena LLM to adapt to your CX needs. Leverage AI Agents to automate repetitive tasks, handle complex inquiries, and provide instant, round-the-clock support, freeing up much-needed financial resources to be critically redistributed. AI Agent optimizes interaction handling, inquiry servicing, and freeing your users to focus their time on the most sensitive interactions. Revolutionizes customer interactions with human-like, efficient communication, setting a new standard unparalleled when using chatbots. Dramatically reduces time and admin costs by ensuring that each interaction is handled promptly and effectively. Train your AI agents with ease by preloading them with contextual information and documentation, creating a highly knowledgeable, contextually savvy workforce. AI agent operates round-the-clock, increasing CSAT by ensuring customers receive timely assistance and information. -
42
Android Use
Action State Labs
Action State Labs develops infrastructure for native Android AI agents, including an open-source driver called Android Use that lets AI agents interact with native Android apps reliably and efficiently by connecting directly to the Android Accessibility Tree instead of relying on brittle computer vision methods. This approach enables AI agents to read and control app UIs with higher speed, lower cost (up to ~95% cheaper), and greater robustness against UI changes, making it easier to automate complex workflows like logistics, field operations, and other tasks traditionally done in native mobile apps. It includes an open source core that runs on local devices or emulators and a managed cloud option with auto-scaling for enterprise use, API endpoints, and support services, letting developers build, test, and deploy agent-powered automation workflows across many devices concurrently.Starting Price: Free -
43
Kilo Code
Kilo Code
Kilo Code is a powerful open-source coding agent designed to help developers build, ship, and iterate faster across every stage of the software development workflow. It offers multiple modes—including Ask, Architect, Code, Debug, and Orchestrator—so developers can switch seamlessly between tasks with tailored AI support. The platform includes features such as hallucination-free code, automatic failure recovery, and deep context awareness to ensure accuracy and reliability. Developers can run parallel agents, enjoy fast autocomplete, and even deploy applications with a single click. With access to 500+ models and integration across terminals, VS Code, and JetBrains editors, Kilo provides unmatched flexibility. As the #1 agent on OpenRouter with over 750,000 users, it has quickly become a preferred choice for modern AI-assisted development.Starting Price: $15/user/month -
44
Qwen Code
Qwen
Qwen3‑Coder is an agentic code model available in multiple sizes, led by the 480B‑parameter Mixture‑of‑Experts variant (35B active) that natively supports 256K‑token contexts (extendable to 1M) and achieves state‑of‑the‑art results on Agentic Coding, Browser‑Use, and Tool‑Use tasks comparable to Claude Sonnet 4. Pre‑training on 7.5T tokens (70 % code) and synthetic data cleaned via Qwen2.5‑Coder optimized both coding proficiency and general abilities, while post‑training employs large‑scale, execution‑driven reinforcement learning and long‑horizon RL across 20,000 parallel environments to excel on multi‑turn software‑engineering benchmarks like SWE‑Bench Verified without test‑time scaling. Alongside the model, the open source Qwen Code CLI (forked from Gemini Code) unleashes Qwen3‑Coder in agentic workflows with customized prompts, function calling protocols, and seamless integration with Node.js, OpenAI SDKs, and more.Starting Price: Free -
45
API Agent
IBM
API Agent in IBM API Connect is a watsonx.ai–powered assistant that automates core tasks across the entire API lifecycle via a natural‑language, conversational interface. Built on an agentic framework, it lets teams rapidly generate OpenAPI specifications, mocked responses, and rich documentation for design‑first projects, or connect to backend data sources, build application code, and auto‑deploy to Code Engine for code‑first workflows, all without manual setup. To combat API sprawl, API Agent intelligently searches your existing API catalog by simple description prompts, recommending reusable endpoints and reducing duplication. It enforces governance by validating specs against organizational rulesets, suggesting or applying fixes automatically, and boosts quality with a built‑in testing suite that generates and runs semantic test cases to catch issues early. -
46
Amazon Nova Act
Amazon
Amazon Nova Act is an AI model designed to perform actions within web browsers, enabling the development of agents capable of completing tasks such as submitting out-of-office requests, scheduling calendar events, and setting up 'away from office' emails. Unlike traditional large language models that primarily generate natural language responses, Nova Act focuses on executing tasks in digital environments. The Nova Act SDK allows developers to decompose complex workflows into reliable atomic commands (e.g., search, checkout, answer questions about the screen) and incorporate detailed instructions where necessary. It also supports API calls and direct browser manipulation through Playwright to enhance reliability. Developers can integrate Python code, including tests, breakpoints, asserts, or thread pools for parallelization, to manage web page load times effectively. -
47
SmythOS
SmythOS
Say goodbye to manual coding and build agents faster than ever. Describe what you need, and SmythOS builds it from your chat or image, using the best AI models and APIs for your task. Use any AI model or API. Integrate with OpenAI, Hugging Face, Amazon Bedrock, and hundreds of vendors without a line of code. A pre-built agent template library gives you agents that already work out of the box for dozens of use cases. Just hit the button and connect with your own API keys. Because your marketing team should not have access to agents that work with your code. We got you covered. Create a space for each client, team, and project with full user and permission management. Deploy on-prem or to AWS. Integrate with Bedrock, Vertex, Adobe, Salesforce, etc. Explainable AI with full control over data flows, audit logs, encryption, and auth. Chat with your agents, give them bulk work, inspect their work logs, assign them work schedules, and more.Starting Price: $30 per month -
48
newo.ai
Newo Inc.
Newo.ai is a low-code platform where developers create advanced, human-level intelligent agents with omnichannel communication, outperforming other builders by 10x. Dubbed "the WordPress for AI Agents," it allows the development of Digital Employees, Workers, and AI-assistants without programming skills. Unique to Newo.ai, these AI agents can be integrated with VoIP channels, smart speakers, and robots for tasks like reception hosting and system management, while aligning with corporate guidelines and enhancing service offerings. Types of Digital Workers created include AI Concierge, Hostess, Receptionist, Technical Support, Sales Consultant, Assistant, Financial Advisor, and HR operations, among others.Starting Price: $99/month -
49
DemoGPT
Melih Ünsal
DemoGPT is an open source platform that simplifies the creation of LLM (Large Language Model) agents by providing an all-in-one toolkit. It offers tools, frameworks, prompts, and models for rapid agent development. The platform automatically generates LangChain code, which can be used for creating interactive applications with Streamlit. DemoGPT translates user instructions into functional applications through a multi-step process: planning, task creation, and code generation. It supports a streamlined approach to building AI-powered agents, offering an accessible environment for developing sophisticated, production-ready solutions with GPT-3.5-turbo. Additionally, it integrates API usage and external API interaction in future updates.Starting Price: Free -
50
Agent Zero
Agent Zero
Agent Zero is an open source AI agent framework designed to run autonomous AI assistants that can perform complex tasks by interacting directly with a computer system. It provides an environment where AI agents operate with real system access, allowing them to execute commands, write and run code, browse the web, analyze data, and manage workflows as part of real-world automation processes. Instead of functioning as a simple chat interface, Agent Zero runs in its own virtual environment where it can interact with the operating system, install tools, execute scripts, and coordinate tasks across multiple components. It emphasizes transparency and control, allowing developers to view, modify, and customize how the agent behaves, what tools it can access, and how it processes information. Agent Zero uses a modular architecture that allows the agent to dynamically create and use tools while maintaining persistent memory.Starting Price: $2.65 per month
